Training in progress, step 873, checkpoint

checkpoint-873/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9bd17c42177e349f5ba87fd8a5536aa9d00b0b96302f87a3408650d068f982
+oid sha256:31336cb7f1010c32785c16ed3b278846a3e4fa00b952f1f4108256f8e73c6836
 size 1415329032

checkpoint-873/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c259c32f7bcf0a18eee31ffd2949f2ea393cd4d79b49775781ba7f79100acff
+oid sha256:c989400ccc9990935be608a8eaf3628d7e284b84a9033ac5a34af2fde476ef5c
 size 2830833850

checkpoint-873/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa6c7732367401f5dbb2ac690c561b5de753159878c16a608f9d7eaa3badb59
+oid sha256:5ab92f9f12426e403898bbace5d93fea6a5ad0b88475e09473f374b60e0bef3a
 size 1064

checkpoint-873/tokenizer.json

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

checkpoint-873/trainer_state.json

@@ -10,85 +10,85 @@
   "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
     },
     {
       "epoch": 0.4135079255685734,
-      "grad_norm": 7.382317543029785,
+      "grad_norm": 40.92453384399414,
       "learning_rate": 6.3732141693438686e-06,
-      "loss": 0.4753,
+      "loss": 0.471,
       "step": 600
     },
     {
       "epoch": 0.4824259131633356,
-      "grad_norm": 6.72527551651001,
-      "learning_rate": 5.308334189697317e-06,
-      "loss": 0.4647,
+      "grad_norm": 16.179763793945312,
+      "learning_rate": 5.3299412488905934e-06,
+      "loss": 0.4839,
       "step": 700
     },
     {
       "epoch": 0.5513439007580979,
-      "grad_norm": 10.617219924926758,
-      "learning_rate": 4.2290566338312015e-06,
-      "loss": 0.4384,
+      "grad_norm": 16.651920318603516,
+      "learning_rate": 4.250456101466412e-06,
+      "loss": 0.4727,
       "step": 800
     },
     {
       "epoch": 0.6016540317022743,
-      "eval_accuracy": 0.7359967542540751,
-      "eval_loss": 0.5269714593887329,
-      "eval_runtime": 1151.3002,
-      "eval_samples_per_second": 72.789,
-      "eval_steps_per_second": 9.099,
+      "eval_accuracy": 0.7367604591775853,
+      "eval_loss": 0.5193670988082886,
+      "eval_runtime": 1152.5824,
+      "eval_samples_per_second": 72.708,
+      "eval_steps_per_second": 9.089,
       "step": 873
     }
   ],

checkpoint-873/training_args.bin

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