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:b6e3849883c3517b9b28055f6fc3d74c0775b28242644cc630a0ee9b7eb6b640
+oid sha256:7e0f0f7d4c470e915eb2fafa01dff3de3771d0db50cf82273dc589da9bdd6d56
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f55fcd4716a9ebf451415365336befd631d5c2ea85fb1ecedba40fea4f4a13
+oid sha256:069e1e1d7d9896b15bfdcf354ae50c5e10727699cfca8c14f194fc1fd4d7bff7
 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": 1.177116870880127,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.1658653020858765,
+  "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": 10.858,
       "eval_steps_per_second": 1.361,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.9721,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.1658653020858765,
+      "eval_runtime": 177.5002,
+      "eval_samples_per_second": 10.873,
+      "eval_steps_per_second": 1.363,
+      "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
 }