Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03c8808fc50752ca91428f850989d82449dec488880eae9257c300b91949f72
+oid sha256:710e9fa8fd54f2c7fa5b3953a7a36335bcad1b94d1553b0c5e8cf5630febf85a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87dc49068fb02cd557a02bce5703a52aa50618d2f26662146e2837906b52918b
+oid sha256:2b2164a0bb29a36d7a715bdb338e2da0d52e4f170eb2f0dabeb399a898b471d6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16429469a49bff10e4c592f3a9a29ce1bd33c24708692eafba2bae5fee5e8095
+oid sha256:8dd42064bd4fb4eec8036fb285c03c704810bfb9590c79f20aac0cfa140f4e28
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1756863594055176,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.1637059450149536,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 10.899,
       "eval_steps_per_second": 1.367,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.9715,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.1637059450149536,
+      "eval_runtime": 177.4052,
+      "eval_samples_per_second": 10.879,
+      "eval_steps_per_second": 1.364,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.735371896897536e+16,
+  "total_flos": 4.481983825772544e+16,
   "trial_name": null,
   "trial_params": null
 }