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 sha256:4cde84e40589a581099de6ffd2b1dfb10787b5c8d90d303ed810a70a33697cd5
+oid sha256:f14b7db205675e39b7bd2b7766040d5767ef618a5de3d85f933fd230453ae8bd
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f651f65956ed08780348bf8bfcaac2b4e5a12648ffed35bb061a6ba26807bf7
+oid sha256:c8084d789f6d3e39dd190d98c0ab12ad0a6482fc011929fa0f34d81d7f752888
 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/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": 0.44872575998306274,
+  "best_model_checkpoint": "longformer-sep_tok_full_labels/checkpoint-41",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 41,
@@ -14,69 +14,81 @@
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 271.0
+        "support": 284.0
       },
       "eval_B-MajorClaim": {
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 139.0
+        "support": 141.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.778263585259213,
-        "precision": 0.643595041322314,
-        "recall": 0.9842022116903634,
-        "support": 633.0
+        "f1-score": 0.8161057692307693,
+        "precision": 0.7102510460251046,
+        "recall": 0.9590395480225988,
+        "support": 708.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.5213290460878884,
-        "precision": 0.4563708012760368,
-        "recall": 0.6078480379905024,
-        "support": 4001.0
+        "f1-score": 0.1270623933244832,
+        "precision": 0.5242566510172144,
+        "recall": 0.0722917565817868,
+        "support": 4634.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.520462355513902,
-        "precision": 0.7011784511784511,
-        "recall": 0.4138102334823646,
-        "support": 2013.0
+        "f1-score": 0.6541305725755335,
+        "precision": 0.635728952772074,
+        "recall": 0.6736292428198434,
+        "support": 2298.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8648793805666204,
-        "precision": 0.8778050331607159,
-        "recall": 0.8523288637967537,
-        "support": 11336.0
+        "f1-score": 0.8604508262992788,
+        "precision": 0.7685153090699018,
+        "recall": 0.9773712438468886,
+        "support": 13611.0
       },
       "eval_O": {
-        "f1-score": 0.9947169811320755,
-        "precision": 0.9991081780076697,
-        "recall": 0.9903642149929278,
-        "support": 11312.0
+        "f1-score": 0.9838489353153878,
+        "precision": 0.9707444699912788,
+        "recall": 0.9973120469169993,
+        "support": 12277.0
       },
-      "eval_accuracy": 0.8332940582393537,
-      "eval_loss": 0.4083092212677002,
+      "eval_accuracy": 0.827879716078108,
+      "eval_loss": 0.44872575998306274,
       "eval_macro avg": {
-        "f1-score": 0.5256644783656713,
-        "precision": 0.5254367864207411,
-        "recall": 0.5497933659932731,
-        "support": 29705.0
+        "f1-score": 0.49165692810649325,
+        "precision": 0.5156423469822248,
+        "recall": 0.5256634054554452,
+        "support": 33953.0
       },
-      "eval_runtime": 1.4074,
-      "eval_samples_per_second": 56.843,
-      "eval_steps_per_second": 7.105,
+      "eval_runtime": 1.5094,
+      "eval_samples_per_second": 53.001,
+      "eval_steps_per_second": 6.625,
       "eval_weighted avg": {
-        "f1-score": 0.830926787853407,
-        "precision": 0.8381591322948091,
-        "recall": 0.8332940582393537,
-        "support": 29705.0
+        "f1-score": 0.7793158674251499,
+        "precision": 0.7884799553707518,
+        "recall": 0.827879716078108,
+        "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": 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:e06f6b44c30fa94c6272333e445e6562930fffeb3ba856f3a9330b45193b951f
-size 4728
+oid sha256:a6bd9d9433178bb46233a14964dd91f951626a7f2358aaa46af2107a2de9fad4
+size 5240