Training in progress, epoch 3, checkpoint

checkpoint-243/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": "4.38.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-243/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493ebd37a1af7bf62dc4d31b3b12090d50327d353cf4f9ae3b5a22b08c632c3b
+size 592324828

checkpoint-243/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4927714b0c09271d1bd331a35d8c6402edfcff02c9b11052b5fc97564b7d9583
+size 1014657786

checkpoint-243/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4510120abb9e19965e0fc90a9342c8b839c7b334c4b005e1a74bbda01d4f51cc
+size 14244

checkpoint-243/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7403b5a2b8007c90df75059abe86b7e67f96587685c6c4fcbd47bcd5bb1b47
+size 1064

checkpoint-243/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-243/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-243/trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 243,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_Claim": {
+        "f1-score": 0.46243291592128805,
+        "precision": 0.6588785046728972,
+        "recall": 0.3562241616903996,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.8342621259029929,
+        "precision": 0.8096955128205128,
+        "recall": 0.8603661132396765,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.9993622448979592,
+        "precision": 0.9987253027405991,
+        "recall": 1.0,
+        "support": 12536.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8941052999825083,
+        "precision": 0.8401157057392676,
+        "recall": 0.955510692388216,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.8857510808573268,
+      "eval_loss": 0.2754688858985901,
+      "eval_macro avg": {
+        "f1-score": 0.7975406466761871,
+        "precision": 0.8268537564933192,
+        "recall": 0.793025241829573,
+        "support": 32613.0
+      },
+      "eval_runtime": 4.8781,
+      "eval_samples_per_second": 16.605,
+      "eval_steps_per_second": 2.255,
+      "eval_weighted avg": {
+        "f1-score": 0.8726239240080429,
+        "precision": 0.8746959682542021,
+        "recall": 0.8857510808573268,
+        "support": 32613.0
+      },
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "eval_Claim": {
+        "f1-score": 0.6446312571646924,
+        "precision": 0.5518482172064115,
+        "recall": 0.77491961414791,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.8912341158733577,
+        "precision": 0.9019180470793374,
+        "recall": 0.8808003405704555,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.9998005504806733,
+        "precision": 0.9999202106439001,
+        "recall": 0.9996809189534142,
+        "support": 12536.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8690409646250897,
+        "precision": 0.9324023303632625,
+        "recall": 0.8137430835950351,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.8848618649004998,
+      "eval_loss": 0.25178349018096924,
+      "eval_macro avg": {
+        "f1-score": 0.8511767220359533,
+        "precision": 0.8465222013232279,
+        "recall": 0.8672859893167036,
+        "support": 32613.0
+      },
+      "eval_runtime": 4.907,
+      "eval_samples_per_second": 16.507,
+      "eval_steps_per_second": 2.242,
+      "eval_weighted avg": {
+        "f1-score": 0.8909418634778542,
+        "precision": 0.9053537287957648,
+        "recall": 0.8848618649004998,
+        "support": 32613.0
+      },
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "eval_Claim": {
+        "f1-score": 0.6598764019226366,
+        "precision": 0.6576186131386861,
+        "recall": 0.6621497473587505,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.9062119366626066,
+        "precision": 0.8661233993015134,
+        "recall": 0.9501915708812261,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.9998404722022812,
+        "precision": 0.9997607273887382,
+        "recall": 0.9999202297383536,
+        "support": 12536.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.9007852612503775,
+        "precision": 0.9097148086014946,
+        "recall": 0.8920293106026619,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.9070002759635728,
+      "eval_loss": 0.23778581619262695,
+      "eval_macro avg": {
+        "f1-score": 0.8666785180094754,
+        "precision": 0.8583043871076081,
+        "recall": 0.876072714645248,
+        "support": 32613.0
+      },
+      "eval_runtime": 4.9168,
+      "eval_samples_per_second": 16.474,
+      "eval_steps_per_second": 2.237,
+      "eval_weighted avg": {
+        "f1-score": 0.907089072967282,
+        "precision": 0.9075314026721463,
+        "recall": 0.9070002759635728,
+        "support": 32613.0
+      },
+      "step": 243
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 430026551602200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-243/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f40e108617f6f8082cc0f1a47e89121d861cfb2e77ef6b602a909d9b6ba8d15
+size 4856