Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29665b487ce9447126541339b4f47def0e3caafdf61c98623dc324af96a11298
+oid sha256:7c17ad05e0cb28ca92ada300edf97759e728692e56b489dc7609e7e282d39d8f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d338db6a2414755ddf22a692a3e2e9cd8ea045c4da8dfe5081b46e753f057be
+oid sha256:56d1b1455d1a731ae06361e07295acc08ded39dd34657558a66d368f42a23833
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74dc1ad0e98e0db95a26d7764c58c1ed4015e89e0dabed8505302378845c8b0b
+oid sha256:7e0d167b9891e530dfce8ffa0ecb74bcb31b42ce9cddaf6bfc22d7ab81a514cd
 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": 2.6055357456207275,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.5787856578826904,
+  "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": 30.69,
       "eval_steps_per_second": 3.84,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.5812,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.5787856578826904,
+      "eval_runtime": 204.1968,
+      "eval_samples_per_second": 30.725,
+      "eval_steps_per_second": 3.844,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.139596603342848e+16,
+  "total_flos": 1.424403231326208e+16,
   "trial_name": null,
   "trial_params": null
 }