Training in progress, epoch 1, checkpoint

checkpoint-41/config.json

@@ -47,7 +47,7 @@
   "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:bfc994ad8415d30f23b9160fd297fc1721753a9a31785662b36b8300f963c285
+oid sha256:2e4a3839877aa1c985a02ad56342a48337f33436994be51bac6c8e26ccc27eac
 size 592318676

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ddf9bfeadab734e0eb88ef4c31c494c82ba554c5c9d73870c49382fef4a135
+oid sha256:bf0530ba4a184f9756ab837efbbab600dff2dfd5b2c35ce6884af216f6977745
 size 1014645498

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": 0.20753507316112518,
+  "best_model_checkpoint": "longformer-spans/checkpoint-41",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 41,
@@ -11,48 +11,60 @@
     {
       "epoch": 1.0,
       "eval_B": {
-        "f1-score": 0.5721362229102167,
-        "precision": 0.8076923076923077,
-        "recall": 0.4429530201342282,
-        "support": 1043.0
+        "f1-score": 0.773921200750469,
+        "precision": 0.8258258258258259,
+        "recall": 0.7281553398058253,
+        "support": 1133.0
       },
       "eval_I": {
-        "f1-score": 0.927966217883682,
-        "precision": 0.8850358282336942,
-        "recall": 0.9752737752161383,
-        "support": 17350.0
+        "f1-score": 0.9504992905522983,
+        "precision": 0.9305934158104424,
+        "recall": 0.9712753734201456,
+        "support": 18277.0
       },
       "eval_O": {
-        "f1-score": 0.864171621779177,
-        "precision": 0.9349142280524723,
-        "recall": 0.8033817472360719,
-        "support": 9226.0
+        "f1-score": 0.9060251089982665,
+        "precision": 0.9388199433921185,
+        "recall": 0.8754441173484926,
+        "support": 9851.0
       },
-      "eval_accuracy": 0.8977515478474963,
-      "eval_loss": 0.29473039507865906,
+      "eval_accuracy": 0.9295991251153413,
+      "eval_loss": 0.20753507316112518,
       "eval_macro avg": {
-        "f1-score": 0.7880913541910252,
-        "precision": 0.8758807879928246,
-        "recall": 0.7405361808621462,
-        "support": 27619.0
+        "f1-score": 0.8768152001003445,
+        "precision": 0.8984130616761289,
+        "recall": 0.8582916101914878,
+        "support": 29261.0
       },
-      "eval_runtime": 1.3384,
-      "eval_samples_per_second": 59.772,
-      "eval_steps_per_second": 7.472,
+      "eval_runtime": 1.4039,
+      "eval_samples_per_second": 56.984,
+      "eval_steps_per_second": 7.123,
       "eval_weighted avg": {
-        "f1-score": 0.8932184128068332,
-        "precision": 0.8987766886849552,
-        "recall": 0.8977515478474963,
-        "support": 27619.0
+        "f1-score": 0.9286894365406706,
+        "precision": 0.9293063047668868,
+        "recall": 0.9295991251153413,
+        "support": 29261.0
       },
       "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": 143786652735600.0,
   "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:aac2e52662466408a70f6e06b318a723873ee5b7ae3588f54b82f465a458153d
-size 4664
+oid sha256:470664396359800f158e3f999f5efe315175d3f491bce43fd53b7e4f31b029fc
+size 5176