Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b72650b34900e960d3b8e6d30ab11061eff5d72b62cfbe82ab01720d03b36ae
+oid sha256:10ec4bacb7d0f97022a5d7a7d8a7b0691d7a5fbbfa9a906a8cd5814b8bf2fe4e
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497a5525627977c98383368d11926918fabb1b93945858800fbd770cf9952fce
+oid sha256:cf4f6d213c420a61b781c520e13c16303685ff4ab39090289cc87f2dac3f0cdd
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b156be7230eb92a2c766e47652dc4dae9df7b1f8b521d4e9ecfbf2a31c902a2
+oid sha256:20f5e974d9a5182c0220936ec7ed26d0817f1e2d86d0852117aad18130cf4452
 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": 1.039888620376587,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.0277502536773682,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.6666666666666666,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 2.185,
       "eval_steps_per_second": 0.274,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.8552,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0277502536773682,
+      "eval_runtime": 724.238,
+      "eval_samples_per_second": 2.665,
+      "eval_steps_per_second": 0.334,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.03701644752896e+17,
+  "total_flos": 1.2948397906255872e+17,
   "trial_name": null,
   "trial_params": null
 }