Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175155ece0b6fb35c587b34a1742a798e25005575cc432ce44da34d018df738d
+oid sha256:1c3963d02ebc5c564f675c9c4b6b695d331697a94cc66b96824b5ca5ce26e515
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf36eafdc301d266cdb20f11d3a83117dc7e89f63e7c36ab180c0d484df15036
+oid sha256:87d23b295cfc208984b15b45dde7a870c8327bb8dae689f22d940c0249641843
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f1c61b3a8c70fb7aba329a21ec4c4663e5956f07d7654e35cfd0a4b61491245
+oid sha256:5f00106cbfb8c632beca164b78975f9a67d424eb8a9d2ed6a5beb4029b939428
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.123192071914673,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.14204545454545456,
+  "best_metric": 2.083603858947754,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.2840909090909091,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 26.584,
       "eval_steps_per_second": 3.332,
       "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 2.2635,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 2.083603858947754,
+      "eval_runtime": 53.713,
+      "eval_samples_per_second": 27.777,
+      "eval_steps_per_second": 3.481,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3002636758302720.0,
+  "total_flos": 6019766034186240.0,
   "trial_name": null,
   "trial_params": null
 }