Push from colab

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c96783acb8c74d71514ef8927f9d6ac1a93130c2bf3db5094ae80b1aed66636
+oid sha256:16a4d10ff927279fb36becd2f190a21747d3f3c6f1d882e03287ebd09915e5f9
 size 997293853

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5084b61c785af4c599aa6aa597cb3003e2e1b4568d0febccab61a5b4502497
+oid sha256:18b671aad3e989725b3b53833a9835710bb3b7be26e480788bf693301520cc9e
 size 498675053

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f1b41ed073cf601ddb528f77f2d33a90008b787735ecf3176242c305532ebc
+oid sha256:a0f011ef8d07f8bd7f0646e9ff2358e40145e8c4fd43ca91fc0690e958b28239
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962e5974b1f3a33508fee4b5c4e904aaaf5f33e9b6a39dcbdc7624a5c461236d
+oid sha256:203e92e616b2e900d74ef24033e04c5b1fd6fca595cf5289b6b8da042797bdf9
 size 623

trainer_state.json

@@ -1,70 +1,58 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.635974304068522,
-  "global_step": 4500,
+  "epoch": 9.25925925925926,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.07,
-      "learning_rate": 4.4646680942184155e-05,
-      "loss": 0.3168,
+      "epoch": 1.32,
+      "learning_rate": 4.3386243386243384e-05,
+      "loss": 0.3304,
       "step": 500
     },
     {
-      "epoch": 2.14,
-      "learning_rate": 3.9293361884368315e-05,
-      "loss": 0.1535,
+      "epoch": 2.65,
+      "learning_rate": 3.677248677248677e-05,
+      "loss": 0.1719,
       "step": 1000
     },
     {
-      "epoch": 3.21,
-      "learning_rate": 3.394004282655247e-05,
-      "loss": 0.0775,
+      "epoch": 3.97,
+      "learning_rate": 3.0158730158730158e-05,
+      "loss": 0.0953,
       "step": 1500
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 2.8586723768736618e-05,
-      "loss": 0.0427,
+      "epoch": 5.29,
+      "learning_rate": 2.3544973544973546e-05,
+      "loss": 0.0475,
       "step": 2000
     },
     {
-      "epoch": 5.35,
-      "learning_rate": 2.323340471092077e-05,
-      "loss": 0.0229,
+      "epoch": 6.61,
+      "learning_rate": 1.693121693121693e-05,
+      "loss": 0.0246,
       "step": 2500
     },
     {
-      "epoch": 6.42,
-      "learning_rate": 1.7880085653104924e-05,
-      "loss": 0.0129,
+      "epoch": 7.94,
+      "learning_rate": 1.0317460317460318e-05,
+      "loss": 0.0109,
       "step": 3000
     },
     {
-      "epoch": 7.49,
-      "learning_rate": 1.252676659528908e-05,
-      "loss": 0.0057,
+      "epoch": 9.26,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0084,
       "step": 3500
-    },
-    {
-      "epoch": 8.57,
-      "learning_rate": 7.173447537473234e-06,
-      "loss": 0.0031,
-      "step": 4000
-    },
-    {
-      "epoch": 9.64,
-      "learning_rate": 1.8201284796573876e-06,
-      "loss": 0.0013,
-      "step": 4500
     }
   ],
-  "max_steps": 4670,
+  "max_steps": 3780,
   "num_train_epochs": 10,
-  "total_flos": 9471997992960000.0,
+  "total_flos": 7349349553843200.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6b41d13df99af9a3e0e0051f825a5a77b3af23bbcb0ae6de01058925e1446b
+oid sha256:1ac2ed7e16e751a79f913fe7e493106649d8f341a524e788038ddd736aef5252
 size 2991