Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87955ae0ca5333d41ee87ba9f62cb5bb029f3dd42818be78e72c6f30666c5110
+oid sha256:65be35c1b2bc26ba83615857e2df5d9921e874ca79072e4666d7c2015ddf64dc
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2f3bda6d51104d90eab1d5f26b587d46fca1fa044e32027d66ae911259599e
+oid sha256:db17a9c3f1ce8cdb2557846c2c3b026cef52042b764f92855950568f5cf76ad5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77987d1aa285679a5104248e7fb7b9ed531b5e9fc37be752c17bd4076014e0e6
+oid sha256:acccb40364c81f60954b209e58ded29513bb5cbed178abd7a3865401a970666f
 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": 2.046644687652588,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.42613636363636365,
+  "best_metric": 2.0298001766204834,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5681818181818182,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 27.63,
       "eval_steps_per_second": 3.463,
       "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 2.1911,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 2.0298001766204834,
+      "eval_runtime": 54.0695,
+      "eval_samples_per_second": 27.594,
+      "eval_steps_per_second": 3.459,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9097682005278720.0,
+  "total_flos": 1.21510343872512e+16,
   "trial_name": null,
   "trial_params": null
 }