Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ffcc6cc4c2d0ca1a1d164f11c21f727fb1ccae9c9f781204fd047bfb151f74f
+oid sha256:42c9e5f3e10917e2fe283e856896be586c9be9af919e6221a09d1686256d6e82
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf23ffb0e0e597928a4c0c22a519209d168f17ab41b7a6e2b1919c625e89635
+oid sha256:b6f3767464af9507cdcf1f69666a2e6dc4044c8dac1ca27d2ad04da97ae5f4a7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db130484859ac18bcc59d3f63a2034b920c3187ab4ad8631498050925a77bb9
+oid sha256:1bc72a2dd61fde2bf7e35b38e131fc7660ee3fdebf98f8b23ba292ea3eb99170
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.566875696182251,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 2.531456708908081,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 30.449,
       "eval_steps_per_second": 3.81,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.5403,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.531456708908081,
+      "eval_runtime": 205.7527,
+      "eval_samples_per_second": 30.493,
+      "eval_steps_per_second": 3.815,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5859971699097600.0,
+  "total_flos": 8808208295362560.0,
   "trial_name": null,
   "trial_params": null
 }