Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450095aa5c5465158557762d47903a143e90c0a66d68de92d95d75fa2ec4389d
+oid sha256:d03c8808fc50752ca91428f850989d82449dec488880eae9257c300b91949f72
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95be57b1ce63a56f8c9b301c6552bc014a53b16f1ac072041ccfacc6eb37422
+oid sha256:87dc49068fb02cd557a02bce5703a52aa50618d2f26662146e2837906b52918b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f1181e0e3e2c9c9c4867f3c8fa0bba665e663473833a2ab7b385cf778c0261
+oid sha256:16429469a49bff10e4c592f3a9a29ce1bd33c24708692eafba2bae5fee5e8095
 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": 1.190936803817749,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.1756863594055176,
+  "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": 10.869,
       "eval_steps_per_second": 1.363,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 0.9767,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.1756863594055176,
+      "eval_runtime": 177.0747,
+      "eval_samples_per_second": 10.899,
+      "eval_steps_per_second": 1.367,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.9915995189248e+16,
+  "total_flos": 3.735371896897536e+16,
   "trial_name": null,
   "trial_params": null
 }