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:e54982edf4e429f30750c11cbc11500cd2273acd13dda3b5b312ccf2785d8a89
+size 592324828

checkpoint-243/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be6b69814b8aecab7c71b56c11c28dac0b4e7452c8079d9f462fc628ccf7639
+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": 0.44734338904742493,
+        "precision": 0.5477537437603993,
+        "recall": 0.3780431786862655,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.6504965622612681,
+        "precision": 0.5898856944925528,
+        "recall": 0.7249893571732652,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.8859784283513097,
+        "precision": 0.8689081979599547,
+        "recall": 0.9037328094302554,
+        "support": 10180.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8720120805863504,
+        "precision": 0.859258183929738,
+        "recall": 0.8851502916105877,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.8059953068711373,
+      "eval_loss": 0.47828415036201477,
+      "eval_macro avg": {
+        "f1-score": 0.7139576150615883,
+        "precision": 0.7164514550356611,
+        "recall": 0.7229789092250934,
+        "support": 30257.0
+      },
+      "eval_runtime": 4.8422,
+      "eval_samples_per_second": 16.728,
+      "eval_steps_per_second": 2.272,
+      "eval_weighted avg": {
+        "f1-score": 0.7984036588902531,
+        "precision": 0.7967665566250599,
+        "recall": 0.8059953068711373,
+        "support": 30257.0
+      },
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "eval_Claim": {
+        "f1-score": 0.5787561000934482,
+        "precision": 0.5281409891984082,
+        "recall": 0.6401010564997703,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.7702650787552824,
+        "precision": 0.7017850892544627,
+        "recall": 0.8535547041294168,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.9095337508698677,
+        "precision": 0.9206077681626081,
+        "recall": 0.8987229862475442,
+        "support": 10180.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8736648538675224,
+        "precision": 0.9162905211325401,
+        "recall": 0.8348287722446538,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.8297584030141786,
+      "eval_loss": 0.4241589605808258,
+      "eval_macro avg": {
+        "f1-score": 0.7830549458965301,
+        "precision": 0.7667060919370048,
+        "recall": 0.8068018797803463,
+        "support": 30257.0
+      },
+      "eval_runtime": 4.8636,
+      "eval_samples_per_second": 16.654,
+      "eval_steps_per_second": 2.262,
+      "eval_weighted avg": {
+        "f1-score": 0.8352680063880269,
+        "precision": 0.8452350051608073,
+        "recall": 0.8297584030141786,
+        "support": 30257.0
+      },
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "eval_Claim": {
+        "f1-score": 0.5728465083303793,
+        "precision": 0.5899245558530056,
+        "recall": 0.5567294441892513,
+        "support": 4354.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.7862876979822088,
+        "precision": 0.8017699115044248,
+        "recall": 0.7713920817369093,
+        "support": 2349.0
+      },
+      "eval_O": {
+        "f1-score": 0.914532821534425,
+        "precision": 0.9048168445341794,
+        "recall": 0.9244597249508841,
+        "support": 10180.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8880533114924986,
+        "precision": 0.8843330614665975,
+        "recall": 0.8918049947659639,
+        "support": 13374.0
+      },
+      "eval_accuracy": 0.8452258981392735,
+      "eval_loss": 0.41067537665367126,
+      "eval_macro avg": {
+        "f1-score": 0.7904300848348779,
+        "precision": 0.7952110933395518,
+        "recall": 0.7860965614107521,
+        "support": 30257.0
+      },
+      "eval_runtime": 4.8684,
+      "eval_samples_per_second": 16.638,
+      "eval_steps_per_second": 2.259,
+      "eval_weighted avg": {
+        "f1-score": 0.8437033615676307,
+        "precision": 0.8424495118392472,
+        "recall": 0.8452258981392735,
+        "support": 30257.0
+      },
+      "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 sha256:0ce83aa27c1a93c128c1dae6a1646206ab5d85d935efad925ac4e4beb0be29a0
+size 4856