diff --git a/.gitignore b/.gitignore index c3eabc17..4ba2204f 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,4 @@ +junk/ .vscode/ data/** notebooks/data/** diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_0.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_0.zanj new file mode 100644 index 00000000..97c17b11 Binary files /dev/null and b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_0.zanj differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_15.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_15.zanj new file mode 100644 index 00000000..77ede48d Binary files /dev/null and b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_15.zanj differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_150.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_150.zanj new file mode 100644 index 00000000..77bed960 Binary files /dev/null and b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_150.zanj differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_75.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_75.zanj new file mode 100644 index 00000000..bca69377 Binary files /dev/null and b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/checkpoints/model.iter_75.zanj differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/config.json b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/config.json similarity index 53% rename from examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/config.json rename to examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/config.json index 8ed1e917..4f79801a 100644 --- a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/config.json +++ b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/config.json @@ -3,7 +3,6 @@ "dataset_cfg": { "__format__": "MazeDatasetConfig(SerializableDataclass)", "name": "demo", - "dtype": "torch.int16", "seq_len_min": 1, "seq_len_max": 512, "seed": 42, @@ -12,7 +11,7 @@ "n_mazes": 10000, "maze_ctor": { "__name__": "gen_dfs", - "__module__": "maze_transformer.generation.generators", + "__module__": "maze_dataset.generation.generators", "__doc__": [ "generate a lattice maze using depth first search, iterative", "", @@ -20,13 +19,13 @@ " - `grid_shape: Coord`: the shape of the grid", " - `lattice_dim: int`: the dimension of the lattice", " (default: `2`)", - " - `n_accessible_cells: int | None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid.", + " - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**", " (default: `None`)", - " - `max_tree_depth: int | None`: the maximum depth of the tree. If `None`, defaults to `2 * n_accessible_cells`.", + " - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**", " (default: `None`)", + " - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.", " - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.", "", - "", " # algorithm", " 1. Choose the initial cell, mark it as visited and push it to the stack", " 2. While the stack is not empty", @@ -43,8 +42,10 @@ " def gen_dfs(", " grid_shape: Coord,", " lattice_dim: int = 2,", - " n_accessible_cells: int | None = None,", - " max_tree_depth: int | None = None,", + " accessible_cells: int | float | None = None,", + " max_tree_depth: int | float | None = None,", + " do_forks: bool = True,", + " randomized_stack: bool = False,", " start_coord: Coord | None = None,", " ) -> LatticeMaze:", " \"\"\"generate a lattice maze using depth first search, iterative", @@ -53,13 +54,13 @@ " - `grid_shape: Coord`: the shape of the grid", " - `lattice_dim: int`: the dimension of the lattice", " (default: `2`)", - " - `n_accessible_cells: int | None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid.", + " - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**", " (default: `None`)", - " - `max_tree_depth: int | None`: the maximum depth of the tree. If `None`, defaults to `2 * n_accessible_cells`.", + " - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**", " (default: `None`)", + " - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.", " - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.", "", - "", " # algorithm", " 1. Choose the initial cell, mark it as visited and push it to the stack", " 2. While the stack is not empty", @@ -74,20 +75,33 @@ " # Default values if no constraints have been passed", " grid_shape: Coord = np.array(grid_shape)", " n_total_cells: int = int(np.prod(grid_shape))", - " if n_accessible_cells is None:", + "", + " n_accessible_cells: int", + " if accessible_cells is None:", " n_accessible_cells = n_total_cells", + " elif isinstance(accessible_cells, float):", + " assert (", + " accessible_cells <= 1", + " ), f\"accessible_cells must be an int (count) or a float in the range [0, 1] (proportion), got {accessible_cells}\"", + "", + " n_accessible_cells = int(accessible_cells * n_total_cells)", + " else:", + " assert isinstance(accessible_cells, int)", + " n_accessible_cells = accessible_cells", + "", " if max_tree_depth is None:", " max_tree_depth = (", " 2 * n_total_cells", " ) # We define max tree depth counting from the start coord in two directions. Therefore we divide by two in the if clause for neighboring sites later and multiply by two here.", - " if start_coord is None:", - " start_coord: Coord = np.random.randint(", - " 0,", - " np.maximum(grid_shape - 1, 1),", - " size=2,", - " )", - " else:", - " start_coord = np.array(start_coord)", + " elif isinstance(max_tree_depth, float):", + " assert (", + " max_tree_depth <= 1", + " ), f\"max_tree_depth must be an int (count) or a float in the range [0, 1] (proportion), got {max_tree_depth}\"", + "", + " max_tree_depth = int(max_tree_depth * np.sum(grid_shape))", + "", + " # choose a random start coord", + " start_coord = _random_start_coord(grid_shape, start_coord)", "", " # initialize the maze with no connections", " connection_list: ConnectionList = np.zeros(", @@ -96,7 +110,7 @@ "", " # initialize the stack with the target coord", " visited_cells: set[tuple[int, int]] = set()", - " visited_cells.add(tuple(start_coord))", + " visited_cells.add(tuple(start_coord)) # this wasnt a bug after all lol", " stack: list[Coord] = [start_coord]", "", " # initialize tree_depth_counter", @@ -105,7 +119,11 @@ " # loop until the stack is empty or n_connected_cells is reached", " while stack and (len(visited_cells) < n_accessible_cells):", " # get the current coord from the stack", - " current_coord: Coord = stack.pop()", + " current_coord: Coord", + " if randomized_stack:", + " current_coord = stack.pop(random.randint(0, len(stack) - 1))", + " else:", + " current_coord = stack.pop()", "", " # filter neighbors by being within grid bounds and being unvisited", " unvisited_neighbors_deltas: list[tuple[Coord, Coord]] = [", @@ -124,7 +142,9 @@ " if unvisited_neighbors_deltas and (", " current_tree_depth <= max_tree_depth / 2", " ):", - " stack.append(current_coord)", + " # if we want a maze without forks, simply don't add the current coord back to the stack", + " if do_forks and (len(unvisited_neighbors_deltas) > 1):", + " stack.append(current_coord)", "", " # choose one of the unvisited neighbors", " chosen_neighbor, delta = random.choice(unvisited_neighbors_deltas)", @@ -147,271 +167,31 @@ " else:", " current_tree_depth -= 1", "", - " return LatticeMaze(", + " output = LatticeMaze(", " connection_list=connection_list,", " generation_meta=dict(", " func_name=\"gen_dfs\",", " grid_shape=grid_shape,", " start_coord=start_coord,", - " visited_cells={tuple(int(x) for x in coord) for coord in visited_cells},", " n_accessible_cells=int(n_accessible_cells),", " max_tree_depth=int(max_tree_depth),", - " fully_connected=bool(len(visited_cells) == n_accessible_cells),", + " # oh my god this took so long to track down. its almost 5am and I've spent like 2 hours on this bug", + " # it was checking that len(visited_cells) == n_accessible_cells, but this means that the maze is", + " # treated as fully connected even when it is most certainly not, causing solving the maze to break", + " fully_connected=bool(len(visited_cells) == n_total_cells),", + " visited_cells={tuple(int(x) for x in coord) for coord in visited_cells},", " ),", - " )" + " )", + "", + " return output" ] }, "maze_ctor_kwargs": {}, - "padding_token_index": 10, - "token_arr": [ - "", - "", - "", - "", - "", - "", - "", - "", - "<-->", - ";", - "", - "(0,0)", - "(0,1)", - "(1,0)", - "(1,1)", - "(0,2)", - "(2,0)", - "(1,2)", - "(2,1)", - "(2,2)", - "(0,3)", - "(3,0)", - "(3,1)", - "(2,3)", - "(3,2)", - "(1,3)", - "(3,3)", - "(0,4)", - "(2,4)", - "(4,0)", - "(1,4)", - "(4,1)", - "(4,2)", - "(3,4)", - "(4,3)", - "(4,4)", - "(0,5)", - "(5,0)", - "(5,1)", - "(2,5)", - "(5,2)", - "(5,3)", - "(4,5)", - "(5,4)", - "(1,5)", - "(3,5)", - "(5,5)" - ], - "tokenizer_map": { - "": 0, - "": 1, - "": 2, - "": 3, - "": 4, - "": 5, - "": 6, - "": 7, - "<-->": 8, - ";": 9, - "": 10, - "(0,0)": 11, - "(0,1)": 12, - "(1,0)": 13, - "(1,1)": 14, - "(0,2)": 15, - "(2,0)": 16, - "(1,2)": 17, - "(2,1)": 18, - "(2,2)": 19, - "(0,3)": 20, - "(3,0)": 21, - "(3,1)": 22, - "(2,3)": 23, - "(3,2)": 24, - "(1,3)": 25, - "(3,3)": 26, - "(0,4)": 27, - "(2,4)": 28, - "(4,0)": 29, - "(1,4)": 30, - "(4,1)": 31, - "(4,2)": 32, - "(3,4)": 33, - "(4,3)": 34, - "(4,4)": 35, - "(0,5)": 36, - "(5,0)": 37, - "(5,1)": 38, - "(2,5)": 39, - "(5,2)": 40, - "(5,3)": 41, - "(4,5)": 42, - "(5,4)": 43, - "(1,5)": 44, - "(3,5)": 45, - "(5,5)": 46 - }, + "endpoint_kwargs": {}, "grid_shape": [ 6, 6 - ], - "token_node_map": { - "(0,0)": [ - 0, - 0 - ], - "(0,1)": [ - 0, - 1 - ], - "(1,0)": [ - 1, - 0 - ], - "(1,1)": [ - 1, - 1 - ], - "(0,2)": [ - 0, - 2 - ], - "(2,0)": [ - 2, - 0 - ], - "(1,2)": [ - 1, - 2 - ], - "(2,1)": [ - 2, - 1 - ], - "(2,2)": [ - 2, - 2 - ], - "(0,3)": [ - 0, - 3 - ], - "(3,0)": [ - 3, - 0 - ], - "(3,1)": [ - 3, - 1 - ], - "(2,3)": [ - 2, - 3 - ], - "(3,2)": [ - 3, - 2 - ], - "(1,3)": [ - 1, - 3 - ], - "(3,3)": [ - 3, - 3 - ], - "(0,4)": [ - 0, - 4 - ], - "(2,4)": [ - 2, - 4 - ], - "(4,0)": [ - 4, - 0 - ], - "(1,4)": [ - 1, - 4 - ], - "(4,1)": [ - 4, - 1 - ], - "(4,2)": [ - 4, - 2 - ], - "(3,4)": [ - 3, - 4 - ], - "(4,3)": [ - 4, - 3 - ], - "(4,4)": [ - 4, - 4 - ], - "(0,5)": [ - 0, - 5 - ], - "(5,0)": [ - 5, - 0 - ], - "(5,1)": [ - 5, - 1 - ], - "(2,5)": [ - 2, - 5 - ], - "(5,2)": [ - 5, - 2 - ], - "(5,3)": [ - 5, - 3 - ], - "(4,5)": [ - 4, - 5 - ], - "(5,4)": [ - 5, - 4 - ], - "(1,5)": [ - 1, - 5 - ], - "(3,5)": [ - 3, - 5 - ], - "(5,5)": [ - 5, - 5 - ] - }, - "n_tokens": 47 + ] }, "model_cfg": { "__format__": "BaseGPTConfig(SerializableDataclass)", @@ -420,14 +200,18 @@ "d_model": 32, "d_head": 16, "n_layers": 4, + "positional_embedding_type": "standard", "weight_processing": { "are_layernorms_folded": false, "are_weights_processed": false - } + }, + "n_heads": 2 }, "train_cfg": { "__format__": "TrainConfig(SerializableDataclass)", "name": "sweep-v1", + "evals_max_new_tokens": 8, + "validation_dataset_cfg": 50, "optimizer": "AdamW", "optimizer_kwargs": { "lr": 0.0001 @@ -439,9 +223,66 @@ "persistent_workers": true, "drop_last": true }, - "print_loss_interval": 1000, - "checkpoint_interval": 5000 + "intervals": null, + "intervals_count": null + }, + "name": "multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1", + "pretrainedtokenizer_kwargs": null, + "maze_tokenizer": { + "__format__": "MazeTokenizerModular(SerializableDataclass)", + "prompt_sequencer": { + "__format__": "AOTP(SerializableDataclass)", + "coord_tokenizer": { + "__format__": "UT(SerializableDataclass)", + "_type_": "" + }, + "adj_list_tokenizer": { + "__format__": "AdjListCoord(SerializableDataclass)", + "pre": false, + "post": true, + "shuffle_d0": true, + "edge_grouping": { + "__format__": "Ungrouped(SerializableDataclass)", + "_type_": "", + "connection_token_ordinal": 1 + }, + "edge_subset": { + "__format__": "ConnectionEdges(SerializableDataclass)", + "_type_": "", + "walls": false + }, + "edge_permuter": { + "__format__": "RandomCoords(SerializableDataclass)", + "_type_": "" + }, + "_type_": "" + }, + "_type_": "", + "target_tokenizer": { + "__format__": "Unlabeled(SerializableDataclass)", + "_type_": "", + "post": false + }, + "path_tokenizer": { + "__format__": "StepSequence(SerializableDataclass)", + "_type_": "", + "step_size": { + "__format__": "Singles(SerializableDataclass)", + "_type_": "" + }, + "step_tokenizers": [ + { + "__format__": "Coord(SerializableDataclass)", + "_type_": "" + } + ], + "pre": false, + "intra": false, + "post": false + } + }, + "tokenizer_element_tree_concrete": "MazeTokenizerModular\n\tAOTP\n\t\tUT\n\t\tAdjListCoord\n\t\t\tUngrouped\n\t\t\tConnectionEdges\n\t\t\tRandomCoords\n\t\tUnlabeled\n\t\tStepSequence\n\t\t\tSingles\n\t\t\tCoord\n", + "name": "MazeTokenizerModular-AOTP(UT(), AdjListCoord(pre=F, post=T, shuffle_d0=T, Ungrouped(connection_token_ordinal=1), ConnectionEdges(walls=F), RandomCoords()), Unlabeled(post=F), StepSequence(Singles(), step_tokenizers=(Coord(), ), pre=F, intra=F, post=F))" }, - "name": "multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1", - "pretrainedtokenizer_kwargs": null + "_tokenizer": "None" } \ No newline at end of file diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj new file mode 100644 index 00000000..d05d5956 Binary files /dev/null and b/examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_0.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_0.zanj deleted file mode 100644 index 8a15f2e2..00000000 Binary files a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_0.zanj and /dev/null differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_78.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_78.zanj deleted file mode 100644 index f52cdaeb..00000000 Binary files a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_78.zanj and /dev/null differ diff --git a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj b/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj deleted file mode 100644 index 2749876a..00000000 Binary files a/examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj and /dev/null differ diff --git a/makefile b/makefile index 6a496571..861ce814 100644 --- a/makefile +++ b/makefile @@ -79,6 +79,7 @@ clean: python -Bc "import pathlib; [p.rmdir() for p in pathlib.Path('.').rglob('__pycache__')]" + # listing targets, from stackoverflow # https://stackoverflow.com/questions/4219255/how-do-you-get-the-list-of-targets-in-a-makefile .PHONY: help diff --git a/maze_transformer/evaluation/baseline_models.py b/maze_transformer/evaluation/baseline_models.py index ac7a318c..3a483748 100644 --- a/maze_transformer/evaluation/baseline_models.py +++ b/maze_transformer/evaluation/baseline_models.py @@ -11,12 +11,13 @@ LatticeMaze, SolvedMaze, ) -from maze_dataset.tokenization.token_utils import ( +from maze_dataset.token_utils import ( get_origin_tokens, get_path_tokens, get_target_tokens, + strings_to_coords, ) -from maze_dataset.tokenization.util import strings_to_coords +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular from transformer_lens import HookedTransformer from maze_transformer.training.config import ConfigHolder @@ -195,9 +196,14 @@ def _generate_path( if predictions[-1] == SPECIAL_TOKENS.PATH_END: break - return self.tokenizer._maze_tokenizer.coords_to_strings( - predictions, when_noncoord="include" - ) + if isinstance(self.tokenizer._maze_tokenizer, MazeTokenizer): + return self.tokenizer._maze_tokenizer.coords_to_strings( + predictions, when_noncoord="include" + ) + elif isinstance(self.tokenizer._maze_tokenizer, MazeTokenizerModular): + return self.tokenizer._maze_tokenizer.coords_to_strings( + predictions[:-1] + ) + [SPECIAL_TOKENS.PATH_END] def _process_context( self, diff --git a/maze_transformer/evaluation/eval_model.py b/maze_transformer/evaluation/eval_model.py index 5d8ddd85..223eca1c 100644 --- a/maze_transformer/evaluation/eval_model.py +++ b/maze_transformer/evaluation/eval_model.py @@ -14,14 +14,14 @@ MazeDatasetConfig, SolvedMaze, ) -from maze_dataset.tokenization import MazeTokenizer -from maze_dataset.tokenization.token_utils import ( +from maze_dataset.token_utils import ( get_context_tokens, get_path_tokens, remove_padding_from_token_str, + strings_to_coords, ) -from maze_dataset.tokenization.util import strings_to_coords -from maze_dataset.utils import WhenMissing +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular +from muutils.misc import WhenMissing # muutils from muutils.mlutils import chunks @@ -143,7 +143,7 @@ def predict_maze_paths( smart_max_new_tokens ), "if max_new_tokens is None, smart_max_new_tokens must be True" - maze_tokenizer: MazeTokenizer = model.tokenizer._maze_tokenizer + maze_tokenizer: MazeTokenizer | MazeTokenizerModular = model.config.maze_tokenizer contexts_lists: list[list[str]] = [ get_context_tokens(tokens) for tokens in tokens_batch diff --git a/maze_transformer/evaluation/eval_single_token_tasks.py b/maze_transformer/evaluation/eval_single_token_tasks.py index 018a6101..0b99b7d2 100644 --- a/maze_transformer/evaluation/eval_single_token_tasks.py +++ b/maze_transformer/evaluation/eval_single_token_tasks.py @@ -12,7 +12,7 @@ # Our Code # dataset stuff from maze_dataset import MazeDataset -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular from muutils.json_serialize import SerializableDataclass, serializable_dataclass # TransformerLens imports @@ -47,7 +47,7 @@ class TaskEvalResult(SerializableDataclass): def get_task_prompts_targets( dataset: MazeDataset, - maze_tokenizer: MazeTokenizer, + maze_tokenizer: MazeTokenizer | MazeTokenizerModular, tasks: dict[str, DLAProtocolFixed] = LOGIT_ATTRIB_TASKS, ) -> dict[str, TaskPrompt]: dataset_tokens: list[list[str]] = dataset.as_tokens( @@ -63,7 +63,7 @@ def eval_model_task( task: TaskPrompt, do_cache: bool = False, ) -> TaskEvalResult: - maze_tokenizer: MazeTokenizer = model.tokenizer._maze_tokenizer + maze_tokenizer: MazeTokenizer | MazeTokenizerModular = model.config.maze_tokenizer prompts_joined: list[str] = [" ".join(prompt) for prompt in task.prompts] diff --git a/maze_transformer/mechinterp/direct_logit_attribution.py b/maze_transformer/mechinterp/direct_logit_attribution.py index f0ce80ef..4f1630f9 100644 --- a/maze_transformer/mechinterp/direct_logit_attribution.py +++ b/maze_transformer/mechinterp/direct_logit_attribution.py @@ -13,7 +13,7 @@ # maze-datset stuff from maze_dataset import MazeDataset, MazeDatasetConfig -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular # TransformerLens imports from transformer_lens import ActivationCache @@ -226,7 +226,9 @@ def create_report( # model and tokenizer if not isinstance(model, ZanjHookedTransformer): model = ZanjHookedTransformer.read(model) - tokenizer: MazeTokenizer = model.zanj_model_config.maze_tokenizer + tokenizer: MazeTokenizer | MazeTokenizerModular = ( + model.zanj_model_config.maze_tokenizer + ) # dataset cfg if dataset_cfg_source is None: diff --git a/maze_transformer/mechinterp/plot_attention.py b/maze_transformer/mechinterp/plot_attention.py index 43f319b6..7d3a0e0f 100644 --- a/maze_transformer/mechinterp/plot_attention.py +++ b/maze_transformer/mechinterp/plot_attention.py @@ -18,8 +18,8 @@ from maze_dataset.plotting import MazePlot from maze_dataset.plotting.plot_tokens import plot_colored_text from maze_dataset.plotting.print_tokens import color_tokens_cmap -from maze_dataset.tokenization import MazeTokenizer -from maze_dataset.tokenization.util import coord_str_to_tuple_noneable +from maze_dataset.token_utils import coord_str_to_tuple_noneable +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular # Utilities from muutils.json_serialize import SerializableDataclass, serializable_dataclass @@ -377,7 +377,7 @@ def mazeplot_attention( def plot_attn_dist_correlation( tokens_context: list[list[str]], tokens_dist_to: list[str], # either current or target token for each maze - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, attention: Float[np.ndarray, "n_mazes n_tokens"], ax: plt.Axes | None = None, respect_topology: bool = False, # manhattan distance if False @@ -480,7 +480,7 @@ def plot_attention_final_token( prompts: list[list[str]], targets: list[str], mazes: list[SolvedMaze], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, n_mazes: int = 5, last_n_tokens: int = 20, # exponentiate_scores: bool = False, diff --git a/maze_transformer/mechinterp/plot_logits.py b/maze_transformer/mechinterp/plot_logits.py index e3e77800..bac9c259 100644 --- a/maze_transformer/mechinterp/plot_logits.py +++ b/maze_transformer/mechinterp/plot_logits.py @@ -6,7 +6,7 @@ from maze_dataset import CoordTup # Our Code -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular _DEFAULT_SUBPLOTS_KWARGS: dict = dict( figsize=(20, 20), @@ -86,7 +86,7 @@ def plot_logit_histograms( def get_baseline_incorrect_group( prompts: list[list[str]], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, baseline: "RandomBaseline", ) -> Bool[torch.Tensor, "n_mazes d_vocab"]: """ @@ -116,7 +116,7 @@ def get_baseline_incorrect_group( def plot_logits( last_tok_logits: Float[torch.Tensor, "n_mazes d_vocab"], target_idxs: Int[torch.Tensor, "n_mazes"], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, n_bins: int = 50, mark_incorrect: bool = False, mark_correct: bool = True, diff --git a/maze_transformer/mechinterp/residual_stream_structure.py b/maze_transformer/mechinterp/residual_stream_structure.py index 36c6b4d9..109d8f54 100644 --- a/maze_transformer/mechinterp/residual_stream_structure.py +++ b/maze_transformer/mechinterp/residual_stream_structure.py @@ -11,8 +11,8 @@ # maze_dataset from maze_dataset.constants import _SPECIAL_TOKENS_ABBREVIATIONS -from maze_dataset.tokenization import MazeTokenizer -from maze_dataset.tokenization.util import strings_to_coords +from maze_dataset.token_utils import strings_to_coords +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular # scipy from scipy.spatial.distance import pdist, squareform @@ -52,7 +52,9 @@ def coordinate_to_color( ) -def process_tokens_for_pca(tokenizer: MazeTokenizer) -> list[TokenPlottingInfo]: +def process_tokens_for_pca( + tokenizer: MazeTokenizer | MazeTokenizerModular, +) -> list[TokenPlottingInfo]: tokens_coords: list[str | tuple[int, int]] = strings_to_coords( tokenizer.token_arr, when_noncoord="include" ) @@ -227,7 +229,7 @@ def abs_dot_product(u, v): def compute_distances_and_correlation( embedding_matrix: Float[np.ndarray, "d_vocab d_model"], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, embedding_metric: str = "cosine", coordinate_metric: str = "euclidean", show: bool = True, @@ -277,7 +279,7 @@ def compute_distances_and_correlation( def plot_distances_matrix( embedding_distances_matrix: Float[np.ndarray, "n_coord_tokens n_coord_tokens"], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, embedding_metric: str, show: bool = True, **kwargs, @@ -313,7 +315,7 @@ def plot_distances_matrix( def compute_grid_distances( embedding_distances_matrix: Float[np.ndarray, "n_coord_tokens n_coord_tokens"], - tokenizer: MazeTokenizer, + tokenizer: MazeTokenizer | MazeTokenizerModular, ) -> Float[np.ndarray, "n n n n"]: n: int = tokenizer.max_grid_size grid_distances: Float[np.ndarray, "n n n n"] = np.full((n, n, n, n), np.nan) diff --git a/maze_transformer/tokenizer.py b/maze_transformer/tokenizer.py index 6a577f09..a422b50e 100644 --- a/maze_transformer/tokenizer.py +++ b/maze_transformer/tokenizer.py @@ -4,7 +4,7 @@ import torch from maze_dataset import SPECIAL_TOKENS, LatticeMaze from maze_dataset.plotting import MazePlot -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular from muutils.tensor_utils import ATensor, NDArray from transformers import PreTrainedTokenizer from transformers.tokenization_utils import BatchEncoding @@ -46,13 +46,13 @@ def apply_overrides(self) -> None: def __init__( self, seq_len_max: int, - maze_tokenizer: MazeTokenizer, + maze_tokenizer: MazeTokenizer | MazeTokenizerModular, **kwargs, ) -> None: """extension of PreTrainedTokenizer for mazes. takes maximum sequence length and maze_tokenizer. also, kwargs are passed to super `PreTrainedTokenizer`""" super().