Training in progress, epoch 5, checkpoint

checkpoint-405/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": "4.38.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-405/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf02ae2871399d5feabd075b396abf179a41555b7ee19f48b135d5b5c69a7e6a
+size 592330980

checkpoint-405/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e1a8f75dd290021bab0769932cfbd09d96135ef84f9aeb0f6787d6264c22f7
+size 1014670074

checkpoint-405/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf337692f531efc3a23b910237391cc3da6dc28e56ab2fbd5db20c81d4fb98bd
+size 14244

checkpoint-405/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73756f22c58a684dfffbbc966a96d1e3e061222bcc1371ddea16fc12be01725
+size 1064

checkpoint-405/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-405/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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-405/trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 405,
+  "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": 295.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.0,
+        "precision": 0.0,
+        "recall": 0.0,
+        "support": 156.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.6820276497695853,
+        "precision": 0.6540404040404041,
+        "recall": 0.7125171939477304,
+        "support": 727.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.43557936284183824,
+        "precision": 0.5235513385293121,
+        "recall": 0.3729181752353367,
+        "support": 4143.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.5835814547001276,
+        "precision": 0.5468314069350338,
+        "recall": 0.6256269949840402,
+        "support": 2193.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8638885700072705,
+        "precision": 0.8318349299926308,
+        "recall": 0.8985115020297699,
+        "support": 12563.0
+      },
+      "eval_O": {
+        "f1-score": 0.8838224593742419,
+        "precision": 0.8730234786775275,
+        "recall": 0.8948919449901768,
+        "support": 10180.0
+      },
+      "eval_accuracy": 0.7876854942657897,
+      "eval_loss": 0.5461820363998413,
+      "eval_macro avg": {
+        "f1-score": 0.4926999280990091,
+        "precision": 0.4898973654535584,
+        "recall": 0.500637973026722,
+        "support": 30257.0
+      },
+      "eval_runtime": 5.0655,
+      "eval_samples_per_second": 15.991,
+      "eval_steps_per_second": 2.172,
+      "eval_weighted avg": {
+        "f1-score": 0.7743853744001297,
+        "precision": 0.7661527277359783,
+        "recall": 0.7876854942657897,
+        "support": 30257.0
+      },
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "eval_B-Claim": {
+        "f1-score": 0.46397188049209137,
+        "precision": 0.48175182481751827,
+        "recall": 0.44745762711864406,
+        "support": 295.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.6402439024390244,
+        "precision": 0.6104651162790697,
+        "recall": 0.6730769230769231,
+        "support": 156.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.7515299877600979,
+        "precision": 0.6769570011025359,
+        "recall": 0.844566712517194,
+        "support": 727.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.5573419078242231,
+        "precision": 0.5500705218617772,
+        "recall": 0.5648081100651702,
+        "support": 4143.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.7704582651391162,
+        "precision": 0.6987012987012987,
+        "recall": 0.8586411308709531,
+        "support": 2193.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8736837792436597,
+        "precision": 0.9002026342451874,
+        "recall": 0.8486826394969355,
+        "support": 12563.0
+      },
+      "eval_O": {
+        "f1-score": 0.9114385688236163,
+        "precision": 0.9145485115221046,
+        "recall": 0.9083497053045186,
+        "support": 10180.0
+      },
+      "eval_accuracy": 0.8256932280133523,
+      "eval_loss": 0.4454804062843323,
+      "eval_macro avg": {
+        "f1-score": 0.7098097559602613,
+        "precision": 0.6903852726470703,
+        "recall": 0.7350832640643341,
+        "support": 30257.0
+      },
+      "eval_runtime": 5.0817,
+      "eval_samples_per_second": 15.94,
+      "eval_steps_per_second": 2.165,
+      "eval_weighted avg": {
+        "f1-score": 0.8274557458920446,
+        "precision": 0.8315444607100787,
+        "recall": 0.8256932280133523,
+        "support": 30257.0
+      },
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "eval_B-Claim": {
+        "f1-score": 0.5551724137931033,
+        "precision": 0.5649122807017544,
+        "recall": 0.5457627118644067,
+        "support": 295.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.7108433734939757,
+        "precision": 0.6704545454545454,
+        "recall": 0.7564102564102564,
+        "support": 156.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.7860892388451444,
+        "precision": 0.7515683814303639,
+        "recall": 0.8239339752407153,
+        "support": 727.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.5878616796047988,
+        "precision": 0.573296627666896,
