Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ee6362e3ed5a15636537546553615ea30e20b8d38aa43293be28e2aa4a7050
+oid sha256:d30837d17a9f2014154b5f21b3f96dad710a0fc206465bad2f7ae94eef6cb9eb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6eadd4e8b0d4cef95445e6ea6f492547a2d6cd236ce6e40f103b686ec7d37d7
+oid sha256:2aabf6b53fdd2202e7d9af268c47b0deffe10f1bf5137c26a0f8ffc5b81a2373
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91dfacd60140a5cbf67fe9b8b80bd85ac38eb6bb2e3f798370b76b550205b468
+oid sha256:7eb7f6be2d16d160f7efe75bf46de6112a7eba7eb5758eaa5230d07ffd99ed7b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.089369297027588,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.185792349726776,
+  "best_metric": 2.076017379760742,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.2586520947176685,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 30.426,
       "eval_steps_per_second": 3.807,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 2.0245,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 2.076017379760742,
+      "eval_runtime": 206.0223,
+      "eval_samples_per_second": 30.453,
+      "eval_steps_per_second": 3.81,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.752327767687168e+16,
+  "total_flos": 9.046021502214144e+16,
   "trial_name": null,
   "trial_params": null
 }