__init__(max_len=seq_len_max, **kwargs) - self._maze_tokenizer: MazeTokenizer = maze_tokenizer + self._maze_tokenizer: MazeTokenizer | MazeTokenizerModular = maze_tokenizer token_arr: list[str] = maze_tokenizer.token_arr self._token_arr: list[str] = token_arr self._seq_len_max: int = seq_len_max @@ -81,13 +81,17 @@ def __init__( # We are having to do evil things here vocab: dict[str, int] = {token: i for i, token in enumerate(token_arr)} - vocab[self.unk_token] = len(vocab) - self.vocab: dict[str, int] = vocab - - special_tokens = list(SPECIAL_TOKENS.values()) - normal_tokens = [x for x in token_arr if x not in special_tokens] - self._add_tokens(normal_tokens) - self._add_tokens(special_tokens) + if self.unk_token not in vocab: # maze-dataset ^1.0.0 includes already + vocab[self.unk_token] = len(vocab) + self.vocab: dict[str, int] = vocab + + if isinstance(self._maze_tokenizer, MazeTokenizer): + special_tokens = list(SPECIAL_TOKENS.values()) + normal_tokens = [x for x in token_arr if x not in special_tokens] + self._add_tokens(normal_tokens) + self._add_tokens(special_tokens) + elif isinstance(self._maze_tokenizer, MazeTokenizerModular): + self._add_tokens(token_arr) self.unique_no_split_tokens = token_arr # Trie is updated automatically? diff --git a/maze_transformer/training/config.py b/maze_transformer/training/config.py index c1c88cb3..01dced14 100644 --- a/maze_transformer/training/config.py +++ b/maze_transformer/training/config.py @@ -1,5 +1,6 @@ from __future__ import annotations +import copy import json import typing import warnings @@ -10,7 +11,7 @@ import torch from maze_dataset.dataset.configs import MAZE_DATASET_CONFIGS from maze_dataset.dataset.dataset import GPTDatasetConfig -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular from muutils.dictmagic import kwargs_to_nested_dict from muutils.json_serialize import ( JSONitem, @@ -385,19 +386,17 @@ def summary(self) -> dict: } -def _load_maze_tokenizer(data: dict) -> MazeTokenizer: +def _load_maze_tokenizer(data: dict) -> MazeTokenizerModular | MazeTokenizer: """load the maze tokenizer, including vocab size from a legacy config""" - if "maze_tokenizer" in data: - # new style tokenizer - return load_item_recursive(data["maze_tokenizer"], path=tuple("maze_tokenizer")) + mt = data.get("maze_tokenizer", None) + if mt is not None: + fmt_str: str = mt.get("__format__", None) + if fmt_str == "MazeTokenizerModular(SerializableDataclass)": + return MazeTokenizerModular.load(mt) + elif fmt_str == "MazeTokenizer(SerializableDataclass)": + return MazeTokenizer.load(mt) else: - if "token_arr" in data["dataset_cfg"]: - output: MazeTokenizer = MazeTokenizer( - tokenization_mode=TokenizationMode.AOTP_UT_rasterized, - max_grid_size=None, - ) - else: - raise ValueError("Could not find vocab size in legacy config") + return None @serializable_dataclass(kw_only=True) @@ -420,7 +419,7 @@ class ConfigHolder(SerializableDataclass): pretrainedtokenizer_kwargs: dict[str, JSONitem] | None = serializable_field( default=None ) - maze_tokenizer: MazeTokenizer | None = serializable_field( + maze_tokenizer: MazeTokenizer | MazeTokenizerModular | None = serializable_field( default_factory=lambda: None, loading_fn=_load_maze_tokenizer, ) @@ -449,8 +448,9 @@ def n_heads(self) -> int: return self.model_cfg.n_heads def _set_tok_gridsize_from_dataset(self): - self.maze_tokenizer.max_grid_size = self.dataset_cfg.max_grid_n - self.maze_tokenizer.clear_cache() + if isinstance(self.maze_tokenizer, MazeTokenizer): + self.maze_tokenizer.max_grid_size = self.dataset_cfg.max_grid_n + self.maze_tokenizer.clear_cache() def __post_init__(self): # fallback to default maze tokenizer if no kwargs are provided @@ -458,15 +458,12 @@ def __post_init__(self): if self.maze_tokenizer is None: # TODO: is this the right default? maybe set it to AOTP_UT_rasterized # since thats what legacy models are likely to be? - self.maze_tokenizer = MazeTokenizer( - tokenization_mode=TokenizationMode.AOTP_UT_uniform, - max_grid_size=None, - ) + self.maze_tokenizer = MazeTokenizerModular() # update the config of the maze tokenizer if there is no grid size # since we need the token array for the vocab size of the model if self.maze_tokenizer is not None: - if self.maze_tokenizer.max_grid_size is None: + if getattr(self.maze_tokenizer, "max_grid_size", None) is None: self._set_tok_gridsize_from_dataset() def summary(self) -> str: @@ -560,38 +557,51 @@ def get_config_multisource( - train_cfg_name: {train_cfg_names} """ + # init the holder config: ConfigHolder + + # make sure we are only using one of the three methods assert ( sum(1 for x in (cfg, cfg_file, cfg_names) if x is not None) == 1 ), "Must provide exactly one of cfg, cfg_file, or cfg_names" if cfg is not None: + # passing config directly assert cfg_names is None, "Must provide either cfg or cfg_names" config = cfg elif cfg_file is not None: + # passing config from file with open(cfg_file) as f: config = ConfigHolder.load(json.load(f)) elif cfg_names is not None: + # passing names assert ( len(cfg_names) == 3 or len(cfg_names) == 4 ), "cfg_names must be (dataset_cfg_name,model_cfg_name,train_cfg_name) or the same with collective name at the end" + # set up the names dataset_cfg_name: str model_cfg_name: str train_cfg_name: str name: str + if len(cfg_names) == 3: + # 3 names if no collective name dataset_cfg_name, model_cfg_name, train_cfg_name = cfg_names + # assemble the collective name name = f"multsrc_{dataset_cfg_name}_{model_cfg_name}_{train_cfg_name}" else: + # 4 names if collective name, unpack it dataset_cfg_name, model_cfg_name, train_cfg_name, name = cfg_names try: + # try to actually assemble the configuration by looking up names in dicts config = ConfigHolder( name=name, - dataset_cfg=MAZE_DATASET_CONFIGS[dataset_cfg_name], - model_cfg=GPT_CONFIGS[model_cfg_name], - train_cfg=TRAINING_CONFIGS[train_cfg_name], + dataset_cfg=copy.deepcopy(MAZE_DATASET_CONFIGS[dataset_cfg_name]), + model_cfg=copy.deepcopy(GPT_CONFIGS[model_cfg_name]), + train_cfg=copy.deepcopy(TRAINING_CONFIGS[train_cfg_name]), ) except KeyError as e: + # exception handling for missing keys case raise KeyError( "tried to get a config that doesn't exist, check the names.\n", f"{dataset_cfg_name = }, {model_cfg_name = }, {train_cfg_name = }\n", @@ -602,14 +612,12 @@ def get_config_multisource( raise ValueError( "Must provide exactly one of cfg, cfg_file, or cfg_names. this state should be unreachable btw." ) - # update config with kwargs if kwargs_in: kwargs_dict: dict = kwargs_to_nested_dict( kwargs_in, sep=".", strip_prefix="cfg.", when_unknown_prefix="raise" ) config.update_from_nested_dict(kwargs_dict) - return config diff --git a/maze_transformer/training/train_model.py b/maze_transformer/training/train_model.py index 9b179ee1..bfc8d7c7 100644 --- a/maze_transformer/training/train_model.py +++ b/maze_transformer/training/train_model.py @@ -1,3 +1,4 @@ +import copy import json import typing import warnings @@ -30,6 +31,7 @@ class TrainingResult(SerializableDataclass): output_path: Path model: ZanjHookedTransformer + logger: WandbLogger def __str__(self): return f"TrainingResult of training run stored at output_path='{self.output_path}', trained a model from config with name: {self.model.zanj_model_config.name}" @@ -161,7 +163,7 @@ def train_model( cfg.train_cfg.validation_dataset_cfg, ] val_dataset = MazeDataset( - cfg.dataset_cfg, + copy.deepcopy(cfg.dataset_cfg), mazes=dataset.mazes[-split_dataset_sizes[1] :], generation_metadata_collected=dataset.generation_metadata_collected, ) @@ -198,6 +200,7 @@ def train_model( return TrainingResult( output_path=output_path, model=trained_model, + logger=logger, ) diff --git a/maze_transformer/training/training.py b/maze_transformer/training/training.py index 15af763d..9f4140c0 100644 --- a/maze_transformer/training/training.py +++ b/maze_transformer/training/training.py @@ -5,7 +5,7 @@ import torch from jaxtyping import Float from maze_dataset import MazeDataset, SolvedMaze -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizer, MazeTokenizerModular from muutils.statcounter import StatCounter from torch.utils.data import DataLoader from transformer_lens.HookedTransformer import SingleLoss @@ -19,7 +19,9 @@ from maze_transformer.training.wandb_logger import WandbLogger -def collate_batch(batch: list[SolvedMaze], maze_tokenizer: MazeTokenizer) -> list[str]: +def collate_batch( + batch: list[SolvedMaze], maze_tokenizer: MazeTokenizer | MazeTokenizerModular +) -> list[str]: return [" ".join(maze.as_tokens(maze_tokenizer)) for maze in batch] diff --git a/maze_transformer/training/wandb_logger.py b/maze_transformer/training/wandb_logger.py index 7442d6a7..721ea2bf 100644 --- a/maze_transformer/training/wandb_logger.py +++ b/maze_transformer/training/wandb_logger.py @@ -83,3 +83,6 @@ def url(self) -> str: @staticmethod def progress(message: str) -> None: logging.info(message) + + def finish(self) -> None: + self._run.finish() diff --git a/notebooks/appendix_figures.ipynb b/notebooks/appendix_figures.ipynb index 2673c1e1..ecbcf793 100644 --- a/notebooks/appendix_figures.ipynb +++ b/notebooks/appendix_figures.ipynb @@ -23,7 +23,7 @@ "# dataset stuff\n", "from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze, LatticeMaze, SPECIAL_TOKENS, LatticeMazeGenerators\n", "from maze_dataset.plotting import MazePlot, PathFormat\n", - "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode\n", + "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode, MazeTokenizerModular\n", "from maze_dataset.plotting.print_tokens import color_maze_tokens_AOTP\n", "\n", "# model stuff\n", @@ -139,7 +139,7 @@ "\tfig.savefig(plot_dir / \"rollouts.pdf\", bbox_inches=\"tight\")\n", "\tplt.show()\n", "\n", - "\ttokenizer: MazeTokenizer = model.zanj_model_config.maze_tokenizer\n", + "\ttokenizer: MazeTokenizer | MazeTokenizerModular = model.zanj_model_config.maze_tokenizer\n", "\ttask_prompts_targets: dict[str, TaskPrompt] = get_task_prompts_targets(\n", "\t\tdataset=dataset,\n", "\t\tmaze_tokenizer=tokenizer,\n", diff --git a/notebooks/demo_dataset.ipynb b/notebooks/demo_dataset.ipynb index c5514307..06367a11 100644 --- a/notebooks/demo_dataset.ipynb +++ b/notebooks/demo_dataset.ipynb @@ -525,7 +525,7 @@ "source": [ "\n", "from maze_dataset.plotting import MazePlot\n", - "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode\n", + "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode, MazeTokenizerModular\n", "from maze_dataset.plotting.print_tokens import display_color_maze_tokens_AOTP, color_maze_tokens_AOTP\n", "\n", "maze: SolvedMaze = dataset[0]\n", @@ -543,7 +543,7 @@ "# as tokens\n", "\n", "# first, initialize a tokenizer -- more about this in the `notebooks/demo_tokenization.ipynb` notebook\n", - "tokenizer: MazeTokenizer = MazeTokenizer(tokenization_mode=TokenizationMode.AOTP_UT_rasterized, max_grid_size=100)\n", + "tokenizer: MazeTokenizerModular = MazeTokenizerModular()\n", "maze_tok = maze.as_tokens(maze_tokenizer=tokenizer)\n", "\n", "# you can view the tokens directly\n", diff --git a/notebooks/direct_logit_attribution.ipynb b/notebooks/direct_logit_attribution.ipynb index d2be48b0..49dd32d1 100644 --- a/notebooks/direct_logit_attribution.ipynb +++ b/notebooks/direct_logit_attribution.ipynb @@ -89,7 +89,7 @@ "# Our Code\n", "# dataset stuff\n", "from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze, LatticeMaze, SPECIAL_TOKENS, LatticeMazeGenerators\n", - "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode\n", + "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode, MazeTokenizerModular\n", "from maze_dataset.plotting.print_tokens import color_maze_tokens_AOTP\n", "\n", "# model stuff\n", @@ -287,7 +287,7 @@ } ], "source": [ - "TOKENIZER: MazeTokenizer = MODEL.zanj_model_config.maze_tokenizer\n", + "TOKENIZER: MazeTokenizer | MazeTokenizerModular = MODEL.zanj_model_config.maze_tokenizer\n", "DATASET_TOKENS: list[list[str]] = DATASET.as_tokens(TOKENIZER, join_tokens_individual_maze=False)\n", "\n", "# print some info\n", diff --git a/notebooks/eval_model.ipynb b/notebooks/eval_model.ipynb index a751f047..ed94dde5 100644 --- a/notebooks/eval_model.ipynb +++ b/notebooks/eval_model.ipynb @@ -47,28 +47,9 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "set up plots with PLOT_MODE = 'inline', FIG_OUTPUT_FMT = None, FIG_BASEPATH = None\n", - "DEVICE = device(type='cpu')\n" - ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 2, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# Setup (we won't be training any models)\n", "DEVICE: torch.device = configure_notebook(seed=42, dark_mode=False)\n", @@ -78,66 +59,14 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "will try to get model from ../examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "self.tokenization_mode = \n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "loaded model: multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1 with 70319 parameters\n" - ] - } - ], + "outputs": [], "source": [ "# Setup\n", "PATH_EXAMPLES: Path = Path(\"../examples/\")\n", @@ -147,7 +76,7 @@ "torch.set_grad_enabled(False)\n", "\n", "# get the default model from examples\n", - "MODEL_PATH: Path = PATH_EXAMPLES / \"multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj\"\n", + "MODEL_PATH: Path = PATH_EXAMPLES / \"multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj\"\n", "# MODEL_PATH: Path = PATH_DATA / \"custom_2023-05-24-05-03-04/model.final.zanj\"\n", "# MODEL_PATH: Path = PATH_EXAMPLES / \"hallway-medium_2023-06-16-03-40-47.iter_26554.zanj\"\n", "print(f\"will try to get model from {MODEL_PATH.as_posix()}\")\n", @@ -157,36 +86,9 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "trying to get the dataset 'demo-g6-n100-a_dfs-h10871'\n", - "seeing if we can download the dataset...\n", - "no download found, or download failed\n", - "generating dataset...\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "generating & solving mazes: 100%|██████████| 100/100 [00:01<00:00, 63.35maze/s]\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "saving dataset to ..\\data\\demo-g6-n100-a_dfs-h10871.zanj\n", - "Got dataset demo with 100 items. output.cfg.to_fname() = 'demo-g6-n100-a_dfs-h10871'\n", - "got test dataset: demo with 100 mazes\n" - ] - } - ], + "outputs": [], "source": [ "# generate a smaller test dataset from the same config\n", "DATASET_TEST_CFG: MazeDatasetConfig = copy.deepcopy(MODEL.config.dataset_cfg)\n", @@ -213,439 +115,18 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/plain": [ - "(
,\n", - " array([, , , , ], dtype=object))" - ] - }, - "execution_count": 7, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "plot_predicted_paths(MODEL, DATASET_TEST, n_mazes=5, max_new_tokens=50)" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/plain": [ - "(
,\n", - " array([, , , , ], dtype=object))" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# now let's do the same with the baseline solver\n", "BASELINE_SOLVER: RandomBaseline = RandomBaseline(MODEL.zanj_model_config)\n", @@ -666,1692 +147,23 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found 2 checkpoints, min_index=0, max_index=78\n", - "will evaluate 2 checkpoints: [(0, '../examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_0.zanj'), (78, '../examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/checkpoints/model.iter_78.zanj')]\n", - "# Evaluating checkpoint 0 at ..\\examples\\multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02\\checkpoints\\model.iter_0.zanj\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "# Evaluating checkpoint 78 at ..\\examples\\multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02\\checkpoints\\model.iter_78.zanj\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\Aaron\\Desktop\\NTFS\\NTFS_Storage\\dev\\Unsearch\\m-t_dev\\maze-transformer\\maze_transformer\\evaluation\\path_evals.py:99: RuntimeWarning:\n", - "\n", - "fraction_connections_adjacent_lattice called on path of length less than 2, retuning NaN\n", - "prediction = array([[0, 3]])\n", - "\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n", - "Getting vocab\n" - ] - } - ], + "outputs": [], "source": [ "PATHDIST_SCORES: dict[str, dict[int, StatCounter]] = eval_model_at_checkpoints(MODEL_PATH, DATASET_TEST, max_checkpoints=5)" ] }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "plot_pathdist_scores(PATHDIST_SCORES)" ] @@ -2380,7 +192,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.11" + "version": "3.12.4" }, "orig_nbformat": 4 }, diff --git a/notebooks/eval_tasks_table.ipynb b/notebooks/eval_tasks_table.ipynb index 6c133c5c..6fec973d 100644 --- a/notebooks/eval_tasks_table.ipynb +++ b/notebooks/eval_tasks_table.ipynb @@ -40,7 +40,7 @@ "# Our Code\n", "# dataset stuff\n", "from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze, LatticeMaze, SPECIAL_TOKENS, LatticeMazeGenerators, CoordArray\n", - "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode\n", + "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode, MazeTokenizerModular\n", "\n", "# model stuff\n", "from maze_transformer.training.config import ZanjHookedTransformer\n", @@ -202,7 +202,7 @@ "# print the distribution of path lengths for each dataset\n", "import matplotlib.pyplot as plt\n", "fig, ax = plt.subplots(len(DATASETS), 2, figsize=(8, 4), sharex=\"col\")\n", - "placeholder_tokenizer: MazeTokenizer = MazeTokenizer(tokenization_mode=TokenizationMode.AOTP_UT_uniform, max_grid_size=16)\n", + "placeholder_tokenizer: MazeTokenizerModular = MazeTokenizerModular()\n", "for i, ds in enumerate(DATASETS):\n", "\ttotal_lengths = [len(maze.as_tokens(placeholder_tokenizer)) for maze in ds]\n", "\tpath_lengths = [len(maze.solution) for maze in ds]\n", @@ -404,7 +404,7 @@ "\t\tfor dataset in datasets:\n", "\t\t\tprint(f\"evaluating {model_path} on {dataset.cfg.to_fname()}\")\n", "\n", - "\t\t\ttokenizer: MazeTokenizer = model.zanj_model_config.maze_tokenizer\n", + "\t\t\ttokenizer: MazeTokenizer | MazeTokenizerModular = model.zanj_model_config.maze_tokenizer\n", "\t\t\ttask_prompt_targets: dict[str, TaskPrompt] = get_task_prompts_targets(\n", "\t\t\t\tdataset=dataset,\n", "\t\t\t\tmaze_tokenizer=tokenizer,\n", diff --git a/notebooks/plot_attention.ipynb b/notebooks/plot_attention.ipynb index c0972b2a..afc0e000 100644 --- a/notebooks/plot_attention.ipynb +++ b/notebooks/plot_attention.ipynb @@ -56,7 +56,7 @@ "# We won't be training any models\n", "torch.set_grad_enabled(False)\n", "\n", - "# MODEL_PATH: Path = PATH_EXAMPLES / \"multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj\"\n", + "# MODEL_PATH: Path = PATH_EXAMPLES / \"multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj\"\n", "MODEL_PATH: Path = PATH_EXAMPLES / \"model.hallway-jvq.final.zanj\"\n", "print(f\"will try to get model from {MODEL_PATH.as_posix()}\")\n", "\n", diff --git a/notebooks/residual_stream_decoding.ipynb b/notebooks/residual_stream_decoding.ipynb index f70536c0..f1445c78 100644 --- a/notebooks/residual_stream_decoding.ipynb +++ b/notebooks/residual_stream_decoding.ipynb @@ -23,16 +23,7 @@ "cell_type": "code", "execution_count": 1, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "c:\\Users\\mivan\\AppData\\Local\\pypoetry\\Cache\\virtualenvs\\maze-transformer-2cGx2R0F-py3.11\\Lib\\site-packages\\_distutils_hack\\__init__.py:26: UserWarning: Setuptools is replacing distutils.\n", - " warnings.warn(\"Setuptools is replacing distutils.