Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17eb10f2ba8233f9fb519bc8ddcb7d404ecebd35e30169ead2d077dc504c9e46
+oid sha256:5cdb2d2bd383f9d682773ba18b3d650b8d86c24807263b460101d104990b5fbd
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1371801f893c84206f187f3e31be6bf63a4e61709a38828e8f85cc17b8c7ce94
+oid sha256:64c136729e239fcf9d475917514a3c85efe9d6d2a9042f14f52bc0da45959199
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36055d9fd25c4040bc7a4fdbd7b637c5d08e464796f0b68296e5cb34f28a816
+oid sha256:a89ea83940ca57b6ef197c4f2ea03f79aae4bea217693ebee91420b20a7417c9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7944462299346924,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 1.7612203359603882,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 0.8743169398907104,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,13 +161,27 @@
       "eval_samples_per_second": 11.32,
       "eval_steps_per_second": 1.416,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 1.7698,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.7612203359603882,
+      "eval_runtime": 554.1779,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.417,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8630550174151475e+17,
+  "total_flos": 3.124074497483735e+17,
   "trial_name": null,
   "trial_params": null
 }