Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001ad34f85ce8eb319ca05191e5dde7f60ab17957ee7d99833249ff881e96847
+oid sha256:5b9f894ceeb07d1f85f9e115cad21d43beb0ee621eca78f9516b1d28bf3174a1
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d3a8bddc1fb34e814e6875924f360fb74d2a79348c51ce8d7b4944c269c42a
+oid sha256:d000df09342d68c0a3c152172de62c02d3215c8efd81a30da29c43709f750dda
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bdbeb5937e67c48029bfb76c4643cade36da9398930f69b0a6221a6ee4eb33
+oid sha256:c0ecaa372dca690ec2f6181df8c7b03d3248836d0042c5e635eada8af4366c91
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2593406438827515,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 1.2501240968704224,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6757741347905282,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 14.996,
       "eval_steps_per_second": 1.876,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 1.2438,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 1.2501240968704224,
+      "eval_runtime": 418.3937,
+      "eval_samples_per_second": 14.995,
+      "eval_steps_per_second": 1.876,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.133138222904146e+17,
+  "total_flos": 7.457059409239757e+17,
   "trial_name": null,
   "trial_params": null
 }