\")\n" - ] - } - ], + "outputs": [], "source": [ "# Generic\n", "import os\n", @@ -69,9 +60,9 @@ "\n", "# Our Code\n", "from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze, LatticeMaze, SPECIAL_TOKENS\n", - "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode\n", + "from maze_dataset.tokenization import MazeTokenizer, TokenizationMode, MazeTokenizerModular\n", "from maze_dataset.plotting.print_tokens import color_maze_tokens_AOTP\n", - "from maze_dataset.tokenization.util import strings_to_coords, coords_to_strings\n", + "from maze_dataset.token_utils import strings_to_coords, coords_to_strings\n", "from maze_dataset.constants import _SPECIAL_TOKENS_ABBREVIATIONS\n", "\n", "from maze_transformer.training.config import ConfigHolder, ZanjHookedTransformer, BaseGPTConfig\n", @@ -101,7 +92,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 2, @@ -125,12 +116,13 @@ "name": "stdout", "output_type": "stream", "text": [ + "ConfigHolder(dataset_cfg=MazeDatasetConfig(name='hallway', seq_len_min=1, seq_len_max=256, seed=42, applied_filters=[{'name': 'collect_generation_meta', 'args': (), 'kwargs': {}}], grid_n=7, n_mazes=100, maze_ctor=, maze_ctor_kwargs={'do_forks': False}, endpoint_kwargs={}), model_cfg=BaseGPTConfig(name='custom-model', act_fn='gelu', d_model=128, d_head=32, n_layers=6, positional_embedding_type='standard', weight_processing={'are_layernorms_folded': False, 'are_weights_processed': True}), train_cfg=TrainConfig(name='custom-train', evals_max_new_tokens=8, validation_dataset_cfg=100, optimizer=, optimizer_kwargs={'lr': 0.0001}, batch_size=32, dataloader_cfg={'shuffle': False, 'num_workers': 8, 'drop_last': False}, intervals=None, intervals_count={'print_loss': 100, 'checkpoint': 47, 'eval_fast': 100, 'eval_slow': 50}), name='hallway_v3', pretrainedtokenizer_kwargs=None, maze_tokenizer=MazeTokenizer(tokenization_mode=, max_grid_size=7), _tokenizer=None)\n", "loaded model with 1.2M params (num_params = 1238076) from:\n", "\tpath: ../examples/model.hallway-jvq.final.zanj\n", "\toriginal model name: 'model.zanj_model_config.name = 'hallway_v3'', changing to 'hallway-jvq.final'\n", "\tmodel tensors on devices: {device(type='cpu')}\n", "loaded dataset with 100 examples\n", - "dataset.cfg.summary() = {'name': 'hallway', 'fname': 'hallway-g7-n100-a_dfs-h52723', 'sdc_hash': 110302684828161283175731365142829285748232501725876255654215979074922758852723, 'seed': 42, 'seq_len_min': 1, 'seq_len_max': 256, 'applied_filters': [{'name': 'collect_generation_meta', 'args': [], 'kwargs': {}}], 'grid_n': 7, 'grid_shape': (7, 7), 'n_mazes': 100, 'maze_ctor_name': 'gen_dfs', 'maze_ctor_kwargs': {'do_forks': False}}\n", + "dataset.cfg.summary() = {'name': 'hallway', 'fname': 'hallway-g7-n100-a_dfs-h11371', 'sdc_hash': 92284480160233715621906274593096472177826541143885775551546319591966823011371, 'seed': 42, 'seq_len_min': 1, 'seq_len_max': 256, 'applied_filters': [{'name': 'collect_generation_meta', 'args': (), 'kwargs': {}}], 'grid_n': 7, 'grid_shape': (7, 7), 'n_mazes': 100, 'maze_ctor_name': 'gen_dfs', 'maze_ctor_kwargs': {'do_forks': False}}\n", "using tokenizer with TOKENIZER = MazeTokenizer(tokenization_mode=, max_grid_size=7)\n", "TOKENIZER.vocab_size = 60\n" ] @@ -145,7 +137,7 @@ "\tn_examples=20,\n", ")\n", "MODEL_NAME: str = MODEL.zanj_model_config.name\n", - "TOKENIZER: MazeTokenizer = MODEL.zanj_model_config.maze_tokenizer\n", + "TOKENIZER: MazeTokenizer | MazeTokenizerModular = MODEL.zanj_model_config.maze_tokenizer\n", "print(f\"using tokenizer with {TOKENIZER = }\")\n", "print(f\"{TOKENIZER.vocab_size = }\")" ] @@ -297,7 +289,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -330,7 +322,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -362,7 +354,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -398,7 +390,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -455,7 +447,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "7240dc200b9045a696398dd084be8de8", + "model_id": "fad3ad629c2747e781e00b2b2c7774ab", "version_major": 2, "version_minor": 0 }, @@ -465,6 +457,16 @@ }, "metadata": {}, "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" } ], "source": [ diff --git a/notebooks/train_model.ipynb b/notebooks/train_model.ipynb index 0ff22795..cea23187 100644 --- a/notebooks/train_model.ipynb +++ b/notebooks/train_model.ipynb @@ -21,14 +21,16 @@ "import torch\n", "\n", "# muutils\n", + "from muutils.nbutils.configure_notebook import configure_notebook\n", "from zanj.zanj import ZANJ, ZANJ_GLOBAL_DEFAULTS\n", "\n", - "# Our Code\n", - "from muutils.nbutils.configure_notebook import configure_notebook\n", - "from maze_transformer.training.config import ConfigHolder, ZanjHookedTransformer, BaseGPTConfig, TrainConfig\n", + "# maze-dataset\n", + "from maze_dataset.generation import LatticeMazeGenerators\n", "from maze_dataset import MazeDataset, MazeDatasetConfig\n", "from maze_dataset.dataset.configs import MAZE_DATASET_CONFIGS\n", - "from maze_dataset.generation import LatticeMazeGenerators\n", + "\n", + "# maze-transformer\n", + "from maze_transformer.training.config import ConfigHolder, ZanjHookedTransformer, BaseGPTConfig, TrainConfig\n", "from maze_transformer.training.train_model import TrainingResult, train_model\n", "from maze_transformer.training.wandb_logger import WandbProject\n" ] @@ -161,7 +163,7 @@ "source": [ "# this is for training a \"real\" demo model\n", "CFG_DEMO: ConfigHolder = ConfigHolder.get_config_multisource(\n", - " cfg_names=(\"test-g3-n5-a_dfs-h73257\", \"tiny-v1\", \"sweep-v1\"),\n", + " cfg_names=(\"demo-g6-n10K-a_dfs-h50618\", \"tiny-v1\", \"sweep-v1\"),\n", ")\n", "\n", "# this is smaller, for testing\n", @@ -200,13 +202,10 @@ " \"seq_len_max\": 512,\n", " \"applied_filters\": [],\n", " \"grid_n\": 3,\n", - " \"grid_shape\": [\n", - " 3,\n", - " 3\n", - " ],\n", " \"n_mazes\": 100,\n", " \"maze_ctor_name\": \"gen_dfs\",\n", - " \"maze_ctor_kwargs\": {}\n", + " \"maze_ctor_kwargs\": {},\n", + " \"endpoint_kwargs\": {}\n", " },\n", " \"model_cfg\": {\n", " \"name\": \"nano-v1\",\n", @@ -245,9 +244,16 @@ " },\n", " \"pretrainedtokenizer_kwargs\": null,\n", " \"maze_tokenizer\": {\n", - " \"tokenization_mode\": \"AOTP_UT_uniform\",\n", - " \"max_grid_size\": 3,\n", - " \"vocab_size\": 20\n", + " \"prompt_sequencer\": \"AOTP(UT(), AdjListCoord(pre=F, post=T, shuffle_d0=T, Ungrouped(connection_token_ordinal=1), ConnectionEdges(walls=F), RandomCoords()), Unlabeled(post=F), StepSequence(Singles(), step_tokenizers=(Coord(), ), pre=F, intra=F, post=F))\",\n", + " \"coord_tokenizer\": \"UT()\",\n", + " \"adj_list_tokenizer\": \"AdjListCoord(pre=F, post=T, shuffle_d0=T, Ungrouped(connection_token_ordinal=1), ConnectionEdges(walls=F), RandomCoords())\",\n", + " \"edge_grouping\": \"Ungrouped(connection_token_ordinal=1)\",\n", + " \"edge_subset\": \"ConnectionEdges(walls=F)\",\n", + " \"edge_permuter\": \"RandomCoords()\",\n", + " \"target_tokenizer\": \"Unlabeled(post=F)\",\n", + " \"path_tokenizer\": \"StepSequence(Singles(), step_tokenizers=(Coord(), ), pre=F, intra=F, post=F)\",\n", + " \"step_size\": \"Singles()\",\n", + " \"step_tokenizers\": \"Coord()\"\n", " }\n", "}\n" ] @@ -267,32 +273,10 @@ "output_type": "stream", "text": [ "trying to get the dataset 'demo_small-g3-n100-a_dfs-h44636'\n", - "seeing if we can download the dataset...\n", - "no download found, or download failed\n", - "generating dataset...\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "generating & solving mazes: 100%|██████████| 100/100 [00:00<00:00, 1562.52maze/s]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "saving dataset to ..\\data\\demo_small-g3-n100-a_dfs-h44636.zanj\n", + "loading dataset from ../data/demo_small-g3-n100-a_dfs-h44636.zanj\n", + "load successful!\n", "Got dataset demo_small with 100 items. output.cfg.to_fname() = 'demo_small-g3-n100-a_dfs-h91156'\n" ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n" - ] } ], "source": [ @@ -313,7 +297,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "2024-07-26 15:12:42 ERROR Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n" + "2024-08-21 12:37:54 ERROR Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n" ] }, { @@ -326,7 +310,7 @@ { "data": { "text/html": [ - "Tracking run with wandb version 0.17.5" + "Tracking run with wandb version 0.17.7" ], "text/plain": [ "" @@ -338,7 +322,7 @@ { "data": { "text/html": [ - "Run data is saved locally in f:\\KNC\\maze-transformer\\notebooks\\wandb\\run-20240726_151244-pq9dpsg6" + "Run data is saved locally in f:\\KNC\\maze-transformer\\notebooks\\wandb\\run-20240821_123757-042s41ob" ], "text/plain": [ "" @@ -350,7 +334,7 @@ { "data": { "text/html": [ - "Syncing run olive-lake-20 to Weights & Biases (docs)
" + "Syncing run clean-water-27 to Weights & Biases (docs)
" ], "text/plain": [ "" @@ -374,7 +358,7 @@ { "data": { "text/html": [ - " View run at https://wandb.ai/miv/understanding-search/runs/pq9dpsg6" + " View run at https://wandb.ai/miv/understanding-search/runs/042s41ob" ], "text/plain": [ "" @@ -387,16 +371,16 @@ "name": "stdout", "output_type": "stream", "text": [ - "2024-07-26 15:12:46 INFO config ={'__format__': 'ConfigHolder(SerializableDataclass)', 'dataset_cfg': {'__format__': 'MazeDatasetConfig(SerializableDataclass)', 'name': 'demo_small', 'seq_len_min': 1, 'seq_len_max': 512, 'seed': 42, 'applied_filters': [], 'grid_n': 3, 'n_mazes': 100, 'maze_ctor': {'__name__': 'gen_dfs', '__module__': 'maze_dataset.generation.generators', '__doc__': ['generate a lattice maze using depth first search, iterative', '', ' # Arguments', ' - `grid_shape: Coord`: the shape of the grid', ' - `lattice_dim: int`: the dimension of the lattice', ' (default: `2`)', ' - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**', ' (default: `None`)', ' - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**', ' (default: `None`)', ' - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.', ' - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.', '', ' # algorithm', ' 1. Choose the initial cell, mark it as visited and push it to the stack', ' 2. While the stack is not empty', ' 1. Pop a cell from the stack and make it a current cell', ' 2. If the current cell has any neighbours which have not been visited', ' 1. Push the current cell to the stack', ' 2. Choose one of the unvisited neighbours', ' 3. Remove the wall between the current cell and the chosen cell', ' 4. Mark the chosen cell as visited and push it to the stack', ' '], 'source_code': [' @staticmethod', ' def gen_dfs(', ' grid_shape: Coord,', ' lattice_dim: int = 2,', ' accessible_cells: int | float | None = None,', ' max_tree_depth: int | float | None = None,', ' do_forks: bool = True,', ' randomized_stack: bool = False,', ' start_coord: Coord | None = None,', ' ) -> LatticeMaze:', ' \"\"\"generate a lattice maze using depth first search, iterative', '', ' # Arguments', ' - `grid_shape: Coord`: the shape of the grid', ' - `lattice_dim: int`: the dimension of the lattice', ' (default: `2`)', ' - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**', ' (default: `None`)', ' - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**', ' (default: `None`)', ' - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.', ' - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.', '', ' # algorithm', ' 1. Choose the initial cell, mark it as visited and push it to the stack', ' 2. While the stack is not empty', ' 1. Pop a cell from the stack and make it a current cell', ' 2. If the current cell has any neighbours which have not been visited', ' 1. Push the current cell to the stack', ' 2. Choose one of the unvisited neighbours', ' 3. Remove the wall between the current cell and the chosen cell', ' 4. Mark the chosen cell as visited and push it to the stack', ' \"\"\"', '', ' # Default values if no constraints have been passed', ' grid_shape: Coord = np.array(grid_shape)', ' n_total_cells: int = int(np.prod(grid_shape))', '', ' n_accessible_cells: int', ' if accessible_cells is None:', ' n_accessible_cells = n_total_cells', ' elif isinstance(accessible_cells, float):', ' assert (', ' accessible_cells <= 1', ' ), f\"accessible_cells must be an int (count) or a float in the range [0, 1] (proportion), got {accessible_cells}\"', '', ' n_accessible_cells = int(accessible_cells * n_total_cells)', ' else:', ' assert isinstance(accessible_cells, int)', ' n_accessible_cells = accessible_cells', '', ' if max_tree_depth is None:', ' max_tree_depth = (', ' 2 * n_total_cells', ' ) # We define max tree depth counting from the start coord in two directions. Therefore we divide by two in the if clause for neighboring sites later and multiply by two here.', ' elif isinstance(max_tree_depth, float):', ' assert (', ' max_tree_depth <= 1', ' ), f\"max_tree_depth must be an int (count) or a float in the range [0, 1] (proportion), got {max_tree_depth}\"', '', ' max_tree_depth = int(max_tree_depth * np.sum(grid_shape))', '', ' # choose a random start coord', ' start_coord = _random_start_coord(grid_shape, start_coord)', '', ' # initialize the maze with no connections', ' connection_list: ConnectionList = np.zeros(', ' (lattice_dim, grid_shape[0], grid_shape[1]), dtype=np.bool_', ' )', '', ' # initialize the stack with the target coord', ' visited_cells: set[tuple[int, int]] = set()', ' visited_cells.add(tuple(start_coord)) # this wasnt a bug after all lol', ' stack: list[Coord] = [start_coord]', '', ' # initialize tree_depth_counter', ' current_tree_depth: int = 1', '', ' # loop until the stack is empty or n_connected_cells is reached', ' while stack and (len(visited_cells) < n_accessible_cells):', ' # get the current coord from the stack', ' current_coord: Coord', ' if randomized_stack:', ' current_coord = stack.pop(random.randint(0, len(stack) - 1))', ' else:', ' current_coord = stack.pop()', '', ' # filter neighbors by being within grid bounds and being unvisited', ' unvisited_neighbors_deltas: list[tuple[Coord, Coord]] = [', ' (neighbor, delta)', ' for neighbor, delta in zip(', ' current_coord + NEIGHBORS_MASK, NEIGHBORS_MASK', ' )', ' if (', ' (tuple(neighbor) not in visited_cells)', ' and (0 <= neighbor[0] < grid_shape[0])', ' and (0 <= neighbor[1] < grid_shape[1])', ' )', ' ]', '', \" # don't continue if max_tree_depth/2 is already reached (divide by 2 because we can branch to multiple directions)\", ' if unvisited_neighbors_deltas and (', ' current_tree_depth <= max_tree_depth / 2', ' ):', \" # if we want a maze without forks, simply don't add the current coord back to the stack\", ' if do_forks and (len(unvisited_neighbors_deltas) > 1):', ' stack.append(current_coord)', '', ' # choose one of the unvisited neighbors', ' chosen_neighbor, delta = random.choice(unvisited_neighbors_deltas)', '', ' # add connection', ' dim: int = np.argmax(np.abs(delta))', ' # if positive, down/right from current coord', ' # if negative, up/left from current coord (down/right from neighbor)', ' clist_node: Coord = (', ' current_coord if (delta.sum() > 0) else chosen_neighbor', ' )', ' connection_list[dim, clist_node[0], clist_node[1]] = True', '', ' # add to visited cells and stack', ' visited_cells.add(tuple(chosen_neighbor))', ' stack.append(chosen_neighbor)', '', ' # Update current tree depth', ' current_tree_depth += 1', ' else:', ' current_tree_depth -= 1', '', ' output = LatticeMaze(', ' connection_list=connection_list,', ' generation_meta=dict(', ' func_name=\"gen_dfs\",', ' grid_shape=grid_shape,', ' start_coord=start_coord,', ' n_accessible_cells=int(n_accessible_cells),', ' max_tree_depth=int(max_tree_depth),', \" # oh my god this took so long to track down. its almost 5am and I've spent like 2 hours on this bug\", ' # it was checking that len(visited_cells) == n_accessible_cells, but this means that the maze is', ' # treated as fully connected even when it is most certainly not, causing solving the maze to break', ' fully_connected=bool(len(visited_cells) == n_total_cells),', ' visited_cells={tuple(int(x) for x in coord) for coord in visited_cells},', ' ),', ' )', '', ' return output']}, 'maze_ctor_kwargs': {}, 'endpoint_kwargs': {}, 'grid_shape': (3, 3)}, 'model_cfg': {'__format__': 'BaseGPTConfig(SerializableDataclass)', 'name': 'nano-v1', 'act_fn': 'gelu', 'd_model': 8, 'd_head': 4, 'n_layers': 2, 'positional_embedding_type': 'standard', 'weight_processing': {'are_layernorms_folded': False, 'are_weights_processed': False}, 'n_heads': 2}, 'train_cfg': {'__format__': 'TrainConfig(SerializableDataclass)', 'name': 'test-v1', 'evals_max_new_tokens': 8, 'validation_dataset_cfg': 1, 'optimizer': 'RMSprop', 'optimizer_kwargs': {'lr': 0.0001}, 'batch_size': 16, 'dataloader_cfg': {'shuffle': True, 'num_workers': 0, 'drop_last': False}, 'intervals': None, 'intervals_count': {'print_loss': 100, 'checkpoint': 2, 'eval_fast': 4, 'eval_slow': 2}}, 'name': 'multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1', 'pretrainedtokenizer_kwargs': None, 'maze_tokenizer': {'__format__': 'MazeTokenizer(SerializableDataclass)', 'tokenization_mode': 'AOTP_UT_uniform', 'max_grid_size': 3, 'name': 'maze_tokenizer-AOTP_UT_uniform-g3', 'token_arr': ['', '', '', '', '', '', '', '', '<-->', ';', '', '(0,0)', '(0,1)', '(1,0)', '(1,1)', '(0,2)', '(2,0)', '(1,2)', '(2,1)', '(2,2)'], 'tokenizer_map': {'': 0, '': 1, '': 2, '': 3, '': 4, '': 5, '': 6, '': 7, '<-->': 8, ';': 9, '': 10, '(0,0)': 11, '(0,1)': 12, '(1,0)': 13, '(1,1)': 14, '(0,2)': 15, '(2,0)': 16, '(1,2)': 17, '(2,1)': 18, '(2,2)': 19}, 'vocab_size': 20, 'padding_token_index': 10}, '_tokenizer': 'None'}\n", - "2024-07-26 15:12:46 INFO Initialized logger\n", - "2024-07-26 15:12:46 INFO Summary logged, getting dataset\n" + "2024-08-21 12:38:00 INFO config ={'__format__': 'ConfigHolder(SerializableDataclass)', 'dataset_cfg': {'__format__': 'MazeDatasetConfig(SerializableDataclass)', 'name': 'demo_small', 'seq_len_min': 1, 'seq_len_max': 512, 'seed': 42, 'applied_filters': [], 'grid_n': 3, 'n_mazes': 100, 'maze_ctor': {'__name__': 'gen_dfs', '__module__': 'maze_dataset.generation.generators', '__doc__': ['generate a lattice maze using depth first search, iterative', '', ' # Arguments', ' - `grid_shape: Coord`: the shape of the grid', ' - `lattice_dim: int`: the dimension of the lattice', ' (default: `2`)', ' - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**', ' (default: `None`)', ' - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**', ' (default: `None`)', ' - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.', ' - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.', '', ' # algorithm', ' 1. Choose the initial cell, mark it as visited and push it to the stack', ' 2. While the stack is not empty', ' 1. Pop a cell from the stack and make it a current cell', ' 2. If the current cell has any neighbours which have not been visited', ' 1. Push the current cell to the stack', ' 2. Choose one of the unvisited neighbours', ' 3. Remove the wall between the current cell and the chosen cell', ' 4. Mark the chosen cell as visited and push it to the stack', ' '], 'source_code': [' @staticmethod', ' def gen_dfs(', ' grid_shape: Coord,', ' lattice_dim: int = 2,', ' accessible_cells: int | float | None = None,', ' max_tree_depth: int | float | None = None,', ' do_forks: bool = True,', ' randomized_stack: bool = False,', ' start_coord: Coord | None = None,', ' ) -> LatticeMaze:', ' \"\"\"generate a lattice maze using depth first search, iterative', '', ' # Arguments', ' - `grid_shape: Coord`: the shape of the grid', ' - `lattice_dim: int`: the dimension of the lattice', ' (default: `2`)', ' - `accessible_cells: int | float |None`: the number of accessible cells in the maze. If `None`, defaults to the total number of cells in the grid. if a float, asserts it is <= 1 and treats it as a proportion of **total cells**', ' (default: `None`)', ' - `max_tree_depth: int | float | None`: the maximum depth of the tree. If `None`, defaults to `2 * accessible_cells`. if a float, asserts it is <= 1 and treats it as a proportion of the **sum of the grid shape**', ' (default: `None`)', ' - `do_forks: bool`: whether to allow forks in the maze. If `False`, the maze will be have no forks and will be a simple hallway.', ' - `start_coord: Coord | None`: the starting coordinate of the generation algorithm. If `None`, defaults to a random coordinate.', '', ' # algorithm', ' 1. Choose the initial cell, mark it as visited and push it to the stack', ' 2. While the stack is not empty', ' 1. Pop a cell from the stack and make it a current cell', ' 2. If the current cell has any neighbours which have not been visited', ' 1. Push the current cell to the stack', ' 2. Choose one of the unvisited neighbours', ' 3. Remove the wall between the current cell and the chosen cell', ' 4. Mark the chosen cell as visited and push it to the stack', ' \"\"\"', '', ' # Default values if no constraints have been passed', ' grid_shape: Coord = np.array(grid_shape)', ' n_total_cells: int = int(np.prod(grid_shape))', '', ' n_accessible_cells: int', ' if accessible_cells is None:', ' n_accessible_cells = n_total_cells', ' elif isinstance(accessible_cells, float):', ' assert (', ' accessible_cells <= 1', ' ), f\"accessible_cells must be an int (count) or a float in the range [0, 1] (proportion), got {accessible_cells}\"', '', ' n_accessible_cells = int(accessible_cells * n_total_cells)', ' else:', ' assert isinstance(accessible_cells, int)', ' n_accessible_cells = accessible_cells', '', ' if max_tree_depth is None:', ' max_tree_depth = (', ' 2 * n_total_cells', ' ) # We define max tree depth counting from the start coord in two directions. Therefore we divide by two in the if clause for neighboring sites later and multiply by two here.', ' elif isinstance(max_tree_depth, float):', ' assert (', ' max_tree_depth <= 1', ' ), f\"max_tree_depth must be an int (count) or a float in the range [0, 1] (proportion), got {max_tree_depth}\"', '', ' max_tree_depth = int(max_tree_depth * np.sum(grid_shape))', '', ' # choose a random start coord', ' start_coord = _random_start_coord(grid_shape, start_coord)', '', ' # initialize the maze with no connections', ' connection_list: ConnectionList = np.zeros(', ' (lattice_dim, grid_shape[0], grid_shape[1]), dtype=np.bool_', ' )', '', ' # initialize the stack with the target coord', ' visited_cells: set[tuple[int, int]] = set()', ' visited_cells.add(tuple(start_coord)) # this wasnt a bug after all lol', ' stack: list[Coord] = [start_coord]', '', ' # initialize tree_depth_counter', ' current_tree_depth: int = 1', '', ' # loop until the stack is empty or n_connected_cells is reached', ' while stack and (len(visited_cells) < n_accessible_cells):', ' # get the current coord from the stack', ' current_coord: Coord', ' if randomized_stack:', ' current_coord = stack.pop(random.randint(0, len(stack) - 1))', ' else:', ' current_coord = stack.pop()', '', ' # filter neighbors by being within grid bounds and being unvisited', ' unvisited_neighbors_deltas: list[tuple[Coord, Coord]] = [', ' (neighbor, delta)', ' for neighbor, delta in zip(', ' current_coord + NEIGHBORS_MASK, NEIGHBORS_MASK', ' )', ' if (', ' (tuple(neighbor) not in visited_cells)', ' and (0 <= neighbor[0] < grid_shape[0])', ' and (0 <= neighbor[1] < grid_shape[1])', ' )', ' ]', '', \" # don't continue if max_tree_depth/2 is already reached (divide by 2 because we can branch to multiple directions)\", ' if unvisited_neighbors_deltas and (', ' current_tree_depth <= max_tree_depth / 2', ' ):', \" # if we want a maze without forks, simply don't add the current coord back to the stack\", ' if do_forks and (len(unvisited_neighbors_deltas) > 1):', ' stack.append(current_coord)', '', ' # choose one of the unvisited neighbors', ' chosen_neighbor, delta = random.choice(unvisited_neighbors_deltas)', '', ' # add connection', ' dim: int = np.argmax(np.abs(delta))', ' # if positive, down/right from current coord', ' # if negative, up/left from current coord (down/right from neighbor)', ' clist_node: Coord = (', ' current_coord if (delta.sum() > 0) else