Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a35a69acb2e000ae0fd0a68664889c9e977ebb98f034edfde8667184b91ac7
+oid sha256:3f6070ee13ab9feebbcb509567a6d105caa73918f26b75f35c969364b563f833
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb6f587592a7a3e8ad25b90b01ad46e5a4ee13cacef676e4384ecdd81a177a9
+oid sha256:840d7b72ea135ef106e2bfe399a59b76bdd79c85babaf070c139da64759bd2d2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3d217570474ed44ac994697c08a6231247f4bb9ecce7bb8af4dbe390e8d62a
+oid sha256:b26837cce4b9686e80c01fd503576bec322032548fab3bb432c6bb17f35ea1da
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5918312072753906,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 2.551574468612671,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 18.8,
       "eval_steps_per_second": 2.352,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.5622,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.551574468612671,
+      "eval_runtime": 204.9306,
+      "eval_samples_per_second": 30.615,
+      "eval_steps_per_second": 3.831,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5821275858370560.0,
+  "total_flos": 8750270976491520.0,
   "trial_name": null,
   "trial_params": null
 }