Training in progress, epoch 1, checkpoint

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c07cbc53c51f5c54df711ef5979bc1f3418049f6d85a04b3dbda81a97924a1
+oid sha256:69b9ba937b00c0bff3bf5290f197251c779721017cdb182752b71e8c7bfa7a9c
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:607460e5b1146da32c681dd270585cfb7f0e8ea70592e43e5c102d6094ae78cc
+oid sha256:08e3e7034f6ea0face55aa4d5a5b9cf98d774aefa195cee077742d829291fbb1
 size 1014670074

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/trainer_state.json

@@ -14,68 +14,68 @@
         "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": 0.22222222222222218,
-        "precision": 0.780952380952381,
-        "recall": 0.12954186413902052,
-        "support": 633.0
+        "f1-score": 0.0028169014084507044,
+        "precision": 0.5,
+        "recall": 0.0014124293785310734,
+        "support": 708.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.3239807781739265,
-        "precision": 0.42653061224489797,
-        "recall": 0.26118470382404396,
-        "support": 4001.0
+        "f1-score": 0.2423290994719566,
+        "precision": 0.28976109215017065,
+        "recall": 0.20824135393671817,
+        "support": 4077.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.43526510480887787,
-        "precision": 0.5735174654752234,
-        "recall": 0.35072031793343267,
-        "support": 2013.0
+        "f1-score": 0.30434782608695654,
+        "precision": 0.5460358056265985,
+        "recall": 0.21096837944664032,
+        "support": 2024.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8370338686471983,
-        "precision": 0.7484180515958556,
-        "recall": 0.9494530698659139,
-        "support": 11336.0
+        "f1-score": 0.8170132059567293,
+        "precision": 0.7161945812807882,
+        "recall": 0.9508665794637018,
+        "support": 12232.0
       },
       "eval_O": {
-        "f1-score": 0.8603704893457543,
-        "precision": 0.8500846381718155,
-        "recall": 0.8709083026230219,
-        "support": 9226.0
+        "f1-score": 0.8384247714048214,
+        "precision": 0.8602345415778252,
+        "recall": 0.8176935549250102,
+        "support": 9868.0
       },
-      "eval_accuracy": 0.7469857706651218,
-      "eval_loss": 0.6934069395065308,
+      "eval_accuracy": 0.7151087475284653,
+      "eval_loss": 0.7737340927124023,
       "eval_macro avg": {
-        "f1-score": 0.3826960661711399,
-        "precision": 0.48278616406288194,
-        "recall": 0.3659726083407761,
-        "support": 27619.0
+        "f1-score": 0.31499025776127354,
+        "precision": 0.41603228866219755,
+        "recall": 0.31274032816437164,
+        "support": 29334.0
       },
-      "eval_runtime": 1.3993,
-      "eval_samples_per_second": 57.171,
-      "eval_steps_per_second": 7.146,
+      "eval_runtime": 1.417,
+      "eval_samples_per_second": 56.458,
+      "eval_steps_per_second": 7.057,
       "eval_weighted avg": {
-        "f1-score": 0.7147071394985115,
-        "precision": 0.7126373293529855,
-        "recall": 0.7469857706651218,
-        "support": 27619.0
+        "f1-score": 0.6774818055577092,
+        "precision": 0.6780466018204494,
+        "recall": 0.7151087475284653,
+        "support": 29334.0
       },
       "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,
   "total_flos": 143790812718000.0,
   "train_batch_size": 8,

checkpoint-41/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7dd3e20b3e160af2247e96dc319ccd6cb101ae7dc47f0b44b05679d4ad74d7
+oid sha256:434fba18a7a4c71e9fb6d8a84b52f11eea7c37f4a33492fefa13b8d79d7d0cd7
 size 4664