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:cf7ec6c4f88e79180e33cccab0fe992e7afc064be0825bbebcf0b03ffa3fe168
+oid sha256:5ca2e2f8b96e8dad0d86abf281942bae46eefde42cc76751ce98612e99a485ff
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4745868b4c22d50a8002581edbf6dff65b743792e182e3b4cf492f973e735562
+oid sha256:57151210ee644864a77b6e80624a3197ff7fa68c3211c5435ff5b642b863a152
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26837cce4b9686e80c01fd503576bec322032548fab3bb432c6bb17f35ea1da
+oid sha256:56c7d9acd97a65ba6f52bddd9c1a7be0b5f95308e5fa05bcc7a62b6822eb6d6f
 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": 2.556633949279785,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 2.52408504486084,
+  "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": 30.364,
       "eval_steps_per_second": 3.799,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 2.5359,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.52408504486084,
+      "eval_runtime": 206.6465,
+      "eval_samples_per_second": 30.361,
+      "eval_steps_per_second": 3.799,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8750270976491520.0,
+  "total_flos": 1.167856193839104e+16,
   "trial_name": null,
   "trial_params": null
 }