Training in progress, epoch 1, checkpoint

checkpoint-41/config.json

@@ -51,7 +51,7 @@
   "pad_token_id": 1,
   "sep_token_id": 2,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
+  "transformers_version": "4.45.2",
   "type_vocab_size": 1,
   "vocab_size": 50265
 }

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6931d18ac1fd57b89fe3f1a3ed77d94b97ee023f2ae9dd66b21982a9250d014c
+oid sha256:fd8a15bf5165d5baed2c51118f238469280e33f3644b6d560686e01e1a7404fb
 size 592324828

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8e523049a6577c1eb374141f4ca2218e9b4f5e6a89ad6833f9470adbf0659e
+oid sha256:b11b4dc3e9c98d116616f53f99e5fe1745feddf2ef825be5bc5997b935a0bbb8
 size 1014657786

checkpoint-41/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
+oid sha256:890a72e183ff8476ed86066068429358f1f4dfcd3a6900ecfd020262ecca5acf
 size 14244

checkpoint-41/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2edfde65f52fe0fcbc13f549dfed4fa891e3eb1476a6c03774294faa3865fa33
+oid sha256:ea37e94b47f3f494a56a7641c427579f080658979e969fdceddf122598ddd745
 size 1064

checkpoint-41/tokenizer_config.json

@@ -43,12 +43,12 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 4096,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "LongformerTokenizer",

checkpoint-41/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
+  "best_metric": 0.3661530613899231,
+  "best_model_checkpoint": "longformer-sep_tok/checkpoint-41",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 41,
@@ -11,54 +11,66 @@
     {
       "epoch": 1.0,
       "eval_Claim": {
-        "f1-score": 0.3650793650793651,
-        "precision": 0.45800144822592326,
-        "recall": 0.30350287907869483,
-        "support": 4168.0
+        "f1-score": 0.24522979923676788,
+        "precision": 0.5429831006612784,
+        "recall": 0.15837976853836264,
+        "support": 4666.0
       },
       "eval_MajorClaim": {
-        "f1-score": 0.652992277992278,
-        "precision": 0.6792168674698795,
-        "recall": 0.6287174721189591,
-        "support": 2152.0
+        "f1-score": 0.6928622927180966,
+        "precision": 0.6182052106786748,
+        "recall": 0.7880278802788028,
+        "support": 2439.0
       },
       "eval_O": {
-        "f1-score": 0.9929261022378432,
-        "precision": 0.9994626063591581,
-        "recall": 0.986474540311174,
-        "support": 11312.0
+        "f1-score": 0.9984117287721441,
+        "precision": 0.9983710702068741,
+        "recall": 0.9984523906491813,
+        "support": 12277.0
       },
       "eval_Premise": {
-        "f1-score": 0.873351637727677,
-        "precision": 0.8190918322936313,
-        "recall": 0.9353101963058064,
-        "support": 12073.0
+        "f1-score": 0.8789023162134945,
+        "precision": 0.81162452775356,
+        "recall": 0.9583419120170201,
+        "support": 14571.0
       },
-      "eval_accuracy": 0.8439319979801381,
-      "eval_loss": 0.3479689359664917,
+      "eval_accuracy": 0.8506759343798781,
+      "eval_loss": 0.3661530613899231,
       "eval_macro avg": {
-        "f1-score": 0.7210873457592908,
-        "precision": 0.7389431885871479,
-        "recall": 0.7135012719536586,
-        "support": 29705.0
+        "f1-score": 0.7038515342351258,
+        "precision": 0.7427959773250968,
+        "recall": 0.7258004878708417,
+        "support": 33953.0
       },
-      "eval_runtime": 1.3927,
-      "eval_samples_per_second": 57.443,
-      "eval_steps_per_second": 7.18,
+      "eval_runtime": 1.4601,
+      "eval_samples_per_second": 54.792,
+      "eval_steps_per_second": 6.849,
       "eval_weighted avg": {
-        "f1-score": 0.8316056073620907,
-        "precision": 0.8269800178224755,
-        "recall": 0.8439319979801381,
-        "support": 29705.0
+        "f1-score": 0.8216687720926173,
+        "precision": 0.8283375336305401,
+        "recall": 0.8506759343798781,
+        "support": 33953.0
       },
       "step": 41
     }
   ],
   "logging_steps": 500,
-  "max_steps": 656,
+  "max_steps": 205,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 16,
+  "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": 143788732726800.0,
   "train_batch_size": 8,
   "trial_name": null,

checkpoint-41/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e1d5f2e91f513d5e22b8b5c6d49a42c6f8d8aae75c864e0bacd5e369ee66a1
-size 4664
+oid sha256:34495a4f03209db85e06749911bd0d8eda693bd68f5922bb7626e8b55a33c2c9
+size 5176