epoch3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19180954deec480ae1a4f5b162c3ebe5ce9ea14e571f4640a672329f3865c351
+oid sha256:a31286e5d14809e22036036d0929ce777e7768e7f9548ed08aaa7ac2fd8899b1
 size 2950844807

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40e82b49ca56938f82edf39c6f1f057e53aa32dfe896335bed919dda726baba
+oid sha256:0755b6cb8f42b773bd744f3455d88e3b5494f4082b82f45f054045c8a5df60e7
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408be700a73614a79a295cc01b992eddbf0a4d68a80c25a2f5f21beb2f9f5a2f
+oid sha256:62cfb1be7e1d4b3e4b051ac2e136616b962a5de9f156f8c4cd9bcd5ae625db0e
 size 623

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9994634641947967,
-  "global_step": 684,
+  "epoch": 2.999463464194797,
+  "global_step": 2052,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12,11 +12,29 @@
       "learning_rate": 0.0002269005847953216,
       "loss": 0.2878,
       "step": 500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00015380116959064327,
+      "loss": 0.1983,
+      "step": 1000
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 8.07017543859649e-05,
+      "loss": 0.1427,
+      "step": 1500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 7.6023391812865485e-06,
+      "loss": 0.0947,
+      "step": 2000
     }
   ],
   "max_steps": 2052,
   "num_train_epochs": 3,
-  "total_flos": 3.79311956164608e+17,
+  "total_flos": 1.137732354048e+18,
   "trial_name": null,
   "trial_params": null
 }