Training in progress, step 291, checkpoint

checkpoint-291/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6e245edf7e7cf126792eb90a95b1de8943e66c77b9fa7983b764fe83910fa18
+oid sha256:d7644d37c8337ff124c044cb3ded5bee2190760e3f93b7182c1a45349b83a5de
 size 1415329032

checkpoint-291/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9eaf6bf17c76459814178c7f608c46b89f21d4f971f22df6a6e98590cbf8f8
+oid sha256:34399dc784eb6a9c418c1403cc4067357863542c80e62722eeaac1729d7a98a0
 size 2830833850

checkpoint-291/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d2f7da6b5846d8de9ae0004dad4845cf3a57eaf18a7c416da512f2cd2de5f8
+oid sha256:22e1f228c5f91c32a551f03c547e2753f195f7168d247ce88741efb49afe64fd
 size 1064

checkpoint-291/tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 640,
+    "max_length": 580,
     "strategy": "LongestFirst",
     "stride": 0
   },

checkpoint-291/trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 0.06891798759476224,
-      "grad_norm": 18.475433349609375,
-      "learning_rate": 9.890136982846565e-06,
-      "loss": 0.6101,
+      "grad_norm": 8.768977165222168,
+      "learning_rate": 9.88557738007169e-06,
+      "loss": 0.6099,
       "step": 100
     },
     {
       "epoch": 0.13783597518952448,
-      "grad_norm": 16.318273544311523,
-      "learning_rate": 9.552035901252971e-06,
-      "loss": 0.5632,
+      "grad_norm": 13.488529205322266,
+      "learning_rate": 9.547546534667266e-06,
+      "loss": 0.5507,
       "step": 200
     },
     {
       "epoch": 0.2005513439007581,
-      "eval_accuracy": 0.7079783298727954,
-      "eval_loss": 0.5585106015205383,
-      "eval_runtime": 1152.8471,
-      "eval_samples_per_second": 72.691,
-      "eval_steps_per_second": 9.087,
+      "eval_accuracy": 0.7176081716426815,
+      "eval_loss": 0.5506236553192139,
+      "eval_runtime": 1151.562,
+      "eval_samples_per_second": 72.772,
+      "eval_steps_per_second": 9.097,
       "step": 291
     }
   ],

checkpoint-291/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f067a16d006438bd235f769421ca0804d0ba51fb682819c90b04f5c99aad4f
+oid sha256:17ac0abd3be3c7ffa5c103daf33aa2dc3687beb22a067b1ddae465234d558ea1
 size 5304