Training in progress, epoch 2, checkpoint

checkpoint-162/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9693539690e178b4784317118f92336ab8954c645bacc67cdf3ae18f330e8803
+oid sha256:deaa6c6706302021ad239de2c71b880c7ae14468e65ce3d2531189754736d7c0
 size 592330980

checkpoint-162/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838250f9da6488494fbf583732d03c963a7635aeac18542fc1936e2f7aae8964
+oid sha256:f0a32c500e36dd2f1241190c7fa8c744f77e57ee2378950a068aba330cb3949c
 size 1014670074

checkpoint-162/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6613e657dfa5c91f076329239ba74e9bccea696a05690b1f35a5faffc85df4aa
+oid sha256:88e210ec99a19f026e2def82a9c5587c47c7771d7dd08d2e2ba3261c169c79d9
 size 14244

checkpoint-162/trainer_state.json

@@ -14,123 +14,123 @@
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 339.0
+        "support": 271.0
       },
       "eval_B-MajorClaim": {
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 160.0
+        "support": 139.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.6898215147129765,
-        "precision": 0.6316254416961131,
-        "recall": 0.7598299681190224,
-        "support": 941.0
+        "f1-score": 0.6746310611384398,
+        "precision": 0.6075949367088608,
+        "recall": 0.7582938388625592,
+        "support": 633.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.5039833312905995,
-        "precision": 0.5940479630164692,
-        "recall": 0.43763303533418474,
-        "support": 4698.0
+        "f1-score": 0.4376506024096386,
+        "precision": 0.550587343690792,
+        "recall": 0.3631592101974506,
+        "support": 4001.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.6970899470899471,
-        "precision": 0.6303827751196173,
-        "recall": 0.7795857988165681,
-        "support": 2028.0
+        "f1-score": 0.620034542314335,
+        "precision": 0.5483008781977854,
+        "recall": 0.7133631395926477,
+        "support": 2013.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8719667429344848,
-        "precision": 0.8366728509585653,
-        "recall": 0.9103694233227912,
-        "support": 14861.0
+        "f1-score": 0.8620734063103671,
+        "precision": 0.8396186972154862,
+        "recall": 0.8857621736062103,
+        "support": 11336.0
       },
       "eval_O": {
-        "f1-score": 0.8820403825717322,
-        "precision": 0.8925603675823639,
-        "recall": 0.8717654922180846,
-        "support": 10473.0
+        "f1-score": 0.8807729058286443,
+        "precision": 0.8630878069080317,
+        "recall": 0.8991979189247779,
+        "support": 9226.0
       },
-      "eval_accuracy": 0.8062985074626866,
-      "eval_loss": 0.5531178712844849,
+      "eval_accuracy": 0.785908251565951,
+      "eval_loss": 0.5655931830406189,
       "eval_macro avg": {
-        "f1-score": 0.5207002740856772,
-        "precision": 0.5121841997675898,
-        "recall": 0.5370262454015216,
-        "support": 33500.0
-      },
-      "eval_runtime": 5.0026,
-      "eval_samples_per_second": 16.192,
-      "eval_steps_per_second": 2.199,
+        "f1-score": 0.49645178828591785,
+        "precision": 0.48702709467442235,
+        "recall": 0.5171108973119495,
+        "support": 27619.0
+      },
+      "eval_runtime": 4.8252,
+      "eval_samples_per_second": 16.58,
+      "eval_steps_per_second": 2.072,
       "eval_weighted avg": {
-        "f1-score": 0.7948191296080505,
-        "precision": 0.789408749451204,
-        "recall": 0.8062985074626866,
-        "support": 33500.0
+        "f1-score": 0.7721020318885458,
+        "precision": 0.766573839857488,
+        "recall": 0.785908251565951,
+        "support": 27619.0
       },
       "step": 81
     },
     {
       "epoch": 2.0,
       "eval_B-Claim": {
-        "f1-score": 0.4537205081669691,
-        "precision": 0.589622641509434,
-        "recall": 0.3687315634218289,
-        "support": 339.0
+        "f1-score": 0.36036036036036034,
+        "precision": 0.4624277456647399,
+        "recall": 0.2952029520295203,
+        "support": 271.0
       },
       "eval_B-MajorClaim": {
-        "f1-score": 0.42794759825327516,
-        "precision": 0.7101449275362319,
-        "recall": 0.30625,
-        "support": 160.0
+        "f1-score": 0.5836909871244635,
+        "precision": 0.723404255319149,
+        "recall": 0.4892086330935252,
+        "support": 139.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.7642352941176471,
-        "precision": 0.6858108108108109,
-        "recall": 0.8629117959617428,
-        "support": 941.0
+        "f1-score": 0.7396491228070177,
+        "precision": 0.6654040404040404,
+        "recall": 0.8325434439178515,
+        "support": 633.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.44524236983842014,
-        "precision": 0.6338969720802202,
-        "recall": 0.3431247339293316,
-        "support": 4698.0
+        "f1-score": 0.46704216775764956,
+        "precision": 0.5973520249221184,
+        "recall": 0.3834041489627593,
+        "support": 4001.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.7363764327367787,
-        "precision": 0.6217317487266554,
-        "recall": 0.9028599605522682,
-        "support": 2028.0
+        "f1-score": 0.7326456649010316,
+        "precision": 0.8348157560355781,
+        "recall": 0.6527570789865872,
+        "support": 2013.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8781162543828609,
-        "precision": 0.8411808209047208,
-        "recall": 0.9184442500504677,
-        "support": 14861.0
+        "f1-score": 0.8679505932065659,
+        "precision": 0.8045344983428744,
+        "recall": 0.9422194777699365,
+        "support": 11336.0
       },
       "eval_O": {
-        "f1-score": 0.9036260459748006,
-        "precision": 0.9102800116267804,
-        "recall": 0.8970686527260575,
-        "support": 10473.0
+        "f1-score": 0.9101698606271778,
+        "precision": 0.9143513454386348,
+        "recall": 0.9060264469976155,
+        "support": 9226.0
       },
-      "eval_accuracy": 0.820089552238806,
-      "eval_loss": 0.5071194171905518,
+      "eval_accuracy": 0.8169376154096818,
+      "eval_loss": 0.4831336438655853,
       "eval_macro avg": {
-        "f1-score": 0.6584663576386788,
-        "precision": 0.7132382761706934,
-        "recall": 0.6570558509488137,
-        "support": 33500.0
-      },
-      "eval_runtime": 4.9923,
-      "eval_samples_per_second": 16.225,
-      "eval_steps_per_second": 2.203,
+        "f1-score": 0.6659298223977524,
+        "precision": 0.7146128094467336,
+        "recall": 0.6430517402511137,
+        "support": 27619.0
+      },
+      "eval_runtime": 4.8125,
+      "eval_samples_per_second": 16.623,
+      "eval_steps_per_second": 2.078,
       "eval_weighted avg": {
-        "f1-score": 0.8071614798424686,
-        "precision": 0.8128932519203979,
-        "recall": 0.820089552238806,
-        "support": 33500.0
+        "f1-score": 0.8047632099274016,
+        "precision": 0.8064582361050344,
+        "recall": 0.8169376154096818,
+        "support": 27619.0
       },
       "step": 162
     }
@@ -140,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 286688514798000.0,
+  "total_flos": 287581625436000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-162/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c84096ff478c0991daa557c55b3ae423c1b21babebadb1405f26dd17942540f
+oid sha256:96f940fbb595414fcc9335f58119ba24a5ec23e0d6daa1a329588d596e481421
 size 4856