chosen_neighbor', ' )', ' connection_list[dim, clist_node[0], clist_node[1]] = True', '', ' # add to visited cells and stack', ' visited_cells.add(tuple(chosen_neighbor))', ' stack.append(chosen_neighbor)', '', ' # Update current tree depth', ' current_tree_depth += 1', ' else:', ' current_tree_depth -= 1', '', ' output = LatticeMaze(', ' connection_list=connection_list,', ' generation_meta=dict(', ' func_name=\"gen_dfs\",', ' grid_shape=grid_shape,', ' start_coord=start_coord,', ' n_accessible_cells=int(n_accessible_cells),', ' max_tree_depth=int(max_tree_depth),', \" # oh my god this took so long to track down. its almost 5am and I've spent like 2 hours on this bug\", ' # it was checking that len(visited_cells) == n_accessible_cells, but this means that the maze is', ' # treated as fully connected even when it is most certainly not, causing solving the maze to break', ' fully_connected=bool(len(visited_cells) == n_total_cells),', ' visited_cells={tuple(int(x) for x in coord) for coord in visited_cells},', ' ),', ' )', '', ' return output']}, 'maze_ctor_kwargs': {}, 'endpoint_kwargs': {}, 'grid_shape': (3, 3)}, 'model_cfg': {'__format__': 'BaseGPTConfig(SerializableDataclass)', 'name': 'nano-v1', 'act_fn': 'gelu', 'd_model': 8, 'd_head': 4, 'n_layers': 2, 'positional_embedding_type': 'standard', 'weight_processing': {'are_layernorms_folded': False, 'are_weights_processed': False}, 'n_heads': 2}, 'train_cfg': {'__format__': 'TrainConfig(SerializableDataclass)', 'name': 'test-v1', 'evals_max_new_tokens': 8, 'validation_dataset_cfg': 1, 'optimizer': 'RMSprop', 'optimizer_kwargs': {'lr': 0.0001}, 'batch_size': 16, 'dataloader_cfg': {'shuffle': True, 'num_workers': 0, 'drop_last': False}, 'intervals': None, 'intervals_count': {'print_loss': 100, 'checkpoint': 2, 'eval_fast': 4, 'eval_slow': 2}}, 'name': 'multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1', 'pretrainedtokenizer_kwargs': None, 'maze_tokenizer': {'__format__': 'MazeTokenizerModular(SerializableDataclass)', 'prompt_sequencer': {'__format__': 'AOTP(SerializableDataclass)', 'coord_tokenizer': {'__format__': 'UT(SerializableDataclass)', '_type_': \"\"}, 'adj_list_tokenizer': {'__format__': 'AdjListCoord(SerializableDataclass)', 'pre': False, 'post': True, 'shuffle_d0': True, 'edge_grouping': {'__format__': 'Ungrouped(SerializableDataclass)', '_type_': \"\", 'connection_token_ordinal': 1}, 'edge_subset': {'__format__': 'ConnectionEdges(SerializableDataclass)', '_type_': \"\", 'walls': False}, 'edge_permuter': {'__format__': 'RandomCoords(SerializableDataclass)', '_type_': \"\"}, '_type_': \"\"}, '_type_': \"\", 'target_tokenizer': {'__format__': 'Unlabeled(SerializableDataclass)', '_type_': \"\", 'post': False}, 'path_tokenizer': {'__format__': 'StepSequence(SerializableDataclass)', '_type_': \"\", 'step_size': {'__format__': 'Singles(SerializableDataclass)', '_type_': \"\"}, 'step_tokenizers': [{'__format__': 'Coord(SerializableDataclass)', '_type_': \"\"}], 'pre': False, 'intra': False, 'post': False}}, 'tokenizer_element_tree_concrete': 'MazeTokenizerModular\\n\\tAOTP\\n\\t\\tUT\\n\\t\\tAdjListCoord\\n\\t\\t\\tUngrouped\\n\\t\\t\\tConnectionEdges\\n\\t\\t\\tRandomCoords\\n\\t\\tUnlabeled\\n\\t\\tStepSequence\\n\\t\\t\\tSingles\\n\\t\\t\\tCoord\\n', 'name': 'MazeTokenizerModular-AOTP(UT(), AdjListCoord(pre=F, post=T, shuffle_d0=T, Ungrouped(connection_token_ordinal=1), ConnectionEdges(walls=F), RandomCoords()), Unlabeled(post=F), StepSequence(Singles(), step_tokenizers=(Coord(), ), pre=F, intra=F, post=F))'}, '_tokenizer': 'None'}\n", + "2024-08-21 12:38:00 INFO Initialized logger\n", + "2024-08-21 12:38:00 INFO Summary logged, getting dataset\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "F:\\KNC\\maze-transformer\\maze_transformer\\training\\train_model.py:139: UserWarning:\n", + "F:\\KNC\\maze-transformer\\maze_transformer\\training\\train_model.py:140: UserWarning:\n", "\n", "dataset has different config than cfg.dataset_cfg, but the only difference is in applied_filters, so using passed dataset. This is due to fast dataset loading collecting generation metadata for performance reasons\n", "\n" @@ -406,27 +390,21 @@ "name": "stdout", "output_type": "stream", "text": [ - "2024-07-26 15:12:46 INFO finished getting training dataset with 100 samples\n", - "2024-07-26 15:12:46 INFO got validation dataset by splitting training dataset into 99 train and 1 validation samples\n", - "2024-07-26 15:12:46 INFO Loaded 99 sequences\n", - "2024-07-26 15:12:46 INFO Creating dataloader\n", - "2024-07-26 15:12:46 INFO finished dataloader, passing to train()\n", - "2024-07-26 15:12:46 INFO Initializing model\n", - "Moving model to device: cpu\n", - "2024-07-26 15:12:46 INFO Initializing optimizer\n", - "2024-07-26 15:12:47 INFO will train for 7 batches, evals_enabled=True, with intervals: {'print_loss': inf, 'checkpoint': 3, 'eval_fast': 1, 'eval_slow': 3}\n", - "2024-07-26 15:12:47 INFO Starting training\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n" + "2024-08-21 12:38:00 INFO finished getting training dataset with 100 samples\n", + "2024-08-21 12:38:00 INFO got validation dataset by splitting training dataset into 99 train and 1 validation samples\n", + "2024-08-21 12:38:00 INFO Loaded 99 sequences\n", + "2024-08-21 12:38:00 INFO Creating dataloader\n", + "2024-08-21 12:38:00 INFO finished dataloader, passing to train()\n", + "2024-08-21 12:38:00 INFO Initializing model\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "F:\\KNC\\maze-transformer\\maze_transformer\\evaluation\\path_evals.py:98: RuntimeWarning:\n", + "c:\\Users\\mivan\\AppData\\Local\\pypoetry\\Cache\\virtualenvs\\maze-transformer-2cGx2R0F-py3.12\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1601: FutureWarning:\n", "\n", - "fraction_connections_adjacent_lattice called on path of length less than 2, retuning NaN\n", - "prediction = array([[1, 2]])\n", + "`clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n", "\n" ] }, @@ -434,21 +412,26 @@ "name": "stdout", "output_type": "stream", "text": [ - "2024-07-26 15:12:47 INFO Running evals: eval_slow\n", - "2024-07-26 15:12:47 INFO iteration 0/7: loss=3.198\n", - "2024-07-26 15:12:47 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-07-26-15-12-39/checkpoints/model.iter_0.zanj\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_slow\n", - "2024-07-26 15:12:47 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-07-26-15-12-39/checkpoints/model.iter_3.zanj\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_fast\n", - "2024-07-26 15:12:47 INFO Running evals: eval_slow\n", - "2024-07-26 15:12:47 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-07-26-15-12-39/checkpoints/model.iter_6.zanj\n", - "2024-07-26 15:12:48 INFO Saving final model to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-07-26-15-12-39/model.final.zanj\n", - "2024-07-26 15:12:48 INFO Done training!\n" + "Moving model to device: cpu\n", + "2024-08-21 12:38:00 INFO Initializing optimizer\n", + "2024-08-21 12:38:01 INFO will train for 7 batches, evals_enabled=True, with intervals: {'print_loss': inf, 'checkpoint': 3, 'eval_fast': 1, 'eval_slow': 3}\n", + "2024-08-21 12:38:01 INFO Starting training\n", + "2024-08-21 12:38:01 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:01 INFO Running evals: eval_slow\n", + "2024-08-21 12:38:01 INFO iteration 0/7: loss=8.586\n", + "2024-08-21 12:38:01 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-08-21-12-37-54/checkpoints/model.iter_0.zanj\n", + "2024-08-21 12:38:01 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_slow\n", + "2024-08-21 12:38:02 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-08-21-12-37-54/checkpoints/model.iter_3.zanj\n", + "2024-08-21 12:38:02 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_fast\n", + "2024-08-21 12:38:02 INFO Running evals: eval_slow\n", + "2024-08-21 12:38:02 INFO Saving model checkpoint to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-08-21-12-37-54/checkpoints/model.iter_6.zanj\n", + "2024-08-21 12:38:03 INFO Saving final model to ../data/multsrc_demo_small-g3-n100-a_dfs-h44636_nano-v1_test-v1_2024-08-21-12-37-54/model.final.zanj\n", + "2024-08-21 12:38:03 INFO Done training!\n" ] } ], @@ -480,7 +463,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.4" + "version": "3.12.4" }, "orig_nbformat": 4 }, diff --git a/poetry.lock b/poetry.lock index 2897ba4b..637e472f 100644 --- a/poetry.lock +++ b/poetry.lock @@ -716,66 +716,86 @@ test = ["pytest"] [[package]] name = "contourpy" -version = "1.2.1" +version = "1.3.0" description = "Python library for calculating contours of 2D quadrilateral grids" optional = false python-versions = ">=3.9" files = [ - {file = "contourpy-1.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bd7c23df857d488f418439686d3b10ae2fbf9bc256cd045b37a8c16575ea1040"}, - {file = "contourpy-1.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5b9eb0ca724a241683c9685a484da9d35c872fd42756574a7cfbf58af26677fd"}, - {file = "contourpy-1.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c75507d0a55378240f781599c30e7776674dbaf883a46d1c90f37e563453480"}, - {file = "contourpy-1.2.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:11959f0ce4a6f7b76ec578576a0b61a28bdc0696194b6347ba3f1c53827178b9"}, - {file = "contourpy-1.2.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eb3315a8a236ee19b6df481fc5f997436e8ade24a9f03dfdc6bd490fea20c6da"}, - {file = "contourpy-1.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:39f3ecaf76cd98e802f094e0d4fbc6dc9c45a8d0c4d185f0f6c2234e14e5f75b"}, - {file = "contourpy-1.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:94b34f32646ca0414237168d68a9157cb3889f06b096612afdd296003fdd32fd"}, - {file = "contourpy-1.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:457499c79fa84593f22454bbd27670227874cd2ff5d6c84e60575c8b50a69619"}, - {file = "contourpy-1.2.1-cp310-cp310-win32.whl", hash = "sha256:ac58bdee53cbeba2ecad824fa8159493f0bf3b8ea4e93feb06c9a465d6c87da8"}, - {file = "contourpy-1.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:9cffe0f850e89d7c0012a1fb8730f75edd4320a0a731ed0c183904fe6ecfc3a9"}, - {file = "contourpy-1.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6022cecf8f44e36af10bd9118ca71f371078b4c168b6e0fab43d4a889985dbb5"}, - {file = "contourpy-1.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ef5adb9a3b1d0c645ff694f9bca7702ec2c70f4d734f9922ea34de02294fdf72"}, - {file = "contourpy-1.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6150ffa5c767bc6332df27157d95442c379b7dce3a38dff89c0f39b63275696f"}, - {file = "contourpy-1.2.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4c863140fafc615c14a4bf4efd0f4425c02230eb8ef02784c9a156461e62c965"}, - {file = "contourpy-1.2.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:00e5388f71c1a0610e6fe56b5c44ab7ba14165cdd6d695429c5cd94021e390b2"}, - {file = "contourpy-1.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4492d82b3bc7fbb7e3610747b159869468079fe149ec5c4d771fa1f614a14df"}, - {file = "contourpy-1.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:49e70d111fee47284d9dd867c9bb9a7058a3c617274900780c43e38d90fe1205"}, - {file = "contourpy-1.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b59c0ffceff8d4d3996a45f2bb6f4c207f94684a96bf3d9728dbb77428dd8cb8"}, - {file = "contourpy-1.2.1-cp311-cp311-win32.whl", hash = "sha256:7b4182299f251060996af5249c286bae9361fa8c6a9cda5efc29fe8bfd6062ec"}, - {file = "contourpy-1.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:2855c8b0b55958265e8b5888d6a615ba02883b225f2227461aa9127c578a4922"}, - {file = "contourpy-1.2.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:62828cada4a2b850dbef89c81f5a33741898b305db244904de418cc957ff05dc"}, - {file = "contourpy-1.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:309be79c0a354afff9ff7da4aaed7c3257e77edf6c1b448a779329431ee79d7e"}, - {file = "contourpy-1.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e785e0f2ef0d567099b9ff92cbfb958d71c2d5b9259981cd9bee81bd194c9a4"}, - {file = "contourpy-1.2.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1cac0a8f71a041aa587410424ad46dfa6a11f6149ceb219ce7dd48f6b02b87a7"}, - {file = "contourpy-1.2.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af3f4485884750dddd9c25cb7e3915d83c2db92488b38ccb77dd594eac84c4a0"}, - {file = "contourpy-1.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ce6889abac9a42afd07a562c2d6d4b2b7134f83f18571d859b25624a331c90b"}, - {file = "contourpy-1.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a1eea9aecf761c661d096d39ed9026574de8adb2ae1c5bd7b33558af884fb2ce"}, - {file = "contourpy-1.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:187fa1d4c6acc06adb0fae5544c59898ad781409e61a926ac7e84b8f276dcef4"}, - {file = "contourpy-1.2.1-cp312-cp312-win32.whl", hash = "sha256:c2528d60e398c7c4c799d56f907664673a807635b857df18f7ae64d3e6ce2d9f"}, - {file = "contourpy-1.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:1a07fc092a4088ee952ddae19a2b2a85757b923217b7eed584fdf25f53a6e7ce"}, - {file = "contourpy-1.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bb6834cbd983b19f06908b45bfc2dad6ac9479ae04abe923a275b5f48f1a186b"}, - {file = "contourpy-1.2.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1d59e739ab0e3520e62a26c60707cc3ab0365d2f8fecea74bfe4de72dc56388f"}, - {file = "contourpy-1.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bd3db01f59fdcbce5b22afad19e390260d6d0222f35a1023d9adc5690a889364"}, - {file = "contourpy-1.2.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a12a813949e5066148712a0626895c26b2578874e4cc63160bb007e6df3436fe"}, - {file = "contourpy-1.2.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fe0ccca550bb8e5abc22f530ec0466136379c01321fd94f30a22231e8a48d985"}, - {file = "contourpy-1.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1d59258c3c67c865435d8fbeb35f8c59b8bef3d6f46c1f29f6123556af28445"}, - {file = "contourpy-1.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f32c38afb74bd98ce26de7cc74a67b40afb7b05aae7b42924ea990d51e4dac02"}, - {file = "contourpy-1.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d31a63bc6e6d87f77d71e1abbd7387ab817a66733734883d1fc0021ed9bfa083"}, - {file = "contourpy-1.2.1-cp39-cp39-win32.whl", hash = "sha256:ddcb8581510311e13421b1f544403c16e901c4e8f09083c881fab2be80ee31ba"}, - {file = "contourpy-1.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:10a37ae557aabf2509c79715cd20b62e4c7c28b8cd62dd7d99e5ed3ce28c3fd9"}, - {file = "contourpy-1.2.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a31f94983fecbac95e58388210427d68cd30fe8a36927980fab9c20062645609"}, - {file = "contourpy-1.2.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef2b055471c0eb466033760a521efb9d8a32b99ab907fc8358481a1dd29e3bd3"}, - {file = "contourpy-1.2.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:b33d2bc4f69caedcd0a275329eb2198f560b325605810895627be5d4b876bf7f"}, - {file = "contourpy-1.2.1.tar.gz", hash = "sha256:4d8908b3bee1c889e547867ca4cdc54e5ab6be6d3e078556814a22457f49423c"}, + {file = "contourpy-1.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:880ea32e5c774634f9fcd46504bf9f080a41ad855f4fef54f5380f5133d343c7"}, + {file = "contourpy-1.3.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:76c905ef940a4474a6289c71d53122a4f77766eef23c03cd57016ce19d0f7b42"}, + {file = "contourpy-1.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:92f8557cbb07415a4d6fa191f20fd9d2d9eb9c0b61d1b2f52a8926e43c6e9af7"}, + {file = "contourpy-1.3.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:36f965570cff02b874773c49bfe85562b47030805d7d8360748f3eca570f4cab"}, + {file = "contourpy-1.3.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cacd81e2d4b6f89c9f8a5b69b86490152ff39afc58a95af002a398273e5ce589"}, + {file = "contourpy-1.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:69375194457ad0fad3a839b9e29aa0b0ed53bb54db1bfb6c3ae43d111c31ce41"}, + {file = "contourpy-1.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:7a52040312b1a858b5e31ef28c2e865376a386c60c0e248370bbea2d3f3b760d"}, + {file = "contourpy-1.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3faeb2998e4fcb256542e8a926d08da08977f7f5e62cf733f3c211c2a5586223"}, + {file = "contourpy-1.3.0-cp310-cp310-win32.whl", hash = "sha256:36e0cff201bcb17a0a8ecc7f454fe078437fa6bda730e695a92f2d9932bd507f"}, + {file = "contourpy-1.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:87ddffef1dbe5e669b5c2440b643d3fdd8622a348fe1983fad7a0f0ccb1cd67b"}, + {file = "contourpy-1.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0fa4c02abe6c446ba70d96ece336e621efa4aecae43eaa9b030ae5fb92b309ad"}, + {file = "contourpy-1.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:834e0cfe17ba12f79963861e0f908556b2cedd52e1f75e6578801febcc6a9f49"}, + {file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dbc4c3217eee163fa3984fd1567632b48d6dfd29216da3ded3d7b844a8014a66"}, + {file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4865cd1d419e0c7a7bf6de1777b185eebdc51470800a9f42b9e9decf17762081"}, + {file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:303c252947ab4b14c08afeb52375b26781ccd6a5ccd81abcdfc1fafd14cf93c1"}, + {file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:637f674226be46f6ba372fd29d9523dd977a291f66ab2a74fbeb5530bb3f445d"}, + {file = "contourpy-1.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:76a896b2f195b57db25d6b44e7e03f221d32fe318d03ede41f8b4d9ba1bff53c"}, + {file = "contourpy-1.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:e1fd23e9d01591bab45546c089ae89d926917a66dceb3abcf01f6105d927e2cb"}, + {file = "contourpy-1.3.0-cp311-cp311-win32.whl", hash = "sha256:d402880b84df3bec6eab53cd0cf802cae6a2ef9537e70cf75e91618a3801c20c"}, + {file = "contourpy-1.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:6cb6cc968059db9c62cb35fbf70248f40994dfcd7aa10444bbf8b3faeb7c2d67"}, + {file = "contourpy-1.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:570ef7cf892f0afbe5b2ee410c507ce12e15a5fa91017a0009f79f7d93a1268f"}, + {file = "contourpy-1.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:da84c537cb8b97d153e9fb208c221c45605f73147bd4cadd23bdae915042aad6"}, + {file = "contourpy-1.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0be4d8425bfa755e0fd76ee1e019636ccc7c29f77a7c86b4328a9eb6a26d0639"}, + {file = "contourpy-1.3.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9c0da700bf58f6e0b65312d0a5e695179a71d0163957fa381bb3c1f72972537c"}, + {file = "contourpy-1.3.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eb8b141bb00fa977d9122636b16aa67d37fd40a3d8b52dd837e536d64b9a4d06"}, + {file = "contourpy-1.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3634b5385c6716c258d0419c46d05c8aa7dc8cb70326c9a4fb66b69ad2b52e09"}, + {file = "contourpy-1.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0dce35502151b6bd35027ac39ba6e5a44be13a68f55735c3612c568cac3805fd"}, + {file = "contourpy-1.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:aea348f053c645100612b333adc5983d87be69acdc6d77d3169c090d3b01dc35"}, + {file = "contourpy-1.3.0-cp312-cp312-win32.whl", hash = "sha256:90f73a5116ad1ba7174341ef3ea5c3150ddf20b024b98fb0c3b29034752c8aeb"}, + {file = "contourpy-1.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:b11b39aea6be6764f84360fce6c82211a9db32a7c7de8fa6dd5397cf1d079c3b"}, + {file = "contourpy-1.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:3e1c7fa44aaae40a2247e2e8e0627f4bea3dd257014764aa644f319a5f8600e3"}, + {file = "contourpy-1.3.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:364174c2a76057feef647c802652f00953b575723062560498dc7930fc9b1cb7"}, + {file = "contourpy-1.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32b238b3b3b649e09ce9aaf51f0c261d38644bdfa35cbaf7b263457850957a84"}, + {file = "contourpy-1.3.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d51fca85f9f7ad0b65b4b9fe800406d0d77017d7270d31ec3fb1cc07358fdea0"}, + {file = "contourpy-1.3.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:732896af21716b29ab3e988d4ce14bc5133733b85956316fb0c56355f398099b"}, + {file = "contourpy-1.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d73f659398a0904e125280836ae6f88ba9b178b2fed6884f3b1f95b989d2c8da"}, + {file = "contourpy-1.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c6c7c2408b7048082932cf4e641fa3b8ca848259212f51c8c59c45aa7ac18f14"}, + {file = "contourpy-1.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f317576606de89da6b7e0861cf6061f6146ead3528acabff9236458a6ba467f8"}, + {file = "contourpy-1.3.0-cp313-cp313-win32.whl", hash = "sha256:31cd3a85dbdf1fc002280c65caa7e2b5f65e4a973fcdf70dd2fdcb9868069294"}, + {file = "contourpy-1.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:4553c421929ec95fb07b3aaca0fae668b2eb5a5203d1217ca7c34c063c53d087"}, + {file = "contourpy-1.3.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:345af746d7766821d05d72cb8f3845dfd08dd137101a2cb9b24de277d716def8"}, + {file = "contourpy-1.3.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:3bb3808858a9dc68f6f03d319acd5f1b8a337e6cdda197f02f4b8ff67ad2057b"}, + {file = "contourpy-1.3.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:420d39daa61aab1221567b42eecb01112908b2cab7f1b4106a52caaec8d36973"}, + {file = "contourpy-1.3.0-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4d63ee447261e963af02642ffcb864e5a2ee4cbfd78080657a9880b8b1868e18"}, + {file = "contourpy-1.3.0-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:167d6c890815e1dac9536dca00828b445d5d0df4d6a8c6adb4a7ec3166812fa8"}, + {file = "contourpy-1.3.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:710a26b3dc80c0e4febf04555de66f5fd17e9cf7170a7b08000601a10570bda6"}, + {file = "contourpy-1.3.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:75ee7cb1a14c617f34a51d11fa7524173e56551646828353c4af859c56b766e2"}, + {file = "contourpy-1.3.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:33c92cdae89ec5135d036e7218e69b0bb2851206077251f04a6c4e0e21f03927"}, + {file = "contourpy-1.3.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a11077e395f67ffc2c44ec2418cfebed032cd6da3022a94fc227b6faf8e2acb8"}, + {file = "contourpy-1.3.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e8134301d7e204c88ed7ab50028ba06c683000040ede1d617298611f9dc6240c"}, + {file = "contourpy-1.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e12968fdfd5bb45ffdf6192a590bd8ddd3ba9e58360b29683c6bb71a7b41edca"}, + {file = "contourpy-1.3.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fd2a0fc506eccaaa7595b7e1418951f213cf8255be2600f1ea1b61e46a60c55f"}, + {file = "contourpy-1.3.