Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff9162fbd145402974375e09dc12bab1aff0e8f70bc19a3f988845881883009
+oid sha256:2c0ca2028bc9806e04cb0e0e3d760a79c50dc3a6c08f480a09d692f1afae1742
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b194c558949949d1f1dcd9ee90dd9469de8c9839f43676b19d73133bde27646
+oid sha256:e14c410f1a37c25930037f8aac9ad5b09a3f2c1966e691aed68922e5a3b5c4d5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2915f019b93087780b8c2fddccd9b297eeaba58311ffa4c3bfcb1370794510fa
+oid sha256:d8f5982f9761d9e64b91454ebea38e874bb241e444b311de415fa1825f7bcf55
 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": 1.4250988960266113,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.4099382162094116,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "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": 12.719,
       "eval_steps_per_second": 1.595,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.1655,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.4099382162094116,
+      "eval_runtime": 151.5335,
+      "eval_samples_per_second": 12.736,
+      "eval_steps_per_second": 1.597,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.913313634025472e+16,
+  "total_flos": 2.55290200510464e+16,
   "trial_name": null,
   "trial_params": null
 }