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:c670e468cb181082720bbce0d51a5ce0e3efe9d83a362275fd4341484ebce8e8
+oid sha256:f8ce6bdec635b30b63b8e52599e9146f7866666b010d86b0c5ccd1807c2b1980
 size 592324828

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ab315b4d58dcf77118f0d9aca46cb80093a1c76461c77ee05c13d783786a57
+oid sha256:3dae7214605fcee5d160e2d67e98c540bba57898c16a0d894f59b974637e48e3
 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": 0.5843302011489868,
+  "best_model_checkpoint": "longformer-simple/checkpoint-41",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 41,
@@ -11,54 +11,66 @@
     {
       "epoch": 1.0,
       "eval_Claim": {
-        "f1-score": 0.31881702957426067,
-        "precision": 0.49395770392749244,
-        "recall": 0.23536468330134358,
-        "support": 4168.0
+        "f1-score": 0.21931818181818183,
+        "precision": 0.48984771573604063,
+        "recall": 0.14128843338213762,
+        "support": 4098.0
       },
       "eval_MajorClaim": {
-        "f1-score": 0.5882107894188711,
-        "precision": 0.5330313325783315,
-        "recall": 0.6561338289962825,
-        "support": 2152.0
+        "f1-score": 0.5428571428571428,
+        "precision": 0.5396243701328447,
+        "recall": 0.5461288827074641,
+        "support": 2157.0
       },
       "eval_O": {
-        "f1-score": 0.8686845568461407,
-        "precision": 0.9200096957944491,
-        "recall": 0.82278343810969,
-        "support": 9226.0
+        "f1-score": 0.8746832169640548,
+        "precision": 0.8916069169126951,
+        "recall": 0.858390011166379,
+        "support": 9851.0
       },
       "eval_Premise": {
-        "f1-score": 0.8547340147728121,
-        "precision": 0.777574153261386,
-        "recall": 0.9488942267870455,
-        "support": 12073.0
+        "f1-score": 0.8596746372645179,
+        "precision": 0.7743724104313917,
+        "recall": 0.9660965412390726,
+        "support": 13155.0
       },
-      "eval_accuracy": 0.7762772004779318,
-      "eval_loss": 0.5690305829048157,
+      "eval_accuracy": 0.7833635214107515,
+      "eval_loss": 0.5843302011489868,
       "eval_macro avg": {
-        "f1-score": 0.6576115976530211,
-        "precision": 0.6811432213904147,
-        "recall": 0.6657940442985903,
-        "support": 27619.0
+        "f1-score": 0.6241332947259743,
+        "precision": 0.673862853303243,
+        "recall": 0.6279759671237634,
+        "support": 29261.0
       },
-      "eval_runtime": 1.3776,
-      "eval_samples_per_second": 58.074,
-      "eval_steps_per_second": 7.259,
+      "eval_runtime": 1.4428,
+      "eval_samples_per_second": 55.446,
+      "eval_steps_per_second": 6.931,
       "eval_weighted avg": {
-        "f1-score": 0.7577517824653167,
-        "precision": 0.7632992267425562,
-        "recall": 0.7762772004779318,
-        "support": 27619.0
+        "f1-score": 0.7516910901801511,
+        "precision": 0.7566882370115429,
+        "recall": 0.7833635214107515,
+        "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": 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:a0c1709ee996939c9fcadfbefb05efc50420ff427d1c0c0c37492208bad18716
-size 4664
+oid sha256:54bc35b0ffab8e37399c62cbb33d09982af8734fc19fedb709b4e41ada38552d
+size 5176