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4cfb5c62ce023dfc410d6059c936dcf96442ba40814aefbfa575425a3a7f19dc"}, + {file = "contourpy-1.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68a32389b06b82c2fdd68276148d7b9275b5f5cf13e5417e4252f6d1a34f72a2"}, + {file = "contourpy-1.3.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:94e848a6b83da10898cbf1311a815f770acc9b6a3f2d646f330d57eb4e87592e"}, + {file = "contourpy-1.3.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:d78ab28a03c854a873787a0a42254a0ccb3cb133c672f645c9f9c8f3ae9d0800"}, + {file = "contourpy-1.3.0-cp39-cp39-win32.whl", hash = "sha256:81cb5ed4952aae6014bc9d0421dec7c5835c9c8c31cdf51910b708f548cf58e5"}, + {file = "contourpy-1.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:14e262f67bd7e6eb6880bc564dcda30b15e351a594657e55b7eec94b6ef72843"}, + {file = "contourpy-1.3.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:fe41b41505a5a33aeaed2a613dccaeaa74e0e3ead6dd6fd3a118fb471644fd6c"}, + {file = "contourpy-1.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eca7e17a65f72a5133bdbec9ecf22401c62bcf4821361ef7811faee695799779"}, + {file = "contourpy-1.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:1ec4dc6bf570f5b22ed0d7efba0dfa9c5b9e0431aeea7581aa217542d9e809a4"}, + {file = "contourpy-1.3.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:00ccd0dbaad6d804ab259820fa7cb0b8036bda0686ef844d24125d8287178ce0"}, + {file = "contourpy-1.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ca947601224119117f7c19c9cdf6b3ab54c5726ef1d906aa4a69dfb6dd58102"}, + {file = "contourpy-1.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:c6ec93afeb848a0845a18989da3beca3eec2c0f852322efe21af1931147d12cb"}, ] [package.dependencies] -numpy = ">=1.20" +numpy = ">=1.23" [package.extras] bokeh = ["bokeh", "selenium"] docs = ["furo", "sphinx (>=7.2)", "sphinx-copybutton"] -mypy = ["contourpy[bokeh,docs]", "docutils-stubs", "mypy (==1.8.0)", "types-Pillow"] +mypy = ["contourpy[bokeh,docs]", "docutils-stubs", "mypy (==1.11.1)", "types-Pillow"] test = ["Pillow", "contourpy[test-no-images]", "matplotlib"] -test-no-images = ["pytest", "pytest-cov", "pytest-xdist", "wurlitzer"] +test-no-images = ["pytest", "pytest-cov", "pytest-rerunfailures", "pytest-xdist", "wurlitzer"] [[package]] name = "coverage" @@ -1190,6 +1210,48 @@ files = [ {file = "fqdn-1.5.1.tar.gz", hash = "sha256:105ed3677e767fb5ca086a0c1f4bb66ebc3c100be518f0e0d755d9eae164d89f"}, ] +[[package]] +name = "frozendict" +version = "2.4.4" +description = "A simple immutable dictionary" +optional = false +python-versions = ">=3.6" +files = [ + {file = "frozendict-2.4.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4a59578d47b3949437519b5c39a016a6116b9e787bb19289e333faae81462e59"}, + {file = "frozendict-2.4.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:12a342e439aef28ccec533f0253ea53d75fe9102bd6ea928ff530e76eac38906"}, + {file = "frozendict-2.4.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f79c26dff10ce11dad3b3627c89bb2e87b9dd5958c2b24325f16a23019b8b94"}, + {file = "frozendict-2.4.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2bd009cf4fc47972838a91e9b83654dc9a095dc4f2bb3a37c3f3124c8a364543"}, + {file = "frozendict-2.4.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:87ebcde21565a14fe039672c25550060d6f6d88cf1f339beac094c3b10004eb0"}, + {file = "frozendict-2.4.4-cp310-cp310-win_amd64.whl", hash = "sha256:fefeb700bc7eb8b4c2dc48704e4221860d254c8989fb53488540bc44e44a1ac2"}, + {file = "frozendict-2.4.4-cp310-cp310-win_arm64.whl", hash = "sha256:4297d694eb600efa429769125a6f910ec02b85606f22f178bafbee309e7d3ec7"}, + {file = "frozendict-2.4.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:812ab17522ba13637826e65454115a914c2da538356e85f43ecea069813e4b33"}, + {file = "frozendict-2.4.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7fee9420475bb6ff357000092aa9990c2f6182b2bab15764330f4ad7de2eae49"}, + {file = "frozendict-2.4.4-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:3148062675536724502c6344d7c485dd4667fdf7980ca9bd05e338ccc0c4471e"}, + {file = "frozendict-2.4.4-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:78c94991944dd33c5376f720228e5b252ee67faf3bac50ef381adc9e51e90d9d"}, + {file = "frozendict-2.4.4-cp36-cp36m-win_amd64.whl", hash = "sha256:1697793b5f62b416c0fc1d94638ec91ed3aa4ab277f6affa3a95216ecb3af170"}, + {file = "frozendict-2.4.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:199a4d32194f3afed6258de7e317054155bc9519252b568d9cfffde7e4d834e5"}, + {file = "frozendict-2.4.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:85375ec6e979e6373bffb4f54576a68bf7497c350861d20686ccae38aab69c0a"}, + {file = "frozendict-2.4.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:2d8536e068d6bf281f23fa835ac07747fb0f8851879dd189e9709f9567408b4d"}, + {file = "frozendict-2.4.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:259528ba6b56fa051bc996f1c4d8b57e30d6dd3bc2f27441891b04babc4b5e73"}, + {file = "frozendict-2.4.4-cp37-cp37m-win_amd64.whl", hash = "sha256:07c3a5dee8bbb84cba770e273cdbf2c87c8e035903af8f781292d72583416801"}, + {file = "frozendict-2.4.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6874fec816b37b6eb5795b00e0574cba261bf59723e2de607a195d5edaff0786"}, + {file = "frozendict-2.4.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8f92425686323a950337da4b75b4c17a3327b831df8c881df24038d560640d4"}, + {file = "frozendict-2.4.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d58d9a8d9e49662c6dafbea5e641f97decdb3d6ccd76e55e79818415362ba25"}, + {file = "frozendict-2.4.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:93a7b19afb429cbf99d56faf436b45ef2fa8fe9aca89c49eb1610c3bd85f1760"}, + {file = "frozendict-2.4.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2b70b431e3a72d410a2cdf1497b3aba2f553635e0c0f657ce311d841bf8273b6"}, + {file = "frozendict-2.4.4-cp38-cp38-win_amd64.whl", hash = "sha256:e1b941132d79ce72d562a13341d38fc217bc1ee24d8c35a20d754e79ff99e038"}, + {file = "frozendict-2.4.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:dc2228874eacae390e63fd4f2bb513b3144066a977dc192163c9f6c7f6de6474"}, + {file = "frozendict-2.4.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:63aa49f1919af7d45fb8fd5dec4c0859bc09f46880bd6297c79bb2db2969b63d"}, + {file = "frozendict-2.4.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6bf9260018d653f3cab9bd147bd8592bf98a5c6e338be0491ced3c196c034a3"}, + {file = "frozendict-2.4.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6eb716e6a6d693c03b1d53280a1947716129f5ef9bcdd061db5c17dea44b80fe"}, + {file = "frozendict-2.4.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d13b4310db337f4d2103867c5a05090b22bc4d50ca842093779ef541ea9c9eea"}, + {file = "frozendict-2.4.4-cp39-cp39-win_amd64.whl", hash = "sha256:b3b967d5065872e27b06f785a80c0ed0a45d1f7c9b85223da05358e734d858ca"}, + {file = "frozendict-2.4.4-cp39-cp39-win_arm64.whl", hash = "sha256:4ae8d05c8d0b6134bfb6bfb369d5fa0c4df21eabb5ca7f645af95fdc6689678e"}, + {file = "frozendict-2.4.4-py311-none-any.whl", hash = "sha256:705efca8d74d3facbb6ace80ab3afdd28eb8a237bfb4063ed89996b024bc443d"}, + {file = "frozendict-2.4.4-py312-none-any.whl", hash = "sha256:d9647563e76adb05b7cde2172403123380871360a114f546b4ae1704510801e5"}, + {file = "frozendict-2.4.4.tar.gz", hash = "sha256:3f7c031b26e4ee6a3f786ceb5e3abf1181c4ade92dce1f847da26ea2c96008c7"}, +] + [[package]] name = "frozenlist" version = "1.4.1" @@ -1384,13 +1446,13 @@ trio = ["trio (>=0.22.0,<0.26.0)"] [[package]] name = "httpx" -version = "0.27.0" +version = "0.27.2" description = "The next generation HTTP client." optional = false python-versions = ">=3.8" files = [ - {file = "httpx-0.27.0-py3-none-any.whl", hash = "sha256:71d5465162c13681bff01ad59b2cc68dd838ea1f10e51574bac27103f00c91a5"}, - {file = "httpx-0.27.0.tar.gz", hash = "sha256:a0cb88a46f32dc874e04ee956e4c2764aba2aa228f650b06788ba6bda2962ab5"}, + {file = "httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0"}, + {file = "httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2"}, ] [package.dependencies] @@ -1405,6 +1467,7 @@ brotli = ["brotli", "brotlicffi"] cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"] http2 = ["h2 (>=3,<5)"] socks = ["socksio (==1.*)"] +zstd = ["zstandard (>=0.18.0)"] [[package]] name = "huggingface-hub" @@ -1442,13 +1505,13 @@ typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "t [[package]] name = "idna" -version = "3.7" +version = "3.8" description = "Internationalized Domain Names in Applications (IDNA)" optional = false -python-versions = ">=3.5" +python-versions = ">=3.6" files = [ - {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"}, - {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"}, + {file = "idna-3.8-py3-none-any.whl", hash = "sha256:050b4e5baadcd44d760cedbd2b8e639f2ff89bbc7a5730fcc662954303377aac"}, + {file = "idna-3.8.tar.gz", hash = "sha256:d838c2c0ed6fced7693d5e8ab8e734d5f8fda53a039c0164afb0b82e771e3603"}, ] [[package]] @@ -1554,21 +1617,21 @@ test-extra = ["curio", "ipython[test]", "matplotlib (!=3.2.0)", "nbformat", "num [[package]] name = "ipywidgets" -version = "8.1.3" +version = "8.1.5" description = "Jupyter interactive widgets" optional = false python-versions = ">=3.7" files = [ - {file = "ipywidgets-8.1.3-py3-none-any.whl", hash = "sha256:efafd18f7a142248f7cb0ba890a68b96abd4d6e88ddbda483c9130d12667eaf2"}, - {file = "ipywidgets-8.1.3.tar.gz", hash = "sha256:f5f9eeaae082b1823ce9eac2575272952f40d748893972956dc09700a6392d9c"}, + {file = "ipywidgets-8.1.5-py3-none-any.whl", hash = "sha256:3290f526f87ae6e77655555baba4f36681c555b8bdbbff430b70e52c34c86245"}, + {file = "ipywidgets-8.1.5.tar.gz", hash = "sha256:870e43b1a35656a80c18c9503bbf2d16802db1cb487eec6fab27d683381dde17"}, ] [package.dependencies] comm = ">=0.1.3" ipython = ">=6.1.0" -jupyterlab-widgets = ">=3.0.11,<3.1.0" +jupyterlab-widgets = ">=3.0.12,<3.1.0" traitlets = ">=4.3.1" -widgetsnbextension = ">=4.0.11,<4.1.0" +widgetsnbextension = ">=4.0.12,<4.1.0" [package.extras] test = ["ipykernel", "jsonschema", "pytest (>=3.6.0)", "pytest-cov", "pytz"] @@ -1909,13 +1972,13 @@ test = ["jupyter-server (>=2.0.0)", "pytest (>=7.0)", "pytest-jupyter[server] (> [[package]] name = "jupyterlab" -version = "4.2.4" +version = "4.2.5" description = "JupyterLab computational environment" optional = false python-versions = ">=3.8" files = [ - {file = "jupyterlab-4.2.4-py3-none-any.whl", hash = "sha256:807a7ec73637744f879e112060d4b9d9ebe028033b7a429b2d1f4fc523d00245"}, - {file = "jupyterlab-4.2.4.tar.gz", hash = "sha256:343a979fb9582fd08c8511823e320703281cd072a0049bcdafdc7afeda7f2537"}, + {file = "jupyterlab-4.2.5-py3-none-any.whl", hash = "sha256:73b6e0775d41a9fee7ee756c80f58a6bed4040869ccc21411dc559818874d321"}, + {file = "jupyterlab-4.2.5.tar.gz", hash = "sha256:ae7f3a1b8cb88b4f55009ce79fa7c06f99d70cd63601ee4aa91815d054f46f75"}, ] [package.dependencies] @@ -1979,13 +2042,13 @@ test = ["hatch", "ipykernel", "openapi-core (>=0.18.0,<0.19.0)", "openapi-spec-v [[package]] name = "jupyterlab-widgets" -version = "3.0.11" +version = "3.0.13" description = "Jupyter interactive widgets for JupyterLab" optional = false python-versions = ">=3.7" files = [ - {file = "jupyterlab_widgets-3.0.11-py3-none-any.whl", hash = "sha256:78287fd86d20744ace330a61625024cf5521e1c012a352ddc0a3cdc2348becd0"}, - {file = "jupyterlab_widgets-3.0.11.tar.gz", hash = "sha256:dd5ac679593c969af29c9bed054c24f26842baa51352114736756bc035deee27"}, + {file = "jupyterlab_widgets-3.0.13-py3-none-any.whl", hash = "sha256:e3cda2c233ce144192f1e29914ad522b2f4c40e77214b0cc97377ca3d323db54"}, + {file = "jupyterlab_widgets-3.0.13.tar.gz", hash = "sha256:a2966d385328c1942b683a8cd96b89b8dd82c8b8f81dda902bb2bc06d46f5bed"}, ] [[package]] @@ -2313,24 +2376,30 @@ traitlets = "*" [[package]] name = "maze-dataset" -version = "0.5.6" +version = "1.0.0" description = "" optional = false -python-versions = "<4.0,>=3.10" -files = [ - {file = "maze_dataset-0.5.6-py3-none-any.whl", hash = "sha256:6013198a6efc253db04f9f39241bdfbbcc0b9724fad91d5bf06611790893985d"}, - {file = "maze_dataset-0.5.6.tar.gz", hash = "sha256:ffdd559f843c5f77d37421edd94f88c6bd43569cd5b3162a7b98de60b26e376b"}, -] +python-versions = "^3.10.6" +files = [] +develop = false [package.dependencies] -ipykernel = ">=6.22.0,<7.0.0" -jaxtyping = ">=0.2.19,<0.3.0" -jupyter = ">=1.0.0,<2.0.0" -matplotlib = ">=3.7.0,<4.0.0" -muutils = ">=0.6.7,<0.7.0" +frozendict = "^2.4.4" +ipykernel = "^6.22.0" +jaxtyping = "^0.2.19" +jupyter = "^1.0.0" +matplotlib = "^3.7.0" +muutils = "^0.6.10" +pandas = "^2.2.2" torch = ">=1.13.1" -tqdm = ">=4.65.0,<5.0.0" -zanj = ">=0.3.1,<0.4.0" +tqdm = "^4.65.0" +zanj = "^0.3.1" + +[package.source] +type = "git" +url = "https://github.com/understanding-search/maze-dataset.git" +reference = "HEAD" +resolved_reference = "d5a20d6f7daf6a9b4d126499c4dc275345f633a5" [[package]] name = "mdurl" @@ -2496,13 +2565,13 @@ dill = ">=0.3.8" [[package]] name = "muutils" -version = "0.6.7" +version = "0.6.10" description = "miscellaneous python utilities" optional = false python-versions = "<4.0,>=3.8" files = [ - {file = "muutils-0.6.7-py3-none-any.whl", hash = "sha256:91cc352a16f701f00b476fd53d9d3f858d785cc6275faabd620d34150940712c"}, - {file = "muutils-0.6.7.tar.gz", hash = "sha256:06d40f6e6c5390418b091a7326f7d78bc4470cc5741a13f4a4160c382f8c1eae"}, + {file = "muutils-0.6.10-py3-none-any.whl", hash = "sha256:a7f4ba138d86a3981ff2ca5d2e7a00102ce12fc0f2009bd8041aa577cad642d5"}, + {file = "muutils-0.6.10.tar.gz", hash = "sha256:3aff934606f485c89f32feec11432e74fcb8dfd6e4f18486bbdc32696cf86a6e"}, ] [package.dependencies] @@ -2639,13 +2708,13 @@ test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"] [[package]] name = "notebook" -version = "7.2.1" +version = "7.2.2" description = "Jupyter Notebook - A web-based notebook environment for interactive computing" optional = false python-versions = ">=3.8" files = [ - {file = "notebook-7.2.1-py3-none-any.whl", hash = "sha256:f45489a3995746f2195a137e0773e2130960b51c9ac3ce257dbc2705aab3a6ca"}, - {file = "notebook-7.2.1.tar.gz", hash = "sha256:4287b6da59740b32173d01d641f763d292f49c30e7a51b89c46ba8473126341e"}, + {file = "notebook-7.2.2-py3-none-any.whl", hash = "sha256:c89264081f671bc02eec0ed470a627ed791b9156cad9285226b31611d3e9fe1c"}, + {file = "notebook-7.2.2.tar.gz", hash = "sha256:2ef07d4220421623ad3fe88118d687bc0450055570cdd160814a59cf3a1c516e"}, ] [package.dependencies] @@ -3185,22 +3254,22 @@ wcwidth = "*" [[package]] name = "protobuf" -version = "5.27.3" +version = "5.27.4" description = "" optional = false python-versions = ">=3.8" files = [ - {file = "protobuf-5.27.3-cp310-abi3-win32.whl", hash = "sha256:dcb307cd4ef8fec0cf52cb9105a03d06fbb5275ce6d84a6ae33bc6cf84e0a07b"}, - {file = "protobuf-5.27.3-cp310-abi3-win_amd64.whl", hash = "sha256:16ddf3f8c6c41e1e803da7abea17b1793a97ef079a912e42351eabb19b2cffe7"}, - {file = "protobuf-5.27.3-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:68248c60d53f6168f565a8c76dc58ba4fa2ade31c2d1ebdae6d80f969cdc2d4f"}, - {file = "protobuf-5.27.3-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:b8a994fb3d1c11156e7d1e427186662b64694a62b55936b2b9348f0a7c6625ce"}, - {file = "protobuf-5.27.3-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:a55c48f2a2092d8e213bd143474df33a6ae751b781dd1d1f4d953c128a415b25"}, - {file = "protobuf-5.27.3-cp38-cp38-win32.whl", hash = "sha256:043853dcb55cc262bf2e116215ad43fa0859caab79bb0b2d31b708f128ece035"}, - {file = "protobuf-5.27.3-cp38-cp38-win_amd64.whl", hash = "sha256:c2a105c24f08b1e53d6c7ffe69cb09d0031512f0b72f812dd4005b8112dbe91e"}, - {file = "protobuf-5.27.3-cp39-cp39-win32.whl", hash = "sha256:c84eee2c71ed83704f1afbf1a85c3171eab0fd1ade3b399b3fad0884cbcca8bf"}, - {file = "protobuf-5.27.3-cp39-cp39-win_amd64.whl", hash = "sha256:af7c0b7cfbbb649ad26132e53faa348580f844d9ca46fd3ec7ca48a1ea5db8a1"}, - {file = "protobuf-5.27.3-py3-none-any.whl", hash = "sha256:8572c6533e544ebf6899c360e91d6bcbbee2549251643d32c52cf8a5de295ba5"}, - {file = "protobuf-5.27.3.tar.gz", hash = "sha256:82460903e640f2b7e34ee81a947fdaad89de796d324bcbc38ff5430bcdead82c"}, + {file = "protobuf-5.27.4-cp310-abi3-win32.whl", hash = "sha256:10319748764b917a9a7cddef1582a0a9cd0f8f6d04e545c6236f7ccaf9b624d9"}, + {file = "protobuf-5.27.4-cp310-abi3-win_amd64.whl", hash = "sha256:f0c24374aaaf103f33662e4de7666a4a4280abebdb8a9f3f0f9b1d71b61174ec"}, + {file = "protobuf-5.27.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e85fed07013e5a0121efbaf1b14355fdc66f6e545f12fc5985b2882370410006"}, + {file = "protobuf-5.27.4-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:d5a0e229061600842e57af4ff6a8522ede5280bcfa4fe7f3a1c20589377859a6"}, + {file = "protobuf-5.27.4-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:25ba1f0633f73c3939f3b84e1636f3eb3bab7196952ebb83906d56945edd6aa8"}, + {file = "protobuf-5.27.4-cp38-cp38-win32.whl", hash = "sha256:565b051249a2f8270af04206dd4f3b73a02343e7d9e072aed57441b369b3467d"}, + {file = "protobuf-5.27.4-cp38-cp38-win_amd64.whl", hash = "sha256:e673f173cbac4e59c7817ed358e471e4c77aa9166986edf3e731156379a556c7"}, + {file = "protobuf-5.27.4-cp39-cp39-win32.whl", hash = "sha256:25169c7624d5a9e669fa6faff5a6e818f854346d51ee347b2284676beb9e85dd"}, + {file = "protobuf-5.27.4-cp39-cp39-win_amd64.whl", hash = "sha256:1fe7735902e84ce35c4152cf07981c176713935a8efad78cea547aae5f4f75cb"}, + {file = "protobuf-5.27.4-py3-none-any.whl", hash = "sha256:b97259641e8d38738eef34a173e51d2d53a453baab01a32477a64752d9ce59a3"}, + {file = "protobuf-5.27.4.tar.gz", hash = "sha256:eaa1016e353d8fc5bf08c8087e96eed15f5297aa52bb7ee1f533278bb3f3aad7"}, ] [[package]] @@ -3353,13 +3422,13 @@ windows-terminal = ["colorama (>=0.4.6)"] [[package]] name = "pyparsing" -version = "3.1.2" +version = "3.1.4" description = "pyparsing module - Classes and methods to define and execute parsing grammars" optional = false python-versions = ">=3.6.8" files = [ - {file = "pyparsing-3.1.2-py3-none-any.whl", hash = "sha256:f9db75911801ed778fe61bb643079ff86601aca99fcae6345aa67292038fb742"}, - {file = "pyparsing-3.1.2.tar.gz", hash = "sha256:a1bac0ce561155ecc3ed78ca94d3c9378656ad4c94c1270de543f621420f94ad"}, + {file = "pyparsing-3.1.4-py3-none-any.whl", hash = "sha256:a6a7ee4235a3f944aa1fa2249307708f893fe5717dc603503c6c7969c070fb7c"}, + {file = "pyparsing-3.1.4.tar.gz", hash = "sha256:f86ec8d1a83f11977c9a6ea7598e8c27fc5cddfa5b07ea2241edbbde1d7bc032"}, ] [package.extras] @@ -3560,120 +3629,120 @@ files = [ [[package]] name = "pyzmq" -version = "26.1.1" +version = "26.2.0" description = "Python bindings for 0MQ" optional = false python-versions = ">=3.7" files = [ - {file = "pyzmq-26.1.1-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:b1bb952d1e407463c9333ea7e0c0600001e54e08ce836d4f0aff1fb3f902cf63"}, - {file = "pyzmq-26.1.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:65e2a18e845c6ea7ab849c70db932eaeadee5edede9e379eb21c0a44cf523b2e"}, - {file = "pyzmq-26.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:def7ae3006924b8a0c146a89ab4008310913fa903beedb95e25dea749642528e"}, - {file = "pyzmq-26.1.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a8234571df7816f99dde89c3403cb396d70c6554120b795853a8ea56fcc26cd3"}, - {file = "pyzmq-26.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18da8e84dbc30688fd2baefd41df7190607511f916be34f9a24b0e007551822e"}, - {file = "pyzmq-26.1.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:c70dab93d98b2bf3f0ac1265edbf6e7f83acbf71dabcc4611889bb0dea45bed7"}, - {file = "pyzmq-26.1.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:fcb90592c5d5c562e1b1a1ceccf6f00036d73c51db0271bf4d352b8d6b31d468"}, - {file = "pyzmq-26.1.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:cf4be7460a0c1bc71e9b0e64ecdd75a86386ca6afaa36641686f5542d0314e9d"}, - {file = "pyzmq-26.1.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4cbecda4ddbfc1e309c3be04d333f9be3fc6178b8b6592b309676f929767a15"}, - {file = "pyzmq-26.1.1-cp310-cp310-win32.whl", hash = "sha256:583f73b113b8165713b6ce028d221402b1b69483055b5aa3f991937e34dd1ead"}, - {file = "pyzmq-26.1.1-cp310-cp310-win_amd64.whl", hash = "sha256:5e6f39ecb8eb7bfcb976c49262e8cf83ff76e082b77ca23ba90c9b6691a345be"}, - {file = "pyzmq-26.1.1-cp310-cp310-win_arm64.whl", hash = "sha256:8d042d6446cab3a1388b38596f5acabb9926b0b95c3894c519356b577a549458"}, - {file = "pyzmq-26.1.1-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:362cac2423e36966d336d79d3ec3eafeabc153ee3e7a5cf580d7e74a34b3d912"}, - {file = "pyzmq-26.1.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0841633446cb1539a832a19bb24c03a20c00887d0cedd1d891b495b07e5c5cb5"}, - {file = "pyzmq-26.1.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e1fcdc333afbf9918d0a614a6e10858aede7da49a60f6705a77e343fe86a317"}, - {file = "pyzmq-26.1.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cc8d655627d775475eafdcf0e49e74bcc1e5e90afd9ab813b4da98f092ed7b93"}, - {file = "pyzmq-26.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:32de51744820857a6f7c3077e620ab3f607d0e4388dfead885d5124ab9bcdc5e"}, - {file = "pyzmq-26.1.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a880240597010914ffb1d6edd04d3deb7ce6a2abf79a0012751438d13630a671"}, - {file = "pyzmq-26.1.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:26131b1cec02f941ed2d2b4b8cc051662b1c248b044eff5069df1f500bbced56"}, - {file = "pyzmq-26.1.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:ce05841322b58510607f9508a573138d995a46c7928887bc433de9cb760fd2ad"}, - {file = "pyzmq-26.1.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:32123ff0a6db521aadf2b95201e967a4e0d11fb89f73663a99d2f54881c07214"}, - {file = "pyzmq-26.1.1-cp311-cp311-win32.whl", hash = "sha256:e790602d7ea1d6c7d8713d571226d67de7ffe47b1e22ae2c043ebd537de1bccb"}, - {file = "pyzmq-26.1.1-cp311-cp311-win_amd64.whl", hash = "sha256:717960855f2d6fdc2dba9df49dff31c414187bb11c76af36343a57d1f7083d9a"}, - {file = "pyzmq-26.1.1-cp311-cp311-win_arm64.whl", hash = "sha256:08956c26dbcd4fd8835cb777a16e21958ed2412317630e19f0018d49dbeeb470"}, - {file = "pyzmq-26.1.1-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:e80345900ae241c2c51bead7c9fa247bba6d4b2a83423e9791bae8b0a7f12c52"}, - {file = "pyzmq-26.1.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ec8fe214fcc45dfb0c32e4a7ad1db20244ba2d2fecbf0cbf9d5242d81ca0a375"}, - {file = "pyzmq-26.1.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf4e283f97688d993cb7a8acbc22889effbbb7cbaa19ee9709751f44be928f5d"}, - {file = "pyzmq-26.1.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2508bdc8ab246e5ed7c92023d4352aaad63020ca3b098a4e3f1822db202f703d"}, - {file = "pyzmq-26.