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:b3c6d86d493cc6109fb4abbeda91197b16550fb2b1a052b8d5d0cab6759fa73b
+oid sha256:84507a980b24d17e266f5639939a8b3f41e5f457a4c72e56ec956bfd67e3fd03
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac60ea27caacf934276f68574328b9b40bea0675ac2fac9834caeea4ee647eb
+oid sha256:7e298cdf7181ed00a5253701178fe3a741538e2bd701304280a3231ffc9b907b
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fe3b9d7263291620430092f11a7ea7a0681167058a88f3663f7172adf47f039
+oid sha256:5d08f4bbf51a6a6932d1b8245d602743b6b47c3167169e34a3aac6c4f5ce559b
 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": 1.5563029050827026,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 1.5300686359405518,
+  "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": 15.014,
       "eval_steps_per_second": 1.879,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.5445,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.5300686359405518,
+      "eval_runtime": 417.9846,
+      "eval_samples_per_second": 15.01,
+      "eval_steps_per_second": 1.878,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.729006729706906e+16,
+  "total_flos": 1.298292292791122e+17,
   "trial_name": null,
   "trial_params": null
 }