Training in progress, epoch 1, checkpoint

checkpoint-41/config.json

@@ -55,7 +55,7 @@
   "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 sha256:69b9ba937b00c0bff3bf5290f197251c779721017cdb182752b71e8c7bfa7a9c
+oid sha256:b7fc971f72dde15b05153d3a4ad8194c9c4868a397e8399ce24ee7abffa2a087
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e3e7034f6ea0face55aa4d5a5b9cf98d774aefa195cee077742d829291fbb1
+oid sha256:7e072be56a8f4f23e14c881e1197d06bd3f883d57c66f412d385f11b339d8740
 size 1014670074

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/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": 0.7363316416740417,
+  "best_model_checkpoint": "longformer-full_labels/checkpoint-41",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 41,
@@ -23,51 +23,51 @@
         "support": 141.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.0028169014084507044,
-        "precision": 0.5,
-        "recall": 0.0014124293785310734,
+        "f1-score": 0.12010443864229765,
+        "precision": 0.7931034482758621,
+        "recall": 0.06497175141242938,
         "support": 708.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.2423290994719566,
-        "precision": 0.28976109215017065,
-        "recall": 0.20824135393671817,
-        "support": 4077.0
+        "f1-score": 0.15241779497098645,
+        "precision": 0.35688405797101447,
+        "recall": 0.09690113133300542,
+        "support": 4066.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.30434782608695654,
-        "precision": 0.5460358056265985,
-        "recall": 0.21096837944664032,
-        "support": 2024.0
+        "f1-score": 0.4055459272097054,
+        "precision": 0.4854771784232365,
+        "recall": 0.3482142857142857,
+        "support": 2016.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8170132059567293,
-        "precision": 0.7161945812807882,
-        "recall": 0.9508665794637018,
-        "support": 12232.0
+        "f1-score": 0.8243874805268375,
+        "precision": 0.7254034519284691,
+        "recall": 0.9546535465354653,
+        "support": 12195.0
       },
       "eval_O": {
-        "f1-score": 0.8384247714048214,
-        "precision": 0.8602345415778252,
-        "recall": 0.8176935549250102,
-        "support": 9868.0
+        "f1-score": 0.8527010510877536,
+        "precision": 0.8224254998113919,
+        "recall": 0.8852908334179271,
+        "support": 9851.0
       },
-      "eval_accuracy": 0.7151087475284653,
-      "eval_loss": 0.7737340927124023,
+      "eval_accuracy": 0.7349372885410614,
+      "eval_loss": 0.7363316416740417,
       "eval_macro avg": {
-        "f1-score": 0.31499025776127354,
-        "precision": 0.41603228866219755,
-        "recall": 0.31274032816437164,
-        "support": 29334.0
+        "f1-score": 0.3364509560625115,
+        "precision": 0.4547562337728534,
+        "recall": 0.3357187926304447,
+        "support": 29261.0
       },
-      "eval_runtime": 1.417,
-      "eval_samples_per_second": 56.458,
-      "eval_steps_per_second": 7.057,
+      "eval_runtime": 1.4953,
+      "eval_samples_per_second": 53.499,
+      "eval_steps_per_second": 6.687,
       "eval_weighted avg": {
-        "f1-score": 0.6774818055577092,
-        "precision": 0.6780466018204494,
-        "recall": 0.7151087475284653,
-        "support": 29334.0
+        "f1-score": 0.6826734788782265,
+        "precision": 0.6814305221181916,
+        "recall": 0.7349372885410614,
+        "support": 29261.0
       },
       "step": 41
     }
@@ -77,6 +77,18 @@
   "num_input_tokens_seen": 0,
   "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": 143790812718000.0,
   "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 sha256:434fba18a7a4c71e9fb6d8a84b52f11eea7c37f4a33492fefa13b8d79d7d0cd7
-size 4664
+oid sha256:d2c20621c437394fbe57b3ef350d9af58206c2da4ae74b0679b7a3cef0ee7703
+size 5176