Training in progress, step 582, checkpoint

checkpoint-582/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0a102b3811e05159937d5110e53a5b494a2e35464adfec0f569a0bc18d1d4d
+oid sha256:c140d89061ccc19d1dcf47dbe1d6f3b793ae1ac54b7202a744003fa62dced9c2
 size 1415329032

checkpoint-582/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab812f3f04604269e712b00981f3b661dc5963d2a22c8aa09d5b0508a401e40
+oid sha256:ada2c64ac1484ad1a00e1aa5093515c048cee25d691e8c2531d7c5704372c30a
 size 2830833850

checkpoint-582/tokenizer.json

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

checkpoint-582/trainer_state.json

@@ -10,55 +10,55 @@
   "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
     },
     {
       "epoch": 0.2067539627842867,
-      "grad_norm": 16.05835723876953,
-      "learning_rate": 9.001378813765828e-06,
-      "loss": 0.5318,
+      "grad_norm": 11.636795043945312,
+      "learning_rate": 8.994878055100864e-06,
+      "loss": 0.5184,
       "step": 300
     },
     {
       "epoch": 0.27567195037904896,
-      "grad_norm": 6.903239727020264,
-      "learning_rate": 8.263878494553072e-06,
-      "loss": 0.5267,
+      "grad_norm": 14.019742965698242,
+      "learning_rate": 8.255669894863161e-06,
+      "loss": 0.5074,
       "step": 400
     },
     {
       "epoch": 0.34458993797381116,
-      "grad_norm": 9.29619026184082,
+      "grad_norm": 32.54533767700195,
       "learning_rate": 7.373972308696536e-06,
-      "loss": 0.4947,
+      "loss": 0.4921,
       "step": 500
     },
     {
       "epoch": 0.4011026878015162,
-      "eval_accuracy": 0.7299706450920026,
-      "eval_loss": 0.5314406156539917,
-      "eval_runtime": 1150.6522,
-      "eval_samples_per_second": 72.83,
-      "eval_steps_per_second": 9.104,
+      "eval_accuracy": 0.7393737619627216,
+      "eval_loss": 0.5162956714630127,
+      "eval_runtime": 1152.6745,
+      "eval_samples_per_second": 72.702,
+      "eval_steps_per_second": 9.088,
       "step": 582
     }
   ],

checkpoint-582/training_args.bin

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