Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93efaee10810fd3b7f470576e002617db3535f572554714efbac42b719e6ea91
+oid sha256:30e932ed307d098aecdcddc90bb163858cec1216e8b7ab333cc70ddf4ff55e0a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d6a398b6f4af7dd851e2bb1248119314000f59e28462d62d774d3d996402e9
+oid sha256:6cf7029a3047979a5b2692979f8b352fc366decc32d73c3591c1a790b04544c1
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24a5519079f5affefa77bc221612f519ec2d7b465daf634e60b03336ade4e2c
+oid sha256:957113e67ab11c2af45eb4aad3a4067ef1fc77a018bd85c77d56e6d10186026f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.318875789642334,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 2.3044281005859375,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 30.52,
       "eval_steps_per_second": 3.819,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 2.3267,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 2.3044281005859375,
+      "eval_runtime": 206.2612,
+      "eval_samples_per_second": 30.418,
+      "eval_steps_per_second": 3.806,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.523768039636992e+16,
+  "total_flos": 3.817057293729792e+16,
   "trial_name": null,
   "trial_params": null
 }