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:741bdb4d96efe8192616abdc3671931d51a8bcd38c71da2d53fb3127149265d1"}, - {file = "pyzmq-26.1.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:76154943e4c4054b2591792eb3484ef1dd23d59805759f9cebd2f010aa30ee8c"}, - {file = "pyzmq-26.1.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9498ac427d20d0e0ef0e4bbd6200841e91640dfdf619f544ceec7f464cfb6070"}, - {file = "pyzmq-26.1.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:6f34453ef3496ca3462f30435bf85f535f9550392987341f9ccc92c102825a79"}, - {file = "pyzmq-26.1.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:50f0669324e27cc2091ef6ab76ca7112f364b6249691790b4cffce31e73fda28"}, - {file = "pyzmq-26.1.1-cp312-cp312-win32.whl", hash = "sha256:3ee5cbf2625b94de21c68d0cefd35327c8dfdbd6a98fcc41682b4e8bb00d841f"}, - {file = "pyzmq-26.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:75bd448a28b1001b6928679015bc95dd5f172703ed30135bb9e34fc9cda0a3e7"}, - {file = "pyzmq-26.1.1-cp312-cp312-win_arm64.whl", hash = "sha256:4350233569b4bbef88595c5e77ee38995a6f1f1790fae148b578941bfffd1c24"}, - {file = "pyzmq-26.1.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6c8087a3281c20b1d11042d372ed5a47734af05975d78e4d1d6e7bd1018535f3"}, - {file = "pyzmq-26.1.1-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:ebef7d3fe11fe4c688f08bc0211a976c3318c097057f258428200737b9fff4da"}, - {file = "pyzmq-26.1.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7a5342110510045a47de1e87f5f1dcc1d9d90109522316dc9830cfc6157c800f"}, - {file = "pyzmq-26.1.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:af690ea4be6ca92a67c2b44a779a023bf0838e92d48497a2268175dc4a505691"}, - {file = "pyzmq-26.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc994e220c1403ae087d7f0fa45129d583e46668a019e389060da811a5a9320e"}, - {file = "pyzmq-26.1.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:b8e153f5dffb0310af71fc6fc9cd8174f4c8ea312c415adcb815d786fee78179"}, - {file = "pyzmq-26.1.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:0065026e624052a51033857e5cd45a94b52946b44533f965f0bdf182460e965d"}, - {file = "pyzmq-26.1.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:63351392f948b5d50b9f55161994bc4feedbfb3f3cfe393d2f503dea2c3ec445"}, - {file = "pyzmq-26.1.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ffecc43b3c18e36b62fcec995761829b6ac325d8dd74a4f2c5c1653afbb4495a"}, - {file = "pyzmq-26.1.1-cp313-cp313-win32.whl", hash = "sha256:6ff14c2fae6c0c2c1c02590c5c5d75aa1db35b859971b3ca2fcd28f983d9f2b6"}, - {file = "pyzmq-26.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:85f2d2ee5ea9a8f1de86a300e1062fbab044f45b5ce34d20580c0198a8196db0"}, - {file = "pyzmq-26.1.1-cp313-cp313-win_arm64.whl", hash = "sha256:cc09b1de8b985ca5a0ca343dd7fb007267c6b329347a74e200f4654268084239"}, - {file = "pyzmq-26.1.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:bc904e86de98f8fc5bd41597da5d61232d2d6d60c4397f26efffabb961b2b245"}, - {file = "pyzmq-26.1.1-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:00f39c367bbd6aa8e4bc36af6510561944c619b58eb36199fa334b594a18f615"}, - {file = "pyzmq-26.1.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de6f384864a959866b782e6a3896538d1424d183f2d3c7ef079f71dcecde7284"}, - {file = "pyzmq-26.1.1-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3abb15df0c763339edb27a644c19381b2425ddd1aea3dbd77c1601a3b31867b8"}, - {file = "pyzmq-26.1.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40908ec2dd3b29bbadc0916a0d3c87f8dbeebbd8fead8e618539f09e0506dec4"}, - {file = "pyzmq-26.1.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:c11a95d3f6fc7e714ccd1066f68f9c1abd764a8b3596158be92f46dd49f41e03"}, - {file = "pyzmq-26.1.1-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:4437af9fee7a58302dbd511cc49f0cc2b35c112a33a1111fb123cf0be45205ca"}, - {file = "pyzmq-26.1.1-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:76390d3d66406cb01b9681c382874400e9dfd77f30ecdea4bd1bf5226dd4aff0"}, - {file = "pyzmq-26.1.1-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:4d4c7fe5e50e269f9c63a260638488fec194a73993008618a59b54c47ef6ae72"}, - {file = "pyzmq-26.1.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:25d128524207f53f7aae7c5abdc2b63f8957a060b00521af5ffcd20986b5d8f4"}, - {file = "pyzmq-26.1.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d74b925d997e4f92b042bdd7085cd0a309ee0fd7cb4dc376059bbff6b32ff34f"}, - {file = "pyzmq-26.1.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:732f957441e5b1c65a7509395e6b6cafee9e12df9aa5f4bf92ed266fe0ba70ee"}, - {file = "pyzmq-26.1.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f0a45102ad7ed9f9ddf2bd699cc5df37742cf7301111cba06001b927efecb120"}, - {file = "pyzmq-26.1.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9f380d5333fc7cd17423f486125dcc073918676e33db70a6a8172b19fc78d23d"}, - {file = "pyzmq-26.1.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:8eaffcd6bf6a9d00b66a2052a33fa7e6a6575427e9644395f13c3d070f2918dc"}, - {file = "pyzmq-26.1.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:f1483d4975ae1b387b39bb8e23d1ff32fe5621aa9e4ed3055d05e9c5613fea53"}, - {file = "pyzmq-26.1.1-cp37-cp37m-win32.whl", hash = "sha256:a83653c6bbe5887caea55e49fbd2909c14b73acf43bcc051eb60b2d514bbd46e"}, - {file = "pyzmq-26.1.1-cp37-cp37m-win_amd64.whl", hash = "sha256:9763a8d3f5f74ef679989b373c37cc22e8d07e56d26439205cb83edb7722357f"}, - {file = "pyzmq-26.1.1-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:2b045647caf620ce0ed6c8fd9fb6a73116f99aceed966b152a5ba1b416d25311"}, - {file = "pyzmq-26.1.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f66dcb6625c002f209cdc12cae1a1fec926493cd2262efe37dc6b25a30cea863"}, - {file = "pyzmq-26.1.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0cf1d980c969fb9e538f52abd2227f09e015096bc5c3ef7aa26e0d64051c1db8"}, - {file = "pyzmq-26.1.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:443ebf5e261a95ee9725693f2a5a71401f89b89df0e0ea58844b074067aac2f1"}, - {file = "pyzmq-26.1.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29de77ba1b1877fe7defc1b9140e65cbd35f72a63bc501e56c2eae55bde5fff4"}, - {file = "pyzmq-26.1.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2f6071ec95af145d7b659dae6786871cd85f0acc599286b6f8ba0c74592d83dd"}, - {file = "pyzmq-26.1.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6f0512fc87629ad968889176bf2165d721cd817401a281504329e2a2ed0ca6a3"}, - {file = "pyzmq-26.1.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:5ccfcf13e80719f6a2d9c0a021d9e47d4550907a29253554be2c09582f6d7963"}, - {file = "pyzmq-26.1.1-cp38-cp38-win32.whl", hash = "sha256:809673947e95752e407aaaaf03f205ee86ebfff9ca51db6d4003dfd87b8428d1"}, - {file = "pyzmq-26.1.1-cp38-cp38-win_amd64.whl", hash = "sha256:62b5180e23e6f581600459cd983473cd723fdc64350f606d21407c99832aaf5f"}, - {file = "pyzmq-26.1.1-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:fe73d7c89d6f803bed122135ff5783364e8cdb479cf6fe2d764a44b6349e7e0f"}, - {file = "pyzmq-26.1.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:db1b7e2b50ef21f398036786da4c153db63203a402396d9f21e08ea61f3f8dba"}, - {file = "pyzmq-26.1.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:7c506a51cb01bb997a3f6440db0d121e5e7a32396e9948b1fdb6a7bfa67243f4"}, - {file = "pyzmq-26.1.1-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:92eca4f80e8a748d880e55d3cf57ef487692e439f12d5c5a2e1cce84aaa7f6cb"}, - {file = "pyzmq-26.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14bdbae02f72f4716b0ffe7500e9da303d719ddde1f3dcfb4c4f6cc1cf73bb02"}, - {file = "pyzmq-26.1.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:e03be7ed17836c9434cce0668ac1e2cc9143d7169f90f46a0167f6155e176e32"}, - {file = "pyzmq-26.1.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bc5df31e36e4fddd4c8b5c42daee8d54d7b529e898ac984be97bf5517de166a7"}, - {file = "pyzmq-26.1.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:f218179c90a12d660906e04b25a340dd63e9743000ba16232ddaf46888f269da"}, - {file = "pyzmq-26.1.1-cp39-cp39-win32.whl", hash = "sha256:7dfabc180a4da422a4b349c63077347392463a75fa07aa3be96712ed6d42c547"}, - {file = "pyzmq-26.1.1-cp39-cp39-win_amd64.whl", hash = "sha256:c5248e6e0fcbbbc912982e99cdd51c342601f495b0fa5bd667f3bdbdbf3e170f"}, - {file = "pyzmq-26.1.1-cp39-cp39-win_arm64.whl", hash = "sha256:2ae7aa1408778dc74582a1226052b930f9083b54b64d7e6ef6ec0466cfdcdec2"}, - {file = "pyzmq-26.1.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:be3fc2b11c0c384949cf1f01f9a48555039408b0f3e877863b1754225635953e"}, - {file = "pyzmq-26.1.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:48dee75c2a9fa4f4a583d4028d564a0453447ee1277a29b07acc3743c092e259"}, - {file = "pyzmq-26.1.1-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:23f2fe4fb567e8098ebaa7204819658195b10ddd86958a97a6058eed2901eed3"}, - {file = "pyzmq-26.1.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:472cacd16f627c06d3c8b2d374345ab74446bae913584a6245e2aa935336d929"}, - {file = "pyzmq-26.1.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:8285b25aa20fcc46f1ca4afbc39fd3d5f2fe4c4bbf7f2c7f907a214e87a70024"}, - {file = "pyzmq-26.1.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2067e63fd9d5c13cfe12624dab0366053e523b37a7a01678ce4321f839398939"}, - {file = "pyzmq-26.1.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:cc109be2ee3638035d276e18eaf66a1e1f44201c0c4bea4ee0c692766bbd3570"}, - {file = "pyzmq-26.1.1-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:d0da97e65ee73261dba70469cc8f63d8da3a8a825337a2e3d246b9e95141cdd0"}, - {file = "pyzmq-26.1.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa79c528706561306938b275f89bb2c6985ce08469c27e5de05bc680df5e826f"}, - {file = "pyzmq-26.1.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:3ddbd851a3a2651fdc5065a2804d50cf2f4b13b1bcd66de8e9e855d0217d4fcd"}, - {file = "pyzmq-26.1.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:d3df226ab7464684ae6706e20a5cbab717c3735a7e409b3fa598b754d49f1946"}, - {file = "pyzmq-26.1.1-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:abad7b897e960d577eb4a0f3f789c1780bc3ffe2e7c27cf317e7c90ad26acf12"}, - {file = "pyzmq-26.1.1-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c513d829a548c2d5c88983167be2b3aa537f6d1191edcdc6fcd8999e18bdd994"}, - {file = "pyzmq-26.1.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70af4c9c991714ef1c65957605a8de42ef0d0620dd5f125953c8e682281bdb80"}, - {file = "pyzmq-26.1.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:8d4234f335b0d0842f7d661d8cd50cbad0729be58f1c4deb85cd96b38fe95025"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:2c0fdb7b758e0e1605157e480b00b3a599073068a37091a1c75ec65bf7498645"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc657577f057d60dd3642c9f95f28b432889b73143140061f7c1331d02f03df6"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3e3b66fe6131b4f33d239f7d4c3bfb2f8532d8644bae3b3da4f3987073edac55"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59b57e912feef6951aec8bb03fe0faa5ad5f36962883c72a30a9c965e6d988fd"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:146956aec7d947c5afc5e7da0841423d7a53f84fd160fff25e682361dcfb32cb"}, - {file = "pyzmq-26.1.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:9521b874fd489495865172f344e46e0159095d1f161858e3fc6e28e43ca15160"}, - {file = "pyzmq-26.1.1.tar.gz", hash = "sha256:a7db05d8b7cd1a8c6610e9e9aa55d525baae7a44a43e18bc3260eb3f92de96c6"}, + {file = "pyzmq-26.2.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:ddf33d97d2f52d89f6e6e7ae66ee35a4d9ca6f36eda89c24591b0c40205a3629"}, + {file = "pyzmq-26.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dacd995031a01d16eec825bf30802fceb2c3791ef24bcce48fa98ce40918c27b"}, + {file = "pyzmq-26.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89289a5ee32ef6c439086184529ae060c741334b8970a6855ec0b6ad3ff28764"}, + {file = "pyzmq-26.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5506f06d7dc6ecf1efacb4a013b1f05071bb24b76350832c96449f4a2d95091c"}, + {file = "pyzmq-26.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ea039387c10202ce304af74def5021e9adc6297067f3441d348d2b633e8166a"}, + {file = "pyzmq-26.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a2224fa4a4c2ee872886ed00a571f5e967c85e078e8e8c2530a2fb01b3309b88"}, + {file = "pyzmq-26.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:28ad5233e9c3b52d76196c696e362508959741e1a005fb8fa03b51aea156088f"}, + {file = "pyzmq-26.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:1c17211bc037c7d88e85ed8b7d8f7e52db6dc8eca5590d162717c654550f7282"}, + {file = "pyzmq-26.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b8f86dd868d41bea9a5f873ee13bf5551c94cf6bc51baebc6f85075971fe6eea"}, + {file = "pyzmq-26.2.0-cp310-cp310-win32.whl", hash = "sha256:46a446c212e58456b23af260f3d9fb785054f3e3653dbf7279d8f2b5546b21c2"}, + {file = "pyzmq-26.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:49d34ab71db5a9c292a7644ce74190b1dd5a3475612eefb1f8be1d6961441971"}, + {file = "pyzmq-26.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:bfa832bfa540e5b5c27dcf5de5d82ebc431b82c453a43d141afb1e5d2de025fa"}, + {file = "pyzmq-26.2.0-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:8f7e66c7113c684c2b3f1c83cdd3376103ee0ce4c49ff80a648643e57fb22218"}, + {file = "pyzmq-26.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3a495b30fc91db2db25120df5847d9833af237546fd59170701acd816ccc01c4"}, + {file = "pyzmq-26.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77eb0968da535cba0470a5165468b2cac7772cfb569977cff92e240f57e31bef"}, + {file = "pyzmq-26.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ace4f71f1900a548f48407fc9be59c6ba9d9aaf658c2eea6cf2779e72f9f317"}, + {file = "pyzmq-26.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:92a78853d7280bffb93df0a4a6a2498cba10ee793cc8076ef797ef2f74d107cf"}, + {file = "pyzmq-26.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:689c5d781014956a4a6de61d74ba97b23547e431e9e7d64f27d4922ba96e9d6e"}, + {file = "pyzmq-26.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0aca98bc423eb7d153214b2df397c6421ba6373d3397b26c057af3c904452e37"}, + {file = "pyzmq-26.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:1f3496d76b89d9429a656293744ceca4d2ac2a10ae59b84c1da9b5165f429ad3"}, + {file = "pyzmq-26.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5c2b3bfd4b9689919db068ac6c9911f3fcb231c39f7dd30e3138be94896d18e6"}, + {file = "pyzmq-26.2.0-cp311-cp311-win32.whl", hash = "sha256:eac5174677da084abf378739dbf4ad245661635f1600edd1221f150b165343f4"}, + {file = "pyzmq-26.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:5a509df7d0a83a4b178d0f937ef14286659225ef4e8812e05580776c70e155d5"}, + {file = "pyzmq-26.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:c0e6091b157d48cbe37bd67233318dbb53e1e6327d6fc3bb284afd585d141003"}, + {file = "pyzmq-26.2.0-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:ded0fc7d90fe93ae0b18059930086c51e640cdd3baebdc783a695c77f123dcd9"}, + {file = "pyzmq-26.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:17bf5a931c7f6618023cdacc7081f3f266aecb68ca692adac015c383a134ca52"}, + {file = "pyzmq-26.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55cf66647e49d4621a7e20c8d13511ef1fe1efbbccf670811864452487007e08"}, + {file = "pyzmq-26.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4661c88db4a9e0f958c8abc2b97472e23061f0bc737f6f6179d7a27024e1faa5"}, + {file = "pyzmq-26.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea7f69de383cb47522c9c208aec6dd17697db7875a4674c4af3f8cfdac0bdeae"}, + {file = "pyzmq-26.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:7f98f6dfa8b8ccaf39163ce872bddacca38f6a67289116c8937a02e30bbe9711"}, + {file = "pyzmq-26.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e3e0210287329272539eea617830a6a28161fbbd8a3271bf4150ae3e58c5d0e6"}, + {file = "pyzmq-26.2.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:6b274e0762c33c7471f1a7471d1a2085b1a35eba5cdc48d2ae319f28b6fc4de3"}, + {file = "pyzmq-26.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:29c6a4635eef69d68a00321e12a7d2559fe2dfccfa8efae3ffb8e91cd0b36a8b"}, + {file = "pyzmq-26.2.0-cp312-cp312-win32.whl", hash = "sha256:989d842dc06dc59feea09e58c74ca3e1678c812a4a8a2a419046d711031f69c7"}, + {file = "pyzmq-26.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:2a50625acdc7801bc6f74698c5c583a491c61d73c6b7ea4dee3901bb99adb27a"}, + {file = "pyzmq-26.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:4d29ab8592b6ad12ebbf92ac2ed2bedcfd1cec192d8e559e2e099f648570e19b"}, + {file = "pyzmq-26.2.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:9dd8cd1aeb00775f527ec60022004d030ddc51d783d056e3e23e74e623e33726"}, + {file = "pyzmq-26.2.0-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:28c812d9757fe8acecc910c9ac9dafd2ce968c00f9e619db09e9f8f54c3a68a3"}, + {file = "pyzmq-26.2.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4d80b1dd99c1942f74ed608ddb38b181b87476c6a966a88a950c7dee118fdf50"}, + {file = "pyzmq-26.2.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c997098cc65e3208eca09303630e84d42718620e83b733d0fd69543a9cab9cb"}, + {file = "pyzmq-26.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ad1bc8d1b7a18497dda9600b12dc193c577beb391beae5cd2349184db40f187"}, + {file = "pyzmq-26.2.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:bea2acdd8ea4275e1278350ced63da0b166421928276c7c8e3f9729d7402a57b"}, + {file = "pyzmq-26.2.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:23f4aad749d13698f3f7b64aad34f5fc02d6f20f05999eebc96b89b01262fb18"}, + {file = "pyzmq-26.2.0-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:a4f96f0d88accc3dbe4a9025f785ba830f968e21e3e2c6321ccdfc9aef755115"}, + {file = "pyzmq-26.2.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ced65e5a985398827cc9276b93ef6dfabe0273c23de8c7931339d7e141c2818e"}, + {file = "pyzmq-26.2.0-cp313-cp313-win32.whl", hash = "sha256:31507f7b47cc1ead1f6e86927f8ebb196a0bab043f6345ce070f412a59bf87b5"}, + {file = "pyzmq-26.2.0-cp313-cp313-win_amd64.whl", hash = "sha256:70fc7fcf0410d16ebdda9b26cbd8bf8d803d220a7f3522e060a69a9c87bf7bad"}, + {file = "pyzmq-26.2.0-cp313-cp313-win_arm64.whl", hash = "sha256:c3789bd5768ab5618ebf09cef6ec2b35fed88709b104351748a63045f0ff9797"}, + {file = "pyzmq-26.2.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:034da5fc55d9f8da09015d368f519478a52675e558c989bfcb5cf6d4e16a7d2a"}, + {file = "pyzmq-26.2.0-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:c92d73464b886931308ccc45b2744e5968cbaade0b1d6aeb40d8ab537765f5bc"}, + {file = "pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:794a4562dcb374f7dbbfb3f51d28fb40123b5a2abadee7b4091f93054909add5"}, + {file = "pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aee22939bb6075e7afededabad1a56a905da0b3c4e3e0c45e75810ebe3a52672"}, + {file = "pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ae90ff9dad33a1cfe947d2c40cb9cb5e600d759ac4f0fd22616ce6540f72797"}, + {file = "pyzmq-26.2.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:43a47408ac52647dfabbc66a25b05b6a61700b5165807e3fbd40063fcaf46386"}, + {file = "pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:25bf2374a2a8433633c65ccb9553350d5e17e60c8eb4de4d92cc6bd60f01d306"}, + {file = "pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:007137c9ac9ad5ea21e6ad97d3489af654381324d5d3ba614c323f60dab8fae6"}, + {file = "pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:470d4a4f6d48fb34e92d768b4e8a5cc3780db0d69107abf1cd7ff734b9766eb0"}, + {file = "pyzmq-26.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3b55a4229ce5da9497dd0452b914556ae58e96a4381bb6f59f1305dfd7e53fc8"}, + {file = "pyzmq-26.2.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:9cb3a6460cdea8fe8194a76de8895707e61ded10ad0be97188cc8463ffa7e3a8"}, + {file = "pyzmq-26.2.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8ab5cad923cc95c87bffee098a27856c859bd5d0af31bd346035aa816b081fe1"}, + {file = "pyzmq-26.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9ed69074a610fad1c2fda66180e7b2edd4d31c53f2d1872bc2d1211563904cd9"}, + {file = "pyzmq-26.2.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:cccba051221b916a4f5e538997c45d7d136a5646442b1231b916d0164067ea27"}, + {file = "pyzmq-26.2.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:0eaa83fc4c1e271c24eaf8fb083cbccef8fde77ec8cd45f3c35a9a123e6da097"}, + {file = "pyzmq-26.2.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:9edda2df81daa129b25a39b86cb57dfdfe16f7ec15b42b19bfac503360d27a93"}, + {file = "pyzmq-26.2.0-cp37-cp37m-win32.whl", hash = "sha256:ea0eb6af8a17fa272f7b98d7bebfab7836a0d62738e16ba380f440fceca2d951"}, + {file = "pyzmq-26.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:4ff9dc6bc1664bb9eec25cd17506ef6672d506115095411e237d571e92a58231"}, + {file = "pyzmq-26.2.0-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:2eb7735ee73ca1b0d71e0e67c3739c689067f055c764f73aac4cc8ecf958ee3f"}, + {file = "pyzmq-26.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1a534f43bc738181aa7cbbaf48e3eca62c76453a40a746ab95d4b27b1111a7d2"}, + {file = "pyzmq-26.2.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:aedd5dd8692635813368e558a05266b995d3d020b23e49581ddd5bbe197a8ab6"}, + {file = "pyzmq-26.2.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8be4700cd8bb02cc454f630dcdf7cfa99de96788b80c51b60fe2fe1dac480289"}, + {file = "pyzmq-26.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fcc03fa4997c447dce58264e93b5aa2d57714fbe0f06c07b7785ae131512732"}, + {file = "pyzmq-26.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:402b190912935d3db15b03e8f7485812db350d271b284ded2b80d2e5704be780"}, + {file = "pyzmq-26.2.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:8685fa9c25ff00f550c1fec650430c4b71e4e48e8d852f7ddcf2e48308038640"}, + {file = "pyzmq-26.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:76589c020680778f06b7e0b193f4b6dd66d470234a16e1df90329f5e14a171cd"}, + {file = "pyzmq-26.2.0-cp38-cp38-win32.whl", hash = "sha256:8423c1877d72c041f2c263b1ec6e34360448decfb323fa8b94e85883043ef988"}, + {file = "pyzmq-26.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:76589f2cd6b77b5bdea4fca5992dc1c23389d68b18ccc26a53680ba2dc80ff2f"}, + {file = "pyzmq-26.2.0-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:b1d464cb8d72bfc1a3adc53305a63a8e0cac6bc8c5a07e8ca190ab8d3faa43c2"}, + {file = "pyzmq-26.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4da04c48873a6abdd71811c5e163bd656ee1b957971db7f35140a2d573f6949c"}, + {file = "pyzmq-26.2.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d049df610ac811dcffdc147153b414147428567fbbc8be43bb8885f04db39d98"}, + {file = "pyzmq-26.2.