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:dd6f8ebd207ce388b0b2de5b2b6c1271cad14213e614097cac28c2ab1d715b32
+oid sha256:690144707e96928796b82719d70eeb0737bf4331f1a834022ce51cbe6e5187e8
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d47fc6880935095a949fc9402f5cc986f4b277444892b9dd5a5ddac82329a8
+oid sha256:f1518d2bd4cff822520a4643a59ea9cddb7de091ffe9d7a67415f6cc0cf7ef49
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e1c216ad0e3fdde267e30a9c468cf226b7b8f0a5659507396b5a46e5e857b8
+oid sha256:eed793b152ba29811eeaef2ddd85ed3082303355a228268d2b4d8d4cf2e23e4f
 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": 1.8709847927093506,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 1.8261810541152954,
+  "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": 43.561,
       "eval_steps_per_second": 5.45,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 1.849,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.8261810541152954,
+      "eval_runtime": 144.0251,
+      "eval_samples_per_second": 43.562,
+      "eval_steps_per_second": 5.45,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7886831549087744e+16,
+  "total_flos": 2.386786614194995e+16,
   "trial_name": null,
   "trial_params": null
 }