Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30837d17a9f2014154b5f21b3f96dad710a0fc206465bad2f7ae94eef6cb9eb
+oid sha256:c6507b5cd65f78716474a374034592c66f023c7ec9ddd341d24e28569e1f1766
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aabf6b53fdd2202e7d9af268c47b0deffe10f1bf5137c26a0f8ffc5b81a2373
+oid sha256:f72f6ffb476bdcbdcd0ad7c5962bf1baa6445c4a23812651383e40a3d11c875f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb7f6be2d16d160f7efe75bf46de6112a7eba7eb5758eaa5230d07ffd99ed7b
+oid sha256:c6fc0a05ece6bf6410546a20117db4d978b60197fb2c90e41d50543cdc997ec7
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
+oid sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.076017379760742,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.2586520947176685,
+  "best_metric": 2.0672309398651123,
+  "best_model_checkpoint": "./outputs/checkpoint-3200",
+  "epoch": 2.3315118397085612,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -441,13 +441,27 @@
       "eval_samples_per_second": 30.453,
       "eval_steps_per_second": 3.81,
       "step": 3100
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 2.0405,
+      "step": 3200
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 2.0672309398651123,
+      "eval_runtime": 206.3429,
+      "eval_samples_per_second": 30.406,
+      "eval_steps_per_second": 3.804,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.046021502214144e+16,
+  "total_flos": 9.337941745606656e+16,
   "trial_name": null,
   "trial_params": null
 }