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:05590cdbc6b902101d0e65d6a4780af14dc22914cc6ab995d99b85af45362cc9"}, + {file = "pyzmq-26.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c811cfcd6a9bf680236c40c6f617187515269ab2912f3d7e8c0174898e2519db"}, + {file = "pyzmq-26.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6835dd60355593de10350394242b5757fbbd88b25287314316f266e24c61d073"}, + {file = "pyzmq-26.2.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bc6bee759a6bddea5db78d7dcd609397449cb2d2d6587f48f3ca613b19410cfc"}, + {file = "pyzmq-26.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c530e1eecd036ecc83c3407f77bb86feb79916d4a33d11394b8234f3bd35b940"}, + {file = "pyzmq-26.2.0-cp39-cp39-win32.whl", hash = "sha256:367b4f689786fca726ef7a6c5ba606958b145b9340a5e4808132cc65759abd44"}, + {file = "pyzmq-26.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:e6fa2e3e683f34aea77de8112f6483803c96a44fd726d7358b9888ae5bb394ec"}, + {file = "pyzmq-26.2.0-cp39-cp39-win_arm64.whl", hash = "sha256:7445be39143a8aa4faec43b076e06944b8f9d0701b669df4af200531b21e40bb"}, + {file = "pyzmq-26.2.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:706e794564bec25819d21a41c31d4df2d48e1cc4b061e8d345d7fb4dd3e94072"}, + {file = "pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b435f2753621cd36e7c1762156815e21c985c72b19135dac43a7f4f31d28dd1"}, + {file = "pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:160c7e0a5eb178011e72892f99f918c04a131f36056d10d9c1afb223fc952c2d"}, + {file = "pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c4a71d5d6e7b28a47a394c0471b7e77a0661e2d651e7ae91e0cab0a587859ca"}, + {file = "pyzmq-26.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:90412f2db8c02a3864cbfc67db0e3dcdbda336acf1c469526d3e869394fe001c"}, + {file = "pyzmq-26.2.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2ea4ad4e6a12e454de05f2949d4beddb52460f3de7c8b9d5c46fbb7d7222e02c"}, + {file = "pyzmq-26.2.0-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:fc4f7a173a5609631bb0c42c23d12c49df3966f89f496a51d3eb0ec81f4519d6"}, + {file = "pyzmq-26.2.0-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:878206a45202247781472a2d99df12a176fef806ca175799e1c6ad263510d57c"}, + {file = "pyzmq-26.2.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:17c412bad2eb9468e876f556eb4ee910e62d721d2c7a53c7fa31e643d35352e6"}, + {file = "pyzmq-26.2.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:0d987a3ae5a71c6226b203cfd298720e0086c7fe7c74f35fa8edddfbd6597eed"}, + {file = "pyzmq-26.2.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:39887ac397ff35b7b775db7201095fc6310a35fdbae85bac4523f7eb3b840e20"}, + {file = "pyzmq-26.2.0-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:fdb5b3e311d4d4b0eb8b3e8b4d1b0a512713ad7e6a68791d0923d1aec433d919"}, + {file = "pyzmq-26.2.0-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:226af7dcb51fdb0109f0016449b357e182ea0ceb6b47dfb5999d569e5db161d5"}, + {file = "pyzmq-26.2.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bed0e799e6120b9c32756203fb9dfe8ca2fb8467fed830c34c877e25638c3fc"}, + {file = "pyzmq-26.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:29c7947c594e105cb9e6c466bace8532dc1ca02d498684128b339799f5248277"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:cdeabcff45d1c219636ee2e54d852262e5c2e085d6cb476d938aee8d921356b3"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35cffef589bcdc587d06f9149f8d5e9e8859920a071df5a2671de2213bef592a"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:18c8dc3b7468d8b4bdf60ce9d7141897da103c7a4690157b32b60acb45e333e6"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7133d0a1677aec369d67dd78520d3fa96dd7f3dcec99d66c1762870e5ea1a50a"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6a96179a24b14fa6428cbfc08641c779a53f8fcec43644030328f44034c7f1f4"}, + {file = "pyzmq-26.2.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:4f78c88905461a9203eac9faac157a2a0dbba84a0fd09fd29315db27be40af9f"}, + {file = "pyzmq-26.2.0.tar.gz", hash = "sha256:070672c258581c8e4f640b5159297580a9974b026043bd4ab0470be9ed324f1f"}, ] [package.dependencies] @@ -3681,13 +3750,13 @@ cffi = {version = "*", markers = "implementation_name == \"pypy\""} [[package]] name = "qtconsole" -version = "5.5.2" +version = "5.6.0" description = "Jupyter Qt console" optional = false python-versions = ">=3.8" files = [ - {file = "qtconsole-5.5.2-py3-none-any.whl", hash = "sha256:42d745f3d05d36240244a04e1e1ec2a86d5d9b6edb16dbdef582ccb629e87e0b"}, - {file = "qtconsole-5.5.2.tar.gz", hash = "sha256:6b5fb11274b297463706af84dcbbd5c92273b1f619e6d25d08874b0a88516989"}, + {file = "qtconsole-5.6.0-py3-none-any.whl", hash = "sha256:c36e0d497a473b67898b96dd38666e645e4594019244263da7b409b84fa2ebb5"}, + {file = "qtconsole-5.6.0.tar.gz", hash = "sha256:4c82120a3b53a3d36e3f76e6a1a26ffddf4e1ce2359d56a19889c55e1d73a436"}, ] [package.dependencies] @@ -3696,7 +3765,6 @@ jupyter-client = ">=4.1" jupyter-core = "*" packaging = "*" pygments = "*" -pyzmq = ">=17.1" qtpy = ">=2.4.0" traitlets = "<5.2.1 || >5.2.1,<5.2.2 || >5.2.2" @@ -3872,13 +3940,13 @@ files = [ [[package]] name = "rich" -version = "13.7.1" +version = "13.8.0" description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal" optional = false python-versions = ">=3.7.0" files = [ - {file = "rich-13.7.1-py3-none-any.whl", hash = "sha256:4edbae314f59eb482f54e9e30bf00d33350aaa94f4bfcd4e9e3110e64d0d7222"}, - {file = "rich-13.7.1.tar.gz", hash = "sha256:9be308cb1fe2f1f57d67ce99e95af38a1e2bc71ad9813b0e247cf7ffbcc3a432"}, + {file = "rich-13.8.0-py3-none-any.whl", hash = "sha256:2e85306a063b9492dffc86278197a60cbece75bcb766022f3436f567cae11bdc"}, + {file = "rich-13.8.0.tar.gz", hash = "sha256:a5ac1f1cd448ade0d59cc3356f7db7a7ccda2c8cbae9c7a90c28ff463d3e91f4"}, ] [package.dependencies] @@ -4179,36 +4247,44 @@ tests = ["black (>=24.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.9)", "numpydoc ( [[package]] name = "scipy" -version = "1.14.0" +version = "1.14.1" description = "Fundamental algorithms for scientific computing in Python" optional = false python-versions = ">=3.10" files = [ - {file = "scipy-1.14.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7e911933d54ead4d557c02402710c2396529540b81dd554fc1ba270eb7308484"}, - {file = "scipy-1.14.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:687af0a35462402dd851726295c1a5ae5f987bd6e9026f52e9505994e2f84ef6"}, - {file = "scipy-1.14.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:07e179dc0205a50721022344fb85074f772eadbda1e1b3eecdc483f8033709b7"}, - {file = "scipy-1.14.0-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:6a9c9a9b226d9a21e0a208bdb024c3982932e43811b62d202aaf1bb59af264b1"}, - {file = "scipy-1.14.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:076c27284c768b84a45dcf2e914d4000aac537da74236a0d45d82c6fa4b7b3c0"}, - {file = "scipy-1.14.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42470ea0195336df319741e230626b6225a740fd9dce9642ca13e98f667047c0"}, - {file = "scipy-1.14.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:176c6f0d0470a32f1b2efaf40c3d37a24876cebf447498a4cefb947a79c21e9d"}, - {file = "scipy-1.14.0-cp310-cp310-win_amd64.whl", hash = "sha256:ad36af9626d27a4326c8e884917b7ec321d8a1841cd6dacc67d2a9e90c2f0359"}, - {file = "scipy-1.14.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6d056a8709ccda6cf36cdd2eac597d13bc03dba38360f418560a93050c76a16e"}, - {file = "scipy-1.14.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f0a50da861a7ec4573b7c716b2ebdcdf142b66b756a0d392c236ae568b3a93fb"}, - {file = "scipy-1.14.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:94c164a9e2498e68308e6e148646e486d979f7fcdb8b4cf34b5441894bdb9caf"}, - {file = "scipy-1.14.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:a7d46c3e0aea5c064e734c3eac5cf9eb1f8c4ceee756262f2c7327c4c2691c86"}, - {file = "scipy-1.14.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9eee2989868e274aae26125345584254d97c56194c072ed96cb433f32f692ed8"}, - {file = "scipy-1.14.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e3154691b9f7ed73778d746da2df67a19d046a6c8087c8b385bc4cdb2cfca74"}, - {file = "scipy-1.14.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c40003d880f39c11c1edbae8144e3813904b10514cd3d3d00c277ae996488cdb"}, - {file = "scipy-1.14.0-cp311-cp311-win_amd64.whl", hash = "sha256:5b083c8940028bb7e0b4172acafda6df762da1927b9091f9611b0bcd8676f2bc"}, - {file = "scipy-1.14.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bff2438ea1330e06e53c424893ec0072640dac00f29c6a43a575cbae4c99b2b9"}, - {file = "scipy-1.14.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:bbc0471b5f22c11c389075d091d3885693fd3f5e9a54ce051b46308bc787e5d4"}, - {file = "scipy-1.14.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:64b2ff514a98cf2bb734a9f90d32dc89dc6ad4a4a36a312cd0d6327170339eb0"}, - {file = "scipy-1.14.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:7d3da42fbbbb860211a811782504f38ae7aaec9de8764a9bef6b262de7a2b50f"}, - {file = "scipy-1.14.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d91db2c41dd6c20646af280355d41dfa1ec7eead235642178bd57635a3f82209"}, - {file = "scipy-1.14.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a01cc03bcdc777c9da3cfdcc74b5a75caffb48a6c39c8450a9a05f82c4250a14"}, - {file = "scipy-1.14.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:65df4da3c12a2bb9ad52b86b4dcf46813e869afb006e58be0f516bc370165159"}, - {file = "scipy-1.14.0-cp312-cp312-win_amd64.whl", hash = "sha256:4c4161597c75043f7154238ef419c29a64ac4a7c889d588ea77690ac4d0d9b20"}, - {file = "scipy-1.14.0.tar.gz", hash = "sha256:b5923f48cb840380f9854339176ef21763118a7300a88203ccd0bdd26e58527b"}, + {file = "scipy-1.14.1-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:b28d2ca4add7ac16ae8bb6632a3c86e4b9e4d52d3e34267f6e1b0c1f8d87e389"}, + {file = "scipy-1.14.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d0d2821003174de06b69e58cef2316a6622b60ee613121199cb2852a873f8cf3"}, + {file = "scipy-1.14.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:8bddf15838ba768bb5f5083c1ea012d64c9a444e16192762bd858f1e126196d0"}, + {file = "scipy-1.14.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:97c5dddd5932bd2a1a31c927ba5e1463a53b87ca96b5c9bdf5dfd6096e27efc3"}, + {file = "scipy-1.14.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2ff0a7e01e422c15739ecd64432743cf7aae2b03f3084288f399affcefe5222d"}, + {file = "scipy-1.14.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e32dced201274bf96899e6491d9ba3e9a5f6b336708656466ad0522d8528f69"}, + {file = "scipy-1.14.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8426251ad1e4ad903a4514712d2fa8fdd5382c978010d1c6f5f37ef286a713ad"}, + {file = "scipy-1.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:a49f6ed96f83966f576b33a44257d869756df6cf1ef4934f59dd58b25e0327e5"}, + {file = "scipy-1.14.1-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:2da0469a4ef0ecd3693761acbdc20f2fdeafb69e6819cc081308cc978153c675"}, + {file = "scipy-1.14.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c0ee987efa6737242745f347835da2cc5bb9f1b42996a4d97d5c7ff7928cb6f2"}, + {file = "scipy-1.14.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:3a1b111fac6baec1c1d92f27e76511c9e7218f1695d61b59e05e0fe04dc59617"}, + {file = "scipy-1.14.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:8475230e55549ab3f207bff11ebfc91c805dc3463ef62eda3ccf593254524ce8"}, + {file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:278266012eb69f4a720827bdd2dc54b2271c97d84255b2faaa8f161a158c3b37"}, + {file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fef8c87f8abfb884dac04e97824b61299880c43f4ce675dd2cbeadd3c9b466d2"}, + {file = "scipy-1.14.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b05d43735bb2f07d689f56f7b474788a13ed8adc484a85aa65c0fd931cf9ccd2"}, + {file = "scipy-1.14.1-cp311-cp311-win_amd64.whl", hash = "sha256:716e389b694c4bb564b4fc0c51bc84d381735e0d39d3f26ec1af2556ec6aad94"}, + {file = "scipy-1.14.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:631f07b3734d34aced009aaf6fedfd0eb3498a97e581c3b1e5f14a04164a456d"}, + {file = "scipy-1.14.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:af29a935803cc707ab2ed7791c44288a682f9c8107bc00f0eccc4f92c08d6e07"}, + {file = "scipy-1.14.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:2843f2d527d9eebec9a43e6b406fb7266f3af25a751aa91d62ff416f54170bc5"}, + {file = "scipy-1.14.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:eb58ca0abd96911932f688528977858681a59d61a7ce908ffd355957f7025cfc"}, + {file = "scipy-1.14.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:30ac8812c1d2aab7131a79ba62933a2a76f582d5dbbc695192453dae67ad6310"}, + {file = "scipy-1.14.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f9ea80f2e65bdaa0b7627fb00cbeb2daf163caa015e59b7516395fe3bd1e066"}, + {file = "scipy-1.14.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:edaf02b82cd7639db00dbff629995ef185c8df4c3ffa71a5562a595765a06ce1"}, + {file = "scipy-1.14.1-cp312-cp312-win_amd64.whl", hash = "sha256:2ff38e22128e6c03ff73b6bb0f85f897d2362f8c052e3b8ad00532198fbdae3f"}, + {file = "scipy-1.14.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:1729560c906963fc8389f6aac023739ff3983e727b1a4d87696b7bf108316a79"}, + {file = "scipy-1.14.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:4079b90df244709e675cdc8b93bfd8a395d59af40b72e339c2287c91860deb8e"}, + {file = "scipy-1.14.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:e0cf28db0f24a38b2a0ca33a85a54852586e43cf6fd876365c86e0657cfe7d73"}, + {file = "scipy-1.14.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:0c2f95de3b04e26f5f3ad5bb05e74ba7f68b837133a4492414b3afd79dfe540e"}, + {file = "scipy-1.14.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b99722ea48b7ea25e8e015e8341ae74624f72e5f21fc2abd45f3a93266de4c5d"}, + {file = "scipy-1.14.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5149e3fd2d686e42144a093b206aef01932a0059c2a33ddfa67f5f035bdfe13e"}, + {file = "scipy-1.14.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e4f5a7c49323533f9103d4dacf4e4f07078f360743dec7f7596949149efeec06"}, + {file = "scipy-1.14.1-cp313-cp313-win_amd64.whl", hash = "sha256:baff393942b550823bfce952bb62270ee17504d02a1801d7fd0719534dfb9c84"}, + {file = "scipy-1.14.1.tar.gz", hash = "sha256:5a275584e726026a5699459aa72f828a610821006228e841b94275c4a7c08417"}, ] [package.dependencies] @@ -4216,8 +4292,8 @@ numpy = ">=1.23.5,<2.3" [package.extras] dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy (==1.10.0)", "pycodestyle", "pydevtool", "rich-click", "ruff (>=0.0.292)", "types-psutil", "typing_extensions"] -doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.13.1)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0)", "sphinx-design (>=0.4.0)"] -test = ["Cython", "array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] +doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.13.1)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0,<=7.3.7)", "sphinx-design (>=0.4.0)"] +test = ["Cython", "array-api-strict (>=2.0)", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"] [[package]] name = "seaborn" @@ -4471,19 +4547,23 @@ test = ["pytest"] [[package]] name = "setuptools" -version = "73.0.1" +version = "74.0.0" description = "Easily download, build, install, upgrade, and uninstall Python packages" optional = false python-versions = ">=3.8" files = [ - {file = "setuptools-73.0.1-py3-none-any.whl", hash = "sha256:b208925fcb9f7af924ed2dc04708ea89791e24bde0d3020b27df0e116088b34e"}, - {file = "setuptools-73.0.1.tar.gz", hash = "sha256:d59a3e788ab7e012ab2c4baed1b376da6366883ee20d7a5fc426816e3d7b1193"}, + {file = "setuptools-74.0.0-py3-none-any.whl", hash = "sha256:0274581a0037b638b9fc1c6883cc71c0210865aaa76073f7882376b641b84e8f"}, + {file = "setuptools-74.0.0.tar.gz", hash = "sha256:a85e96b8be2b906f3e3e789adec6a9323abf79758ecfa3065bd740d81158b11e"}, ] [package.extras] +check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)", "ruff (>=0.5.2)"] core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"] +cover = ["pytest-cov"] doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"] -test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"] +enabler = ["pytest-enabler (>=2.2)"] +test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"] +type = ["importlib-metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (==1.11.*)", "pytest-mypy"] [[package]] name = "shellingham" @@ -4939,13 +5019,13 @@ wandb = ">=0.13.5" [[package]] name = "transformers" -version = "4.44.1" +version = "4.44.2" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = false python-versions = ">=3.8.0" files = [ - {file = "transformers-4.44.1-py3-none-any.whl", hash = "sha256:bd2642da18b4e6d29b135c17650cd7ca8e874f2d092d2eddd3ed6b71a93a155c"}, - {file = "transformers-4.44.1.tar.gz", hash = "sha256:3b9a1a07ca65c665c7bf6109b7da76182184d10bb58d9ab14e6892e7b9e073a2"}, + {file = "transformers-4.44.2-py3-none-any.whl", hash = "sha256:1c02c65e7bfa5e52a634aff3da52138b583fc6f263c1f28d547dc144ba3d412d"}, + {file = "transformers-4.44.2.tar.gz", hash = "sha256:36aa17cc92ee154058e426d951684a2dab48751b35b49437896f898931270826"}, ] [package.dependencies] @@ -5049,13 +5129,13 @@ test = ["mypy", "pytest", "typing-extensions"] [[package]] name = "typer" -version = "0.12.4" +version = "0.12.5" description = "Typer, build great CLIs. Easy to code. Based on Python type hints." optional = false python-versions = ">=3.7" files = [ - {file = "typer-0.12.4-py3-none-any.whl", hash = "sha256:819aa03699f438397e876aa12b0d63766864ecba1b579092cc9fe35d886e34b6"}, - {file = "typer-0.12.4.tar.gz", hash = "sha256:c9c1613ed6a166162705b3347b8d10b661ccc5d95692654d0fb628118f2c34e6"}, + {file = "typer-0.12.5-py3-none-any.whl", hash = "sha256:62fe4e471711b147e3365034133904df3e235698399bc4de2b36c8579298d52b"}, + {file = "typer-0.12.5.tar.gz", hash = "sha256:f592f089bedcc8ec1b974125d64851029c3b1af145f04aca64d69410f0c9b722"}, ] [package.dependencies] @@ -5066,13 +5146,13 @@ typing-extensions = ">=3.7.4.3" [[package]] name = "types-python-dateutil" -version = "2.9.0.20240316" +version = "2.9.0.20240821" description = "Typing stubs for python-dateutil" optional = false python-versions = ">=3.8" files = [ - {file = "types-python-dateutil-2.9.0.20240316.tar.gz", hash = "sha256:5d2f2e240b86905e40944dd787db6da9263f0deabef1076ddaed797351ec0202"}, - {file = "types_python_dateutil-2.9.0.20240316-py3-none-any.whl", hash = "sha256:6b8cb66d960771ce5ff974e9dd45e38facb81718cc1e208b10b1baccbfdbee3b"}, + {file = "types-python-dateutil-2.9.0.20240821.tar.gz", hash = "sha256:9649d1dcb6fef1046fb18bebe9ea2aa0028b160918518c34589a46045f6ebd98"}, + {file = "types_python_dateutil-2.9.0.20240821-py3-none-any.whl", hash = "sha256:f5889fcb4e63ed4aaa379b44f93c32593d50b9a94c9a60a0c854d8cc3511cd57"}, ] [[package]] @@ -5226,13 +5306,13 @@ test = ["websockets"] [[package]] name = "widgetsnbextension" -version = "4.0.11" +version = "4.0.13" description = "Jupyter interactive widgets for Jupyter Notebook" optional = false python-versions = ">=3.7" files = [ - {file = "widgetsnbextension-4.0.11-py3-none-any.whl", hash = "sha256:55d4d6949d100e0d08b94948a42efc3ed6dfdc0e9468b2c4b128c9a2ce3a7a36"}, - {file = "widgetsnbextension-4.0.11.tar.gz", hash = "sha256:8b22a8f1910bfd188e596fe7fc05dcbd87e810c8a4ba010bdb3da86637398474"}, + {file = "widgetsnbextension-4.0.13-py3-none-any.whl", hash = "sha256:74b2692e8500525cc38c2b877236ba51d34541e6385eeed5aec15a70f88a6c71"}, + {file = "widgetsnbextension-4.0.13.tar.gz", hash = "sha256:ffcb67bc9febd10234a362795f643927f4e0c05d9342c727b65d2384f8feacb6"}, ] [[package]] @@ -5490,20 +5570,24 @@ pandas = ["pandas (>=1.5.3)"] [[package]] name = "zipp" -version = "3.20.0" +version = "3.20.1" description = "Backport of pathlib-compatible object wrapper for zip files" optional = false python-versions = ">=3.8" files = [ - {file = "zipp-3.20.0-py3-none-any.whl", hash = "sha256:58da6168be89f0be59beb194da1250516fdaa062ccebd30127ac65d30045e10d"}, - {file = "zipp-3.20.0.tar.gz", hash = "sha256:0145e43d89664cfe1a2e533adc75adafed82fe2da404b4bbb6b026c0157bdb31"}, + {file = "zipp-3.20.1-py3-none-any.whl", hash = "sha256:9960cd8967c8f85a56f920d5d507274e74f9ff813a0ab8889a5b5be2daf44064"}, + {file = "zipp-3.20.1.tar.gz", hash = "sha256:c22b14cc4763c5a5b04134207736c107db42e9d3ef2d9779d465f5f1bcba572b"}, ] [package.extras] +check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"] +cover = ["pytest-cov"] doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"] -test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy", "pytest-ruff (>=0.2.1)"] +enabler = ["pytest-enabler (>=2.2)"] +test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"] +type = ["pytest-mypy"] [metadata] lock-version = "2.0" -python-versions = ">=3.10,<3.13" -content-hash = "adb68dc5faad8c231fb4dcc8b1e628479cd9dd34b0217b89c7a5d1d7857fc4cf" +python-versions = ">=3.10.6,<3.13" +content-hash = "3496fbc599e285bdfba9de382242c28dd56bc6446a2ba47459c81b986d6ab5cb" diff --git a/pyproject.toml b/pyproject.toml index 5c793c1d..3f7e535e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -8,9 +8,10 @@ packages = [{include = "maze_transformer"}] repository = "https://github.com/understanding-search/maze-transformer" [tool.poetry.dependencies] -python = ">=3.10,<3.13" +python = ">=3.10.6,<3.13" # dataset -maze-dataset = "^0.5.6" +# maze-dataset = "^0.5.6" +maze-dataset = {git = "https://github.com/understanding-search/maze-dataset.git"} # transformers torch = "^2.4.0" transformer-lens = "^2.4.0" @@ -21,7 +22,7 @@ zanj = "^0.3.1" # wandb = "^0.13.5" # note: TransformerLens forces us to use 0.13.5 wandb = "^0.17.5" fire = "^0.6.0" -typing-extensions = "^4.12.2" +# typing-extensions = "^4.12.2" # plotting matplotlib = "^3.7.0" plotly = "^5.13.1" diff --git a/tests/integration/test_eval_model.py b/tests/integration/test_eval_model.py index 474faac3..c42faa90 100644 --- a/tests/integration/test_eval_model.py +++ b/tests/integration/test_eval_model.py @@ -12,55 +12,17 @@ import numpy as np import pytest from maze_dataset import CoordTup, MazeDataset -from zanj import ZANJ -from zanj.torchutil import assert_model_cfg_equality from maze_transformer.evaluation.eval_model import evaluate_model, predict_maze_paths from maze_transformer.evaluation.path_evals import PathEvals -from maze_transformer.test_helpers.assertions import assert_model_output_equality from maze_transformer.training.config import ConfigHolder, ZanjHookedTransformer -from maze_transformer.training.train_model import TrainingResult, train_model -from maze_transformer.training.train_save_files import