Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb01bbb5e28958191c1403ed5dbd1dcbcbc921fdb865a1be1f6d72e5e5af6437
+oid sha256:a099db4a597bf3663563fd45eb81a3fbd24e931df3d358a78bbe8cff55d805b6
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8b9b7e5c8e1f3c69cedbc4c939682037ad4ed01d672e7fee206dfd34bef1e6
+oid sha256:fb57a026e328ad1fa275fe7ceb29dd55f150ec16932f83f7a9370f8cd80671e8
 size 12639365

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdba55c43769059e866e73758c51b067ee153060eb661a7b796b5c001f2fe30
+oid sha256:fba2ec29b727e3a0922186da9958dbfb3f3436d108f3953990b55b82bc253fb4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.361365795135498,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.319554328918457,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 15.19,
       "eval_steps_per_second": 1.905,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.1628,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.319554328918457,
+      "eval_runtime": 126.2625,
+      "eval_samples_per_second": 15.286,
+      "eval_steps_per_second": 1.917,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3546752647888896.0,
+  "total_flos": 7082689446199296.0,
   "trial_name": null,
   "trial_params": null
 }