+        "recall": 0.6031860970311369,
+        "support": 4143.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.7989093387866394,
+        "precision": 0.7961956521739131,
+        "recall": 0.801641586867305,
+        "support": 2193.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8824656529006482,
+        "precision": 0.9044793581815143,
+        "recall": 0.8614980498288626,
+        "support": 12563.0
+      },
+      "eval_O": {
+        "f1-score": 0.9169814976266588,
+        "precision": 0.9044525128989107,
+        "recall": 0.9298624754420433,
+        "support": 10180.0
+      },
+      "eval_accuracy": 0.8402683676504611,
+      "eval_loss": 0.41143855452537537,
+      "eval_macro avg": {
+        "f1-score": 0.7483318850072812,
+        "precision": 0.7379084797868425,
+        "recall": 0.7603278789549609,
+        "support": 30257.0
+      },
+      "eval_runtime": 5.0654,
+      "eval_samples_per_second": 15.991,
+      "eval_steps_per_second": 2.172,
+      "eval_weighted avg": {
+        "f1-score": 0.8412916372002002,
+        "precision": 0.8430827906594975,
+        "recall": 0.8402683676504611,
+        "support": 30257.0
+      },
+      "step": 243
+    },
+    {
+      "epoch": 4.0,
+      "eval_B-Claim": {
+        "f1-score": 0.5518394648829431,
+        "precision": 0.5445544554455446,
+        "recall": 0.559322033898305,
+        "support": 295.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.7048192771084337,
+        "precision": 0.6647727272727273,
+        "recall": 0.75,
+        "support": 156.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.792225201072386,
+        "precision": 0.7725490196078432,
+        "recall": 0.81292984869326,
+        "support": 727.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.577999737153371,
+        "precision": 0.6344489324870167,
+        "recall": 0.5307748008689356,
+        "support": 4143.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.800089746466233,
+        "precision": 0.7875441696113075,
+        "recall": 0.8130414956680346,
+        "support": 2193.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8919449901768174,
+        "precision": 0.8642131979695431,
+        "recall": 0.9215155615696887,
+        "support": 12563.0
+      },
+      "eval_O": {
+        "f1-score": 0.9180246175312703,
+        "precision": 0.9316273895013655,
+        "recall": 0.9048133595284872,
+        "support": 10180.0
+      },
+      "eval_accuracy": 0.8475063621641273,
+      "eval_loss": 0.476072758436203,
+      "eval_macro avg": {
+        "f1-score": 0.7481347191987793,
+        "precision": 0.7428156988421926,
+        "recall": 0.7560567286038158,
+        "support": 30257.0
+      },
+      "eval_runtime": 5.0796,
+      "eval_samples_per_second": 15.946,
+      "eval_steps_per_second": 2.166,
+      "eval_weighted avg": {
+        "f1-score": 0.8443975745657389,
+        "precision": 0.8435295888400192,
+        "recall": 0.8475063621641273,
+        "support": 30257.0
+      },
+      "step": 324
+    },
+    {
+      "epoch": 5.0,
+      "eval_B-Claim": {
+        "f1-score": 0.5932203389830508,
+        "precision": 0.5932203389830508,
+        "recall": 0.5932203389830508,
+        "support": 295.0
+      },
+      "eval_B-MajorClaim": {
+        "f1-score": 0.7398119122257053,
+        "precision": 0.7239263803680982,
+        "recall": 0.7564102564102564,
+        "support": 156.0
+      },
+      "eval_B-Premise": {
+        "f1-score": 0.7774172615184944,
+        "precision": 0.7358722358722358,
+        "recall": 0.8239339752407153,
+        "support": 727.0
+      },
+      "eval_I-Claim": {
+        "f1-score": 0.5827523883294604,
+        "precision": 0.6264224257563141,
+        "recall": 0.5447743181269611,
+        "support": 4143.0
+      },
+      "eval_I-MajorClaim": {
+        "f1-score": 0.79782711384034,
+        "precision": 0.8275355218030377,
+        "recall": 0.7701778385772914,
+        "support": 2193.0
+      },
+      "eval_I-Premise": {
+        "f1-score": 0.8862478777589133,
+        "precision": 0.8792698213726104,
+        "recall": 0.8933375786038367,
+        "support": 12563.0
+      },
+      "eval_O": {
+        "f1-score": 0.9135231488172665,
+        "precision": 0.8963789354259242,
+        "recall": 0.931335952848723,
+        "support": 10180.0
+      },
+      "eval_accuracy": 0.8441682916349935,
+      "eval_loss": 0.526358962059021,
+      "eval_macro avg": {
+        "f1-score": 0.7558285773533188,
+        "precision": 0.7546608085116101,
+        "recall": 0.7590271798272621,
+        "support": 30257.0
+      },
+      "eval_runtime": 5.076,
+      "eval_samples_per_second": 15.958,
+      "eval_steps_per_second": 2.167,
+      "eval_weighted avg": {
+        "f1-score": 0.841232400970915,
+        "precision": 0.8396195745969204,
+        "recall": 0.8441682916349935,
+        "support": 30257.0
+      },
+      "step": 405
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 716721286995000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-405/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf5d4f8fefb4e78449403d6f60739ea086b5ecbb9bc2500c2c1407621dbdb5a
+size 4856