Training in progress, step 582, checkpoint

checkpoint-582/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab427f00b31a56659dd5c3cd4e2bc057375aad478efb185890c7c631a7de362
+oid sha256:52e872b92d65ee9c018cbe1d42112eda9b4a77423cfda063f2ca51977740f1e0
 size 494777904

checkpoint-582/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2c7516d853f592d2ebf608c316f9a85a780ba1988f19c51fab1813847371a8
+oid sha256:e57e18426c03092087f3abcf6a950defc4e6b702756f92df62712d4bd343077c
 size 989645754

checkpoint-582/trainer_state.json

@@ -10,55 +10,55 @@
   "log_history": [
     {
       "epoch": 0.06891798759476224,
-      "grad_norm": 3412.1337890625,
+      "grad_norm": 2056.53857421875,
       "learning_rate": 9.88326321974139e-06,
-      "loss": 0.6771,
+      "loss": 0.6821,
       "step": 100
     },
     {
       "epoch": 0.13783597518952448,
-      "grad_norm": 2289.116943359375,
+      "grad_norm": 1819.6336669921875,
       "learning_rate": 9.53850386931162e-06,
-      "loss": 0.6546,
+      "loss": 0.6584,
       "step": 200
     },
     {
       "epoch": 0.2005513439007581,
-      "eval_accuracy": 0.6393522827617479,
-      "eval_loss": 0.6445200443267822,
-      "eval_runtime": 480.5705,
-      "eval_samples_per_second": 174.38,
-      "eval_steps_per_second": 21.799,
+      "eval_accuracy": 0.6663206128732011,
+      "eval_loss": 0.6131747961044312,
+      "eval_runtime": 482.559,
+      "eval_samples_per_second": 173.662,
+      "eval_steps_per_second": 21.709,
       "step": 291
     },
     {
       "epoch": 0.2067539627842867,
-      "grad_norm": 2271.836181640625,
+      "grad_norm": 1910.1011962890625,
       "learning_rate": 8.981820387323976e-06,
-      "loss": 0.659,
+      "loss": 0.6434,
       "step": 300
     },
     {
       "epoch": 0.27567195037904896,
-      "grad_norm": 250.91078186035156,
+      "grad_norm": 1810.4771728515625,
       "learning_rate": 8.239206948702616e-06,
-      "loss": 0.6682,
+      "loss": 0.6385,
       "step": 400
     },
     {
       "epoch": 0.34458993797381116,
-      "grad_norm": 236.6408233642578,
+      "grad_norm": 1388.5435791015625,
       "learning_rate": 7.345339674168113e-06,
-      "loss": 0.6415,
+      "loss": 0.6248,
       "step": 500
     },
     {
       "epoch": 0.4011026878015162,
-      "eval_accuracy": 0.6845421350325768,
-      "eval_loss": 0.6049288511276245,
-      "eval_runtime": 480.7106,
-      "eval_samples_per_second": 174.329,
-      "eval_steps_per_second": 21.793,
+      "eval_accuracy": 0.6850433163886304,
+      "eval_loss": 0.5890468955039978,
+      "eval_runtime": 481.5926,
+      "eval_samples_per_second": 174.01,
+      "eval_steps_per_second": 21.753,
       "step": 582
     }
   ],

checkpoint-582/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d496252f73b44be80766e54c79423ee5bd19a6ab8c58e5b90c726e512c89f188
+oid sha256:c006e54ea2fe3388052228de4bb025a6b560f297cbb8ca0c1442b57d9461bbd8
 size 5240