Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2592befc98f86aa9c39f766a20af328d4d18f5c7c775f8e1eca91c4b76b20dfc
+oid sha256:72235e3dd090cfa4df0b89efb2ac081bb9173513e361f96d1add317189559a95
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65abf4da535795bea55a70667eb47631177f9697f84bf2bc5806e450a88651a3
+oid sha256:458ffc0a86e2ba96ba3fc6f9e8a888e2ab3395ddd13833601882b0613507d44b
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d2fa6d0958c9fdd25d8902864c6b85a1f48f760bf117b29d82e62027fc276b
+oid sha256:63916ab7d5be6d7bb777fc4e5bd29eea52b9737122f154edbb3373deb10a9583
 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": 0.13471502590673576,
+  "epoch": 0.2694300518134715,
   "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": 54.684,
       "eval_steps_per_second": 28.009,
       "step": 10
+    },
+    {
+      "epoch": 0.15544041450777202,
+      "grad_norm": 1.4844454526901245,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.2829,
+      "step": 15
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 1.2455134391784668,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.0929,
+      "step": 20
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "eval_loss": 3.0835258960723877,
+      "eval_runtime": 0.7639,
+      "eval_samples_per_second": 53.673,
+      "eval_steps_per_second": 27.491,
+      "step": 20
+    },
+    {
+      "epoch": 0.25906735751295334,
+      "grad_norm": 0.8904907703399658,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.0248,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 44580445618176.0,
+  "total_flos": 89160891236352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null