Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f8c3883e1d61586cbdb3f2e5c26acb82daf0b4140da2fef9df82d640b8a243
+oid sha256:cbb483807e526797c9c7b0a75348939be454091a87a48c1532b300f24bf12b5a
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbaec31672f5e4bf8f3b72efe937c7721c85ffc8d851ba3d484fc474d34bb76f
+oid sha256:409c6f2167f59cf7b1a41b8f9f11cd935ae2395027281c0467772429d1edf55a
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16df58a38a19b7b1f9f5565b44c53c75669a622cbaf622cac5c2ed8badf7bd6a
+oid sha256:7bea08ca801c364515690c53d5d49520e2ed03cb6f378aadb8b48554d9d5835b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015939674462802317,
+  "epoch": 0.0031879348925604634,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 25.842,
       "eval_steps_per_second": 12.921,
       "step": 10
+    },
+    {
+      "epoch": 0.0018391932072464212,
+      "grad_norm": 3.554645538330078,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.4652,
+      "step": 15
+    },
+    {
+      "epoch": 0.002452257609661895,
+      "grad_norm": 3.504028797149658,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.1416,
+      "step": 20
+    },
+    {
+      "epoch": 0.002452257609661895,
+      "eval_loss": 0.0860864594578743,
+      "eval_runtime": 129.789,
+      "eval_samples_per_second": 26.458,
+      "eval_steps_per_second": 13.229,
+      "step": 20
+    },
+    {
+      "epoch": 0.0030653220120773687,
+      "grad_norm": 1.3442739248275757,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0971,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 421587736068096.0,
+  "total_flos": 843175472136192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null