Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eeb7dd87dac4eb8a6c9d272d0181f44ed99a2c135f3da8f25965d13f65382f6
+oid sha256:e096cb1cbdcfb7b15c27bc24f3188f4551fa1df7dbb2a9960123ba045df41c54
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f339580640d8d6689f85939a8e98015336608485e780425167c5bfd67cb3ca
+oid sha256:092167b3f35a0a53f85c7fb4fb3a5a2d3e782a3f55977fe3235e9726e0823f6d
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed793b152ba29811eeaef2ddd85ed3082303355a228268d2b4d8d4cf2e23e4f
+oid sha256:1585afb4bb5c414a38503027658037a96267ad2845903b5a78a03fb0cbe9f594
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.825339436531067,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 1.7843894958496094,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.36429872495446264,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,13 +63,27 @@
       "eval_samples_per_second": 43.748,
       "eval_steps_per_second": 5.474,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 1.7978,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.7843894958496094,
+      "eval_runtime": 143.3888,
+      "eval_samples_per_second": 43.755,
+      "eval_steps_per_second": 5.475,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.386786614194995e+16,
+  "total_flos": 2.983213629977395e+16,
   "trial_name": null,
   "trial_params": null
 }