Training in progress, step 41000, checkpoint

checkpoint-41000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3404da1f2cec2cb61a15bdcf130653fe2a5162663d65fffc53312d948d7b63fe
+oid sha256:a1ebbab1a636ecf9a2237d418df5caad9a873f98f4ae332980f0d778fb1085a8
 size 5125261

checkpoint-41000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd5bc74afc65c0430538dc8e5bf13a628cee7025a17c2464694dbab24dd8e65
+oid sha256:84ad864e5754123f31687f2074a9593a9d80032f28bda79a00c4b925fb4975ff
 size 2460465086

checkpoint-41000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf81365484e2b491a668f47a016d2fa2bf55d495831d4ade1be08c36c504305
+oid sha256:432835924e17cd2f804de7767081d755615e55ca9e28c6338a0caf6204c88416
 size 14244

checkpoint-41000/trainer_state.json

@@ -1145,15 +1145,15 @@
     {
       "epoch": 9.03,
       "learning_rate": 6.337666666666668e-06,
-      "loss": 1.1582,
+      "loss": 1.1416,
       "step": 41000
     },
     {
       "epoch": 9.03,
-      "eval_loss": 1.3448957204818726,
-      "eval_runtime": 43.2139,
-      "eval_samples_per_second": 210.071,
-      "eval_steps_per_second": 13.144,
+      "eval_loss": 1.3459570407867432,
+      "eval_runtime": 43.3162,
+      "eval_samples_per_second": 209.575,
+      "eval_steps_per_second": 13.113,
       "step": 41000
     }
   ],
@@ -1161,7 +1161,7 @@
   "max_steps": 60000,
   "num_train_epochs": 14,
   "save_steps": 500,
-  "total_flos": 4.155033672941568e+16,
+  "total_flos": 4.155907286984294e+16,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-41000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830dfd3361730689ba236ab185bd7320b3a6e7c41161919a3432f36a7c0f458c
+oid sha256:2937595315976c76b924187e8a40420b986d12550a38400a758323718071411a
 size 4664