Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204e0212fc32764b7e4c76308ff9b0dddbb28453414d4a980a90e5c7de9c263a
+oid sha256:5f0b681152033ac6289221720520865bf43e20a1bb9ddf7ee0119664e4bf83e3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b585cafe5e95c6878a46b01a327f048ad42015e329e441481a90b5ed0bc3a2
+oid sha256:44fce0c53f7b5088be88f4c50fa9125b6597ad1148561a59b5ffc4e78beb3475
 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": 2.6044600009918213,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.5784292221069336,
+  "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": 30.678,
       "eval_steps_per_second": 3.838,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.5814,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.5784292221069336,
+      "eval_runtime": 204.5265,
+      "eval_samples_per_second": 30.676,
+      "eval_steps_per_second": 3.838,
+      "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
 }