Training in progress, epoch 1, checkpoint

checkpoint-41/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": "4.37.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-41/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1fb171fb5af12d9eccf503db2902b8a4bd37e32f7ed430ae657b51f610f39c5
+size 592324828

checkpoint-41/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c644f1cb6f93d7f4d03de827bf429d6dd27cd40feb48fd3713731ab93e3d5886
+size 1014657786

checkpoint-41/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
+size 14244

checkpoint-41/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edfde65f52fe0fcbc13f549dfed4fa891e3eb1476a6c03774294faa3865fa33
+size 1064

checkpoint-41/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-41/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-41/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 41,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_Claim": {
+        "f1-score": 0.3472626289341444,
+        "precision": 0.3978787878787879,
+        "recall": 0.3080713280150164,
+        "support": 4262.0
+      },
+      "eval_MajorClaim": {
+        "f1-score": 0.5334239746204397,
+        "precision": 0.5235765124555161,
+        "recall": 0.54364896073903,
+        "support": 2165.0
+      },
+      "eval_O": {
+        "f1-score": 0.8390533194223273,
+        "precision": 0.9157377442167086,
+        "recall": 0.7742197000405351,
+        "support": 9868.0
+      },
+      "eval_Premise": {
+        "f1-score": 0.8562600940945159,
+        "precision": 0.7896134170821731,
+        "recall": 0.9351944167497508,
+        "support": 13039.0
+      },
+      "eval_accuracy": 0.7610281584509443,
+      "eval_loss": 0.6209574341773987,
+      "eval_macro avg": {
+        "f1-score": 0.6440000042678569,
+        "precision": 0.6567016154082965,
+        "recall": 0.6402836013860831,
+        "support": 29334.0
+      },
+      "eval_runtime": 1.3904,
+      "eval_samples_per_second": 57.539,
+      "eval_steps_per_second": 7.192,
+      "eval_weighted avg": {
+        "f1-score": 0.7526914076678427,
+        "precision": 0.7554909643645776,
+        "recall": 0.7610281584509443,
+        "support": 29334.0
+      },
+      "step": 41
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 656,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 500,
+  "total_flos": 143788732726800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-41/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7094583e4fe5a2c55a5632947c89b5062ef3102a7d8117131675dc677677192b
+size 4664