TRAIN_SAVE_FILES -from maze_transformer.training.wandb_logger import WandbProject temp_dir: Path = Path("tests/_temp/test_eval_model") -def test_model_loading(): - zanj: ZANJ = ZANJ( - custom_settings={ - "_load_state_dict_wrapper": {"recover_exact": True, "fold_ln": False} - } - ) - # get config - cfg: ConfigHolder = ConfigHolder.get_config_multisource( - cfg_names=("test-g3-n5-a_dfs-h73257", "nano-v1", "test-v1"), - ) - # train model - result: TrainingResult = train_model( - base_path=temp_dir, - wandb_project=WandbProject.INTEGRATION_TESTS, - cfg=cfg, - do_generate_dataset=True, - ) - model_ret: ZanjHookedTransformer = result.model - - # load model - model_load_auto: ZanjHookedTransformer = zanj.read( - result.output_path / TRAIN_SAVE_FILES.model_final_zanj - ) - - # Load model manually without folding - assert cfg == model_ret.zanj_model_config - assert_model_cfg_equality(model_ret, model_load_auto) - - assert_model_output_equality(model_ret, model_load_auto) - # assert_model_exact_equality(model_ret, model_load_auto) - - def test_predict_maze_paths(): model: ZanjHookedTransformer = ZanjHookedTransformer.read( - "examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj" + "examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj" ) cfg: ConfigHolder = model.zanj_model_config cfg.dataset_cfg.n_mazes = 10 @@ -101,7 +63,7 @@ def test_predict_maze_paths(): @pytest.mark.usefixtures("temp_dir") def test_evaluate_model(temp_dir): model: ZanjHookedTransformer = ZanjHookedTransformer.read( - "examples/multsrc_demo-g6-n10K-a_dfs-h92077_tiny-v1_sweep-v1_2023-05-20-21-30-02/model.final.zanj" + "examples/multsrc_demo-g6-n10K-a_dfs-h50618_tiny-v1_sweep-v1_2024-08-21-12-21-39/model.final.zanj" ) cfg: ConfigHolder = model.zanj_model_config cfg.dataset_cfg.n_mazes = 10 diff --git a/tests/integration/test_train_model.py b/tests/integration/test_train_model.py index 2652ee08..e1398ec8 100644 --- a/tests/integration/test_train_model.py +++ b/tests/integration/test_train_model.py @@ -1,15 +1,30 @@ +from pathlib import Path + +from maze_dataset.dataset.configs import MAZE_DATASET_CONFIGS + from maze_transformer.training.config import ConfigHolder, ZanjHookedTransformer from maze_transformer.training.train_model import TrainingResult, train_model from maze_transformer.training.wandb_logger import WandbProject +temp_dir: Path = Path("tests/_temp/test_train_model") + + +def test_configs(): + for k, v in MAZE_DATASET_CONFIGS.items(): + assert k == v.to_fname() + v_summary = v.summary() + print(f"{k}: {v_summary}") + assert k == v_summary["fname"] + def test_train_model(): cfg: ConfigHolder = ConfigHolder.get_config_multisource( - cfg_names=("test-g3-n5-a_dfs-h73257", "nano-v1", "test-v1"), + cfg_names=("demo_small-g3-n100-a_dfs-h44636", "nano-v1", "test-v1"), ) - cfg.dataset_cfg.n_mazes = 10 + print(cfg.dataset_cfg.summary()) + assert cfg.dataset_cfg.n_mazes == 100 result: TrainingResult = train_model( - base_path="tests/_temp/test_train_model", + base_path=temp_dir, wandb_project=WandbProject.INTEGRATION_TESTS, cfg=cfg, do_generate_dataset=True, @@ -17,3 +32,43 @@ def test_train_model(): assert isinstance(result.model, ZanjHookedTransformer) assert result.model.zanj_model_config == cfg + + print(cfg.dataset_cfg.summary()) + + +def test_model_loading(): + # get config + cfg: ConfigHolder = ConfigHolder.get_config_multisource( + cfg_names=("demo_small-g3-n100-a_dfs-h44636", "nano-v1", "test-v1"), + ) + print(cfg.dataset_cfg.summary()) + # train model + result: TrainingResult = train_model( + base_path=temp_dir, + wandb_project=WandbProject.INTEGRATION_TESTS, + cfg=cfg, + do_generate_dataset=True, + ) + # model_ret: ZanjHookedTransformer = result.model + + # # load model + # zanj: ZANJ = ZANJ( + # custom_settings={ + # "_load_state_dict_wrapper": {"recover_exact": True, "fold_ln": False} + # } + # ) + # model_load_auto: ZanjHookedTransformer = zanj.read( + # result.output_path / TRAIN_SAVE_FILES.model_final_zanj + # ) + + # # Load model manually without folding + # assert cfg == model_ret.zanj_model_config + # assert_model_cfg_equality(model_ret, model_load_auto) + + # vocab_size: int = len(model_ret.zanj_model_config.tokenizer) + # assert_model_output_equality( + # model_ret, + # model_load_auto, + # check_argsort_equality=(vocab_size > 2048), + # ) + # # assert_model_exact_equality(model_ret, model_load_auto) diff --git a/tests/unit/maze_transformer/evaluation/test_baseline_models.py b/tests/unit/maze_transformer/evaluation/test_baseline_models.py index 7ebc285e..545aeb24 100644 --- a/tests/unit/maze_transformer/evaluation/test_baseline_models.py +++ b/tests/unit/maze_transformer/evaluation/test_baseline_models.py @@ -1,7 +1,11 @@ import numpy as np import pytest from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) from maze_transformer.evaluation.baseline_models import RandomBaseline from maze_transformer.evaluation.eval_model import predict_maze_paths @@ -9,13 +13,18 @@ @pytest.mark.parametrize( - "tok_mode", + "tokenizer", [ - pytest.param(TokenizationMode.AOTP_UT_rasterized, id="rasterized"), - pytest.param(TokenizationMode.AOTP_UT_uniform, id="uniform"), + pytest.param( + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), id="rasterized" + ), + pytest.param( + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="uniform" + ), + pytest.param(MazeTokenizerModular(), id="MazeTokenizerModular"), ], ) -def test_random_baseline(tok_mode): +def test_random_baseline(tokenizer: MazeTokenizer | MazeTokenizerModular): # Setup will be refactored in https://github.com/orgs/understanding-search/projects/1?pane=issue&itemId=22504590 # Disk interactions can be removed after https://github.com/understanding-search/maze-transformer/issues/113 # First create a dataset and train a model @@ -23,7 +32,7 @@ def test_random_baseline(tok_mode): train_cfg=TRAINING_CONFIGS["test-v1"], model_cfg=GPT_CONFIGS["tiny-v1"], dataset_cfg=MazeDatasetConfig(name="test", grid_n=3, n_mazes=5), - maze_tokenizer=MazeTokenizer(tokenization_mode=tok_mode), + maze_tokenizer=tokenizer, ) dataset: MazeDataset = MazeDataset.from_config(cfg.dataset_cfg, save_local=False) diff --git a/tests/unit/maze_transformer/test_tokenizers.py b/tests/unit/maze_transformer/test_tokenizers.py index 584039d5..ecee92aa 100644 --- a/tests/unit/maze_transformer/test_tokenizers.py +++ b/tests/unit/maze_transformer/test_tokenizers.py @@ -10,7 +10,12 @@ import torch from maze_dataset import MazeDatasetConfig, SolvedMaze from maze_dataset.generation import get_maze_with_solution -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.testing_utils import LEGACY_AND_EQUIVALENT_TOKENIZERS +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) from pytest import mark, param from transformer_lens import HookedTransformer @@ -18,50 +23,56 @@ @mark.parametrize( - "tok_mode,grid_size,grid_size_max", + "tokenizer,grid_size,grid_size_max", [ param( - tok_mode, + tokenizer, grid_size, grid_size_max, - id=f"{tok_mode.name.split('_')[-1]},g{grid_size},m{grid_size_max}", + id=f"{tokenizer.name}-g{grid_size}-m{grid_size_max}", ) - for tok_mode, grid_size, grid_size_max in product( - TokenizationMode, [3, 4], [3, 4, 5, 6, 10, 50] + for tokenizer, grid_size, grid_size_max in product( + LEGACY_AND_EQUIVALENT_TOKENIZERS, + [3, 4], + [3, 4, 5, 6, 10, 50], ) ], ) def test_tokenization_encoding( - tok_mode: TokenizationMode, grid_size: int, grid_size_max: int + tokenizer: MazeTokenizer | MazeTokenizerModular, grid_size: int, grid_size_max: int ): # create maze and tokenizer solved_maze: SolvedMaze = get_maze_with_solution("gen_dfs", (3, 3)) - tok: MazeTokenizer = MazeTokenizer( - tokenization_mode=tok_mode, max_grid_size=grid_size - ) + if isinstance(tokenizer, MazeTokenizer): + print(f"{tokenizer.tokenization_mode = }, {grid_size_max = }") + tokenizer = MazeTokenizer( + tokenization_mode=tokenizer.tokenization_mode, max_grid_size=grid_size_max + ) # convert to strings - maze_str_tokens: list[str] = solved_maze.as_tokens(tok) + maze_str_tokens: list[str] = solved_maze.as_tokens(tokenizer) # cant tokenize if grid size is too big - if grid_size > grid_size_max: - tok.encode(maze_str_tokens) + if grid_size > grid_size_max and isinstance(tokenizer, MazeTokenizer): + tokenizer.encode(maze_str_tokens) return # check that tokenizer map is as expected - token_to_index: dict[str, int] = {token: i for i, token in enumerate(tok.token_arr)} - assert token_to_index == tok.tokenizer_map, "Tokenization mismatch" + token_to_index: dict[str, int] = { + token: i for i, token in enumerate(tokenizer.token_arr) + } + assert token_to_index == tokenizer.tokenizer_map, "Tokenization mismatch" # round trip tokenize - maze_tokens: list[int] = tok.encode(maze_str_tokens) - assert maze_str_tokens == tok.decode(maze_tokens), "Tokenization mismatch" + maze_tokens: list[int] = tokenizer.encode(maze_str_tokens) + assert maze_str_tokens == tokenizer.decode(maze_tokens), "Tokenization mismatch" # create and test actual HuggingMazeTokenizer cfg_holder: ConfigHolder = ConfigHolder( train_cfg=None, model_cfg=None, dataset_cfg=MazeDatasetConfig(name="testing_maze", grid_n=3, n_mazes=1), - maze_tokenizer=tok, + maze_tokenizer=tokenizer, ) tokenizer_out = cfg_holder.tokenizer(maze_str_tokens)["input_ids"] @@ -71,16 +82,17 @@ def test_tokenization_encoding( @mark.parametrize( - "tok_mode", + "tokenizer", [ - param(tok_mode, id=tok_mode.name) - for tok_mode in [ - TokenizationMode.AOTP_UT_uniform, - TokenizationMode.AOTP_UT_rasterized, + param(tokenizer, id=tokenizer.name) + for tokenizer in [ + MazeTokenizer(tokenization_mode=TokenizationMode.AOTP_UT_uniform), + MazeTokenizer(tokenization_mode=TokenizationMode.AOTP_UT_rasterized), + MazeTokenizerModular(), ] ], ) -def test_to_ascii(tok_mode): +def test_to_ascii(tokenizer: MazeTokenizer | MazeTokenizerModular): # Check that the ascii encoding works for multiple different inputs maze_str_tokens: list[str] = ( """ (1,1) <--> (2,1) ; (2,0) <--> (1,0) ; (0,1) <--> (0,0) ; @@ -99,12 +111,11 @@ def test_to_ascii(tok_mode): ] # Need to generate a config to extract the token map >.< - maze_tok_cfg = MazeTokenizer(tokenization_mode=tok_mode) cfg_holder = ConfigHolder( train_cfg=None, dataset_cfg=MazeDatasetConfig(name="testing_maze", grid_n=5, n_mazes=1), model_cfg=None, - maze_tokenizer=maze_tok_cfg, + maze_tokenizer=tokenizer, ) # Try with string tokens @@ -119,14 +130,19 @@ def test_to_ascii(tok_mode): @mark.parametrize( - "tok_mode", + "tokenizer", [ - param(TokenizationMode.AOTP_UT_uniform, id="AOTP_UT_uniform"), - param(TokenizationMode.AOTP_UT_rasterized, id="AOTP_UT_rasterized"), + param(tokenizer, id=tokenizer.name) + for tokenizer in [ + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), + MazeTokenizerModular(), + ] ], ) -def test_tokenizer_inside_hooked_transformer(tok_mode): - maze_tok_cfg = MazeTokenizer(tokenization_mode=tok_mode) +def test_tokenizer_inside_hooked_transformer( + tokenizer: MazeTokenizer | MazeTokenizerModular, +): cfg_holder = ConfigHolder( train_cfg=None, dataset_cfg=MazeDatasetConfig(name="testing_maze", grid_n=3, n_mazes=1), @@ -137,7 +153,7 @@ def test_tokenizer_inside_hooked_transformer(tok_mode): d_head=1, n_layers=1, ), - maze_tokenizer=maze_tok_cfg, + maze_tokenizer=tokenizer, ) # Adjacency List Tokenization @@ -155,9 +171,9 @@ def test_tokenizer_inside_hooked_transformer(tok_mode): # -- Test Simple Tokenization -- # Manual Tokenization - vocab_map = {k: v for v, k in enumerate(maze_tok_cfg.token_arr)} + vocab_map = {k: v for v, k in enumerate(tokenizer.token_arr)} maze_tokens_manual = [vocab_map[token] for token in maze_str_tokens] - maze_tokens = maze_tok_cfg.encode(maze_str_tokens) + maze_tokens = tokenizer.encode(maze_str_tokens) assert maze_tokens == maze_tokens_manual, "Manual tokenization failed" assert torch.all( @@ -209,53 +225,72 @@ def test_tokenizer_inside_hooked_transformer(tok_mode): @mark.parametrize( - "inp,expected,tok_mode", + "inp,expected,tokenizer", [ param( [1, 2, 3], [PAD_PLACEHOLDER, PAD_PLACEHOLDER, 1, 2, 3], - TokenizationMode.AOTP_UT_uniform, + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="short+uniform", ), param( [1, 2, 3, 4, 5], [1, 2, 3, 4, 5], - TokenizationMode.AOTP_UT_uniform, + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="max_length+uniform", ), param( [1, 2, 3, 4, 5, 6], [2, 3, 4, 5, 6], - TokenizationMode.AOTP_UT_uniform, + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="too_long+uniform", ), param( [1, 2, 3], [PAD_PLACEHOLDER, PAD_PLACEHOLDER, 1, 2, 3], - TokenizationMode.AOTP_UT_rasterized, + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), id="short+rasterized", ), param( [1, 2, 3, 4, 5], [1, 2, 3, 4, 5], - TokenizationMode.AOTP_UT_rasterized, + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), id="max_length+rasterized", ), param( [1, 2, 3, 4, 5, 6], [2, 3, 4, 5, 6], - TokenizationMode.AOTP_UT_rasterized, + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), + id="too_long+rasterized", + ), + param( + [1, 2, 3], + [PAD_PLACEHOLDER, PAD_PLACEHOLDER, 1, 2, 3], + MazeTokenizerModular(), + id="short+rasterized", + ), + param( + [1, 2, 3, 4, 5], + [1, 2, 3, 4, 5], + MazeTokenizerModular(), + id="max_length+rasterized", + ), + param( + [1, 2, 3, 4, 5, 6], + [2, 3, 4, 5, 6], + MazeTokenizerModular(), id="too_long+rasterized", ), ], ) -def test_pad_sequence_param(inp, expected, tok_mode): - maze_tok_cfg: MazeTokenizer = MazeTokenizer(tokenization_mode=tok_mode) +def test_pad_sequence_param( + inp, expected, tokenizer: MazeTokenizer | MazeTokenizerModular +): cfg_holder: ConfigHolder = ConfigHolder( train_cfg=None, dataset_cfg=MazeDatasetConfig(name="testing_maze", grid_n=3, n_mazes=1), model_cfg=None, - maze_tokenizer=maze_tok_cfg, + maze_tokenizer=tokenizer, ) # Pad token id is chosen when the tokenizer is initialized diff --git a/tests/unit/maze_transformer/training/config/test_cfg_post_init.py b/tests/unit/maze_transformer/training/config/test_cfg_post_init.py index 1c245a3e..43a70afa 100644 --- a/tests/unit/maze_transformer/training/config/test_cfg_post_init.py +++ b/tests/unit/maze_transformer/training/config/test_cfg_post_init.py @@ -1,5 +1,5 @@ from maze_dataset import MazeDatasetConfig -from maze_dataset.tokenization import MazeTokenizer +from maze_dataset.tokenization import MazeTokenizerModular from maze_transformer.training.config import BaseGPTConfig, ConfigHolder, TrainConfig @@ -17,7 +17,6 @@ def test_cfg_post_init(): ), ) - assert isinstance(cfg.maze_tokenizer, MazeTokenizer) - assert isinstance(cfg.maze_tokenizer.max_grid_size, int) - assert cfg.maze_tokenizer.max_grid_size == 5 + assert isinstance(cfg.maze_tokenizer, MazeTokenizerModular) assert isinstance(cfg.maze_tokenizer.vocab_size, int) + assert cfg.maze_tokenizer.vocab_size == 4096 diff --git a/tests/unit/maze_transformer/training/config/test_config_holder.py b/tests/unit/maze_transformer/training/config/test_config_holder.py index 46078e57..c7dcf136 100644 --- a/tests/unit/maze_transformer/training/config/test_config_holder.py +++ b/tests/unit/maze_transformer/training/config/test_config_holder.py @@ -27,7 +27,7 @@ def test_model_config_has_correct_values(): assert model.cfg.d_head == 16 assert model.cfg.n_layers == 4 assert model.cfg.n_ctx == 512 - assert model.cfg.d_vocab == 27 + assert model.cfg.d_vocab == 4096 def test_serialize_and_load(): diff --git a/tests/unit/maze_transformer/training/test_get_dataloader.py b/tests/unit/maze_transformer/training/test_get_dataloader.py index d41994e1..696a62ea 100644 --- a/tests/unit/maze_transformer/training/test_get_dataloader.py +++ b/tests/unit/maze_transformer/training/test_get_dataloader.py @@ -1,6 +1,10 @@ import pytest from maze_dataset import MazeDataset, MazeDatasetConfig, SolvedMaze -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) from maze_transformer.test_helpers.stub_logger import StubLogger from maze_transformer.training.config import GPT_CONFIGS, TRAINING_CONFIGS, ConfigHolder @@ -8,20 +12,25 @@ @pytest.mark.parametrize( - "tok_mode", + "tokenizer", [ - pytest.param(TokenizationMode.AOTP_UT_rasterized, id="rasterized"), - pytest.param(TokenizationMode.AOTP_UT_uniform, id="uniform"), + pytest.param( + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), id="rasterized" + ), + pytest.param( + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="uniform" + ), + pytest.param(MazeTokenizerModular(), id="MazeTokenizerModular"), ], ) -def test_get_dataloader(tok_mode: TokenizationMode): +def test_get_dataloader(tokenizer: MazeTokenizer | MazeTokenizerModular): dataset_config = MazeDatasetConfig(name="test", grid_n=3, n_mazes=5) dataset = MazeDataset.generate(dataset_config) config_holder: ConfigHolder = ConfigHolder( dataset_cfg=dataset_config, model_cfg=GPT_CONFIGS["tiny-v1"], train_cfg=TRAINING_CONFIGS["test-v1"], - maze_tokenizer=MazeTokenizer(tokenization_mode=tok_mode), + maze_tokenizer=tokenizer, ) config_holder.train_cfg.batch_size = 5 logger = StubLogger() diff --git a/tests/unit/maze_transformer/training/test_maze_dataset_construction.py b/tests/unit/maze_transformer/training/test_maze_dataset_construction.py index 3e8985ac..5fb73516 100644 --- a/tests/unit/maze_transformer/training/test_maze_dataset_construction.py +++ b/tests/unit/maze_transformer/training/test_maze_dataset_construction.py @@ -1,26 +1,34 @@ import pytest from maze_dataset import SPECIAL_TOKENS, MazeDataset, MazeDatasetConfig -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) @pytest.mark.parametrize( - "tok_mode", + "tokenizer", [ - pytest.param(TokenizationMode.AOTP_UT_rasterized, id="rasterized"), - pytest.param(TokenizationMode.AOTP_UT_uniform, id="uniform"), + pytest.param( + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), id="rasterized" + ), + pytest.param( + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), id="uniform" + ), + pytest.param(MazeTokenizerModular(), id="MazeTokenizerModular"), ], ) -def test_dataset_construction(tok_mode: TokenizationMode): +def test_dataset_construction(tokenizer: MazeTokenizer | MazeTokenizerModular): config: MazeDatasetConfig = MazeDatasetConfig( name="test", grid_n=2, n_mazes=3, ) dataset: MazeDataset = MazeDataset.from_config(cfg=config) - tok: MazeTokenizer = MazeTokenizer(tokenization_mode=tok_mode, max_grid_size=None) # check the tokenization - test_tokenizations: list[list[str]] = dataset.as_tokens(tok) + test_tokenizations: list[list[str]] = dataset.as_tokens(tokenizer) # the adj_list always gets shuffled, so easier to check the paths # this will be much simpler once token utils are merged @@ -31,7 +39,7 @@ def test_dataset_construction(tok_mode: TokenizationMode): dataset_tokenization_paths = [ tokens[tokens.index(SPECIAL_TOKENS.PATH_START) :] - for tokens in dataset.as_tokens(tok) + for tokens in dataset.as_tokens(tokenizer) ] assert sorted(test_tokenization_paths) == sorted(dataset_tokenization_paths) diff --git a/tests/unit/maze_transformer/training/test_tokenizer.py b/tests/unit/maze_transformer/training/test_tokenizer.py index 189eb4cd..2994b0f0 100644 --- a/tests/unit/maze_transformer/training/test_tokenizer.py +++ b/tests/unit/maze_transformer/training/test_tokenizer.py @@ -2,20 +2,25 @@ import pytest from maze_dataset import SPECIAL_TOKENS, SolvedMaze, utils from maze_dataset.generation import get_maze_with_solution -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) @pytest.mark.parametrize( - "tok_mode", + "tokenizer", [ - pytest.param(tok_mode, id=tok_mode.name) - for tok_mode in ( - TokenizationMode.AOTP_UT_rasterized, - TokenizationMode.AOTP_UT_uniform, + pytest.param(tokenizer, id=tokenizer.name) + for tokenizer in ( + TokenizationMode.AOTP_UT_rasterized.to_legacy_tokenizer(), + TokenizationMode.AOTP_UT_uniform.to_legacy_tokenizer(), + MazeTokenizerModular(), ) ], ) -def test_coordinate_system(tok_mode: TokenizationMode): +def test_coordinate_system(tokenizer: MazeTokenizer | MazeTokenizerModular): """ Check that the adj_list created by as_tokens() uses the same coordinate system as the LatticeMaze adj_list. @@ -30,10 +35,7 @@ def test_coordinate_system(tok_mode: TokenizationMode): [f"({c[0]},{c[1]})" for c in conn] for conn in maze_adj_list ] - tok: MazeTokenizer = MazeTokenizer( - tokenization_mode=tok_mode, max_grid_size=maze_size - ) - tokenized_maze: list[str] = solved_maze.as_tokens(tok) + tokenized_maze: list[str] = solved_maze.as_tokens(tokenizer) tokenizer_adj_list = tokenized_maze[ tokenized_maze.index(SPECIAL_TOKENS.ADJLIST_START) diff --git a/tests/unit/maze_transformer/training/zanj/test_zanj_ht_save_load.py b/tests/unit/maze_transformer/training/zanj/test_zanj_ht_save_load.py index ae8085f7..2db1d8da 100644 --- a/tests/unit/maze_transformer/training/zanj/test_zanj_ht_save_load.py +++ b/tests/unit/maze_transformer/training/zanj/test_zanj_ht_save_load.py @@ -2,7 +2,11 @@ import pytest from maze_dataset import MazeDatasetConfig -from maze_dataset.tokenization import MazeTokenizer, TokenizationMode +from maze_dataset.tokenization import ( + MazeTokenizer, + MazeTokenizerModular, + TokenizationMode, +) from zanj import ZANJ from zanj.torchutil import assert_model_exact_equality @@ -33,21 +37,22 @@ ( "raster", MazeTokenizer( - tokenization_mode=TokenizationMode.AOTP_UT_rasterized, max_grid_size=10 + tokenization_mode=TokenizationMode.AOTP_UT_rasterized, max_grid_size=5 ), ), ( "uniform", MazeTokenizer( - tokenization_mode=TokenizationMode.AOTP_UT_uniform, max_grid_size=10 + tokenization_mode=TokenizationMode.AOTP_UT_uniform, max_grid_size=5 ), ), ( "indexed", MazeTokenizer( - tokenization_mode=TokenizationMode.AOTP_CTT_indexed, max_grid_size=10 + tokenization_mode=TokenizationMode.AOTP_CTT_indexed, max_grid_size=5 ), ), + ("modular", MazeTokenizerModular()), # only checking default for now ] ] @@ -101,7 +106,12 @@ def test_model_save_fold_ln(cfg_model: tuple[ConfigHolder, ZanjHookedTransformer zanj.save(model, fname) model_load = zanj.read(fname) - assert_model_output_equality(model, model_load) + vocab_size: int = len(model.zanj_model_config.tokenizer) + assert_model_output_equality( + model, + model_load, + check_argsort_equality=(vocab_size > 2048), + ) @pytest.mark.parametrize("cfg_model", MODELS, ids=lambda x: x[0].name) @@ -126,4 +136,9 @@ def test_model_save_refactored_attn_matrices( zanj.save(model, fname) model_load = zanj.read(fname) - assert_model_output_equality(model, model_load) + vocab_size: int = len(model.zanj_model_config.tokenizer) + assert_model_output_equality( + model, + model_load, + check_argsort_equality=(vocab_size > 2048), + )