Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3517988794b6754a2644001dd7b8ee63a56b069533360271461e45895b918ac8
+oid sha256:7954860969a458ed88c8bf6190f24903462ac28f37b787a59f41c398f9449ab2
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41bed0827f1d0ccd4f57540f2fae51ab8c35f5562aadf74c336b3170a88b5f6
+oid sha256:7f2e6c66100233bc4be4208c89af3a591ee515299660b124710ba5e654c8c363
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0991493e3ac522258a52c5e5855e34a1077a108bf34c050d61cd9082a802fb6b
+oid sha256:b17127c1713807334f935edb094b8a47aee68e40641e90a7299725b5a6682dd6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8596361875534058,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 1.813263177871704,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.29143897996357016,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,27 @@
       "eval_samples_per_second": 43.544,
       "eval_steps_per_second": 5.448,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.8371,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.813263177871704,
+      "eval_runtime": 144.1028,
+      "eval_samples_per_second": 43.538,
+      "eval_steps_per_second": 5.447,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7888590056259584e+16,
+  "total_flos": 2.386997635055616e+16,
   "trial_name": null,
   "trial_params": null
 }