Training in progress, epoch 1, checkpoint

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef9cbea4284aab780e4dfcae38caec260a206288c47dbe643fa2388ac84a0e9
+oid sha256:4cde84e40589a581099de6ffd2b1dfb10787b5c8d90d303ed810a70a33697cd5
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b929b09b8681501786d959eed9fa2f0053e4905bde89144f635820c2db40adf5
+oid sha256:5f651f65956ed08780348bf8bfcaac2b4e5a12648ffed35bb061a6ba26807bf7
 size 1014670074

checkpoint-41/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b75d0f85c6e5f43bda08f24453a869f5d0b5d0d33d936ef1b542f406f081347
+oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
 size 14244

checkpoint-41/trainer_state.json

@@ -14,60 +14,60 @@
         "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": 0.7931404072883173,
-        "precision": 0.8,
-        "recall": 0.7863974495217854,
-        "support": 941.0
+        "f1-score": 0.778263585259213,
+        "precision": 0.643595041322314,
+        "recall": 0.9842022116903634,
+        "support": 633.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.40067911714770804,
-        "precision": 0.46561443066516345,
-        "recall": 0.35163899531715626,
-        "support": 4698.0
+        "f1-score": 0.5213290460878884,
+        "precision": 0.4563708012760368,
+        "recall": 0.6078480379905024,
+        "support": 4001.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.5607655502392344,
-        "precision": 0.4144271570014144,
-        "recall": 0.8668639053254438,
-        "support": 2028.0
+        "f1-score": 0.520462355513902,
+        "precision": 0.7011784511784511,
+        "recall": 0.4138102334823646,
+        "support": 2013.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8556539864512767,
-        "precision": 0.8844441252513645,
-        "recall": 0.8286790929277976,
-        "support": 14861.0
+        "f1-score": 0.8648793805666204,
+        "precision": 0.8778050331607159,
+        "recall": 0.8523288637967537,
+        "support": 11336.0
       },
       "eval_O": {
-        "f1-score": 0.9839078762825717,
-        "precision": 0.9700167382286587,
-        "recall": 0.9982026510896428,
-        "support": 13353.0
+        "f1-score": 0.9947169811320755,
+        "precision": 0.9991081780076697,
+        "recall": 0.9903642149929278,
+        "support": 11312.0
       },
-      "eval_accuracy": 0.8189664650907091,
-      "eval_loss": 0.4724249243736267,
+      "eval_accuracy": 0.8332940582393537,
+      "eval_loss": 0.4083092212677002,
       "eval_macro avg": {
-        "f1-score": 0.5134495624870155,
-        "precision": 0.5049289215923716,
-        "recall": 0.5473974420259752,
-        "support": 36380.0
+        "f1-score": 0.5256644783656713,
+        "precision": 0.5254367864207411,
+        "recall": 0.5497933659932731,
+        "support": 29705.0
       },
-      "eval_runtime": 1.4721,
-      "eval_samples_per_second": 55.025,
-      "eval_steps_per_second": 7.473,
+      "eval_runtime": 1.4074,
+      "eval_samples_per_second": 56.843,
+      "eval_steps_per_second": 7.105,
       "eval_weighted avg": {
-        "f1-score": 0.8141826255128369,
-        "precision": 0.8212499318469384,
-        "recall": 0.8189664650907091,
-        "support": 36380.0
+        "f1-score": 0.830926787853407,
+        "precision": 0.8381591322948091,
+        "recall": 0.8332940582393537,
+        "support": 29705.0
       },
       "step": 41
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 16,
   "save_steps": 500,
-  "total_flos": 143344257399000.0,
+  "total_flos": 143790812718000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-41/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e60aef760c0bebacd32c85d34779d7bd28b7fb5a467a761ffe5e8a7e5bb2bb
+oid sha256:e06f6b44c30fa94c6272333e445e6562930fffeb3ba856f3a9330b45193b951f
 size 4728