Training in progress, epoch 2, checkpoint

checkpoint-82/config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForTokenClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "X_placeholder_X",
+    "2": "MajorClaim",
+    "3": "Claim",
+    "4": "Premise"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Claim": 3,
+    "MajorClaim": 2,
+    "O": 0,
+    "Premise": 4,
+    "X_placeholder_X": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-82/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fccdecdb27fc29d024d77df16a6af98d6ff1e263b1c3e4ca426dcfcbd003e9a
+size 592324828

checkpoint-82/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887d800715f36b641dd442b807fe8b88b056d9b8b9afe45ccc7a5825eb95ad1d
+size 1014657786

checkpoint-82/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89877ef9e20371f8fe0b9908da02b2f9df9183d72fe426c751529fa8e0e2e0e2
+size 14244

checkpoint-82/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35becfc5c99f2600532b4996a243492c9f70147154c4888c3394125f10b7908d
+size 1064

checkpoint-82/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-82/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-82/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.29108279943466187,
+  "best_model_checkpoint": "longformer-sep_tok/checkpoint-82",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 82,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_Claim": {
+        "f1-score": 0.24522979923676788,
+        "precision": 0.5429831006612784,
+        "recall": 0.15837976853836264,
+        "support": 4666.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.6928622927180966,
+        "precision": 0.6182052106786748,
+        "recall": 0.7880278802788028,
+        "support": 2439.0
+      },
+      "eval_O": {
+        "f1-score": 0.9984117287721441,
+        "precision": 0.9983710702068741,
+        "recall": 0.9984523906491813,
+        "support": 12277.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8789023162134945,
+        "precision": 0.81162452775356,
+        "recall": 0.9583419120170201,
+        "support": 14571.0
+      },
+      "eval_accuracy": 0.8506759343798781,
+      "eval_loss": 0.3661530613899231,
+      "eval_macro avg": {
+        "f1-score": 0.7038515342351258,
+        "precision": 0.7427959773250968,
+        "recall": 0.7258004878708417,
+        "support": 33953.0
+      },
+      "eval_runtime": 1.3975,
+      "eval_samples_per_second": 57.244,
+      "eval_steps_per_second": 7.156,
+      "eval_weighted avg": {
+        "f1-score": 0.8216687720926173,
+        "precision": 0.8283375336305401,
+        "recall": 0.8506759343798781,
+        "support": 33953.0
+      },
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "eval_Claim": {
+        "f1-score": 0.4604960021683155,
+        "precision": 0.6262440103206782,
+        "recall": 0.3641234462066009,
+        "support": 4666.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.7777777777777778,
+        "precision": 0.7612877895563408,
+        "recall": 0.7949979499794998,
+        "support": 2439.0
+      },
+      "eval_O": {
+        "f1-score": 0.9991033583306163,
+        "precision": 0.9998368545558365,
+        "recall": 0.9983709375254541,
+        "support": 12277.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8994033220448315,
+        "precision": 0.8484239990264086,
+        "recall": 0.9569006931576419,
+        "support": 14571.0
+      },
+      "eval_accuracy": 0.878803051276765,
+      "eval_loss": 0.29108279943466187,
+      "eval_macro avg": {
+        "f1-score": 0.7841951150803853,
+        "precision": 0.808948163364816,
+        "recall": 0.7785982567172992,
+        "support": 33953.0
+      },
+      "eval_runtime": 1.3877,
+      "eval_samples_per_second": 57.647,
+      "eval_steps_per_second": 7.206,
+      "eval_weighted avg": {
+        "f1-score": 0.8663997903530639,
+        "precision": 0.8663805444019677,
+        "recall": 0.878803051276765,
+        "support": 33953.0
+      },
+      "step": 82
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 205,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 287577465453600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-82/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10dd2d1f9e0756d1516c02d05267840dbdb5c7e30a763f7d34e96191809fd8bb
+size 5240