Push from colab

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895d0b4e7c9692088ab659494df43601c24459804e33ba612b9d8606049a22e3
+oid sha256:2c96783acb8c74d71514ef8927f9d6ac1a93130c2bf3db5094ae80b1aed66636
 size 997293853

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ede9b09209dd5644fa9a7f453082eee896464a9a50eb50a44dea406b098059
+oid sha256:6e5084b61c785af4c599aa6aa597cb3003e2e1b4568d0febccab61a5b4502497
 size 498675053

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f774346f5effc87fcc856da9ee90ba0dfe7ed861e04acc9095bca1f19dbf66a3
+oid sha256:74f1b41ed073cf601ddb528f77f2d33a90008b787735ecf3176242c305532ebc
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f59298a08cd157d1ecc05e8d4af34705a5651d34f0742e06d5e37fa3d64298a
+oid sha256:962e5974b1f3a33508fee4b5c4e904aaaf5f33e9b6a39dcbdc7624a5c461236d
 size 623

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.615384615384615,
+  "epoch": 9.635974304068522,
   "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -9,62 +9,62 @@
   "log_history": [
     {
       "epoch": 1.07,
-      "learning_rate": 4.465811965811966e-05,
-      "loss": 0.386,
+      "learning_rate": 4.4646680942184155e-05,
+      "loss": 0.3168,
       "step": 500
     },
     {
       "epoch": 2.14,
-      "learning_rate": 3.931623931623932e-05,
-      "loss": 0.2035,
+      "learning_rate": 3.9293361884368315e-05,
+      "loss": 0.1535,
       "step": 1000
     },
     {
       "epoch": 3.21,
-      "learning_rate": 3.397435897435898e-05,
-      "loss": 0.1108,
+      "learning_rate": 3.394004282655247e-05,
+      "loss": 0.0775,
       "step": 1500
     },
     {
-      "epoch": 4.27,
-      "learning_rate": 2.863247863247863e-05,
-      "loss": 0.065,
+      "epoch": 4.28,
+      "learning_rate": 2.8586723768736618e-05,
+      "loss": 0.0427,
       "step": 2000
     },
     {
-      "epoch": 5.34,
-      "learning_rate": 2.3290598290598293e-05,
-      "loss": 0.0495,
+      "epoch": 5.35,
+      "learning_rate": 2.323340471092077e-05,
+      "loss": 0.0229,
       "step": 2500
     },
     {
-      "epoch": 6.41,
-      "learning_rate": 1.794871794871795e-05,
-      "loss": 0.0278,
+      "epoch": 6.42,
+      "learning_rate": 1.7880085653104924e-05,
+      "loss": 0.0129,
       "step": 3000
     },
     {
-      "epoch": 7.48,
-      "learning_rate": 1.2606837606837608e-05,
-      "loss": 0.02,
+      "epoch": 7.49,
+      "learning_rate": 1.252676659528908e-05,
+      "loss": 0.0057,
       "step": 3500
     },
     {
-      "epoch": 8.55,
-      "learning_rate": 7.264957264957266e-06,
-      "loss": 0.0161,
+      "epoch": 8.57,
+      "learning_rate": 7.173447537473234e-06,
+      "loss": 0.0031,
       "step": 4000
     },
     {
-      "epoch": 9.62,
-      "learning_rate": 1.9230769230769234e-06,
-      "loss": 0.0107,
+      "epoch": 9.64,
+      "learning_rate": 1.8201284796573876e-06,
+      "loss": 0.0013,
       "step": 4500
     }
   ],
-  "max_steps": 4680,
+  "max_steps": 4670,
   "num_train_epochs": 10,
-  "total_flos": 9458973995719680.0,
+  "total_flos": 9471997992960000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa25cc6bd0e760da2d27cd74041067b0cdabb6c5e42e39d5c26272c29b7b96bb
+oid sha256:de6b41d13df99af9a3e0e0051f825a5a77b3af23bbcb0ae6de01058925e1446b
 size 2991