Training in progress, epoch 2, checkpoint

checkpoint-82/config.json

@@ -0,0 +1,61 @@
+{
+  "_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": "B-MajorClaim",
+    "2": "I-MajorClaim",
+    "3": "B-Claim",
+    "4": "I-Claim",
+    "5": "B-Premise",
+    "6": "I-Premise"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Claim": 3,
+    "B-MajorClaim": 1,
+    "B-Premise": 5,
+    "I-Claim": 4,
+    "I-MajorClaim": 2,
+    "I-Premise": 6,
+    "O": 0
+  },
+  "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": "4.45.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-82/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c0f1c9bd04591a3456a15bf7bde168d661c124f762a97ce2cffe913982dc60
+size 592330980

checkpoint-82/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd92fd9832594cb14d0ef621d9be0cc96cd13140b7e88632eef8417ba7439ae4
+size 1014670074

checkpoint-82/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f23442d3fbd2b285133fc17830fc5ef321f30363930dc169287329da4345042
+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 +1,159 @@
+{
+  "best_metric": 0.47574615478515625,
+  "best_model_checkpoint": "longformer-full_labels/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_B-Claim": {
+        "f1-score": 0.0,
+        "precision": 0.0,
+        "recall": 0.0,
+        "support": 284.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.0,
+        "precision": 0.0,
+        "recall": 0.0,
+        "support": 141.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.12010443864229765,
+        "precision": 0.7931034482758621,
+        "recall": 0.06497175141242938,
+        "support": 708.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.15241779497098645,
+        "precision": 0.35688405797101447,
+        "recall": 0.09690113133300542,
+        "support": 4066.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.4055459272097054,
+        "precision": 0.4854771784232365,
+        "recall": 0.3482142857142857,
+        "support": 2016.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8243874805268375,
+        "precision": 0.7254034519284691,
+        "recall": 0.9546535465354653,
+        "support": 12195.0
+      },
+      "eval_O": {
+        "f1-score": 0.8527010510877536,
+        "precision": 0.8224254998113919,
+        "recall": 0.8852908334179271,
+        "support": 9851.0
+      },
+      "eval_accuracy": 0.7349372885410614,
+      "eval_loss": 0.7363316416740417,
+      "eval_macro avg": {
+        "f1-score": 0.3364509560625115,
+        "precision": 0.4547562337728534,
+        "recall": 0.3357187926304447,
+        "support": 29261.0
+      },
+      "eval_runtime": 1.4874,
+      "eval_samples_per_second": 53.786,
+      "eval_steps_per_second": 6.723,
+      "eval_weighted avg": {
+        "f1-score": 0.6826734788782265,
+        "precision": 0.6814305221181916,
+        "recall": 0.7349372885410614,
+        "support": 29261.0
+      },
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "eval_B-Claim": {
+        "f1-score": 0.020905923344947737,
+        "precision": 1.0,
+        "recall": 0.01056338028169014,
+        "support": 284.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.0,
+        "precision": 0.0,
+        "recall": 0.0,
+        "support": 141.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.7109756097560975,
+        "precision": 0.6255364806866953,
+        "recall": 0.8234463276836158,
+        "support": 708.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.5191693290734825,
+        "precision": 0.5658734764944864,
+        "recall": 0.4795868175110674,
+        "support": 4066.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.6294067067927773,
+        "precision": 0.745417515274949,
+        "recall": 0.5446428571428571,
+        "support": 2016.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8761396663614285,
+        "precision": 0.8514935768456895,
+        "recall": 0.9022550225502255,
+        "support": 12195.0
+      },
+      "eval_O": {
+        "f1-score": 0.931648308418568,
+        "precision": 0.9034811635670005,
+        "recall": 0.9616282610902447,
+        "support": 9851.0
+      },
+      "eval_accuracy": 0.8239636376063703,
+      "eval_loss": 0.47574615478515625,
+      "eval_macro avg": {
+        "f1-score": 0.5268922205353288,
+        "precision": 0.6702574589812601,
+        "recall": 0.5317318094656714,
+        "support": 29261.0
+      },
+      "eval_runtime": 1.5047,
+      "eval_samples_per_second": 53.167,
+      "eval_steps_per_second": 6.646,
+      "eval_weighted avg": {
+        "f1-score": 0.8117058591419718,
+        "precision": 0.8138696629123667,
+        "recall": 0.8239636376063703,
+        "support": 29261.0
+      },
+      "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": 287581625436000.0,
+  "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:fe195065619b864cb5750c9937fe7b655a8f6d715d46f4e339179bcd7da8efaa
+size 5176