Training in progress, step 291, checkpoint

checkpoint-291/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d06414e5bc5324c814cc60142f0a14567d558ec65cd340835a973427432780
+oid sha256:f6e245edf7e7cf126792eb90a95b1de8943e66c77b9fa7983b764fe83910fa18
 size 1415329032

checkpoint-291/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d552ff815a54c06779ec6dfe979da6239367a0544522ae7e9efa40d1c53071
+oid sha256:6e9eaf6bf17c76459814178c7f608c46b89f21d4f971f22df6a6e98590cbf8f8
 size 2830833850

checkpoint-291/trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 0.06891798759476224,
-      "grad_norm": 16.886085510253906,
-      "learning_rate": 9.887868638020368e-06,
-      "loss": 0.6214,
+      "grad_norm": 18.475433349609375,
+      "learning_rate": 9.890136982846565e-06,
+      "loss": 0.6101,
       "step": 100
     },
     {
       "epoch": 0.13783597518952448,
-      "grad_norm": 10.54348087310791,
+      "grad_norm": 16.318273544311523,
       "learning_rate": 9.552035901252971e-06,
-      "loss": 0.5573,
+      "loss": 0.5632,
       "step": 200
     },
     {
       "epoch": 0.2005513439007581,
-      "eval_accuracy": 0.7245531132908523,
-      "eval_loss": 0.5506443381309509,
-      "eval_runtime": 1148.8539,
-      "eval_samples_per_second": 72.944,
-      "eval_steps_per_second": 9.119,
+      "eval_accuracy": 0.7079783298727954,
+      "eval_loss": 0.5585106015205383,
+      "eval_runtime": 1152.8471,
+      "eval_samples_per_second": 72.691,
+      "eval_steps_per_second": 9.087,
       "step": 291
     }
   ],

checkpoint-291/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae443431e8a9554eb89937c50f60f45d0dc22b4dfcc8324512fd9f6d4f9191c9
+oid sha256:82f067a16d006438bd235f769421ca0804d0ba51fb682819c90b04f5c99aad4f
 size 5304