Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387437f25c3f442fa0739b337e027bfa8f5dcfec3c7c574d82e670e3c4cb863e
+oid sha256:def217c92faedd2d632dc327d7e522ffc10631b6d4731d041ae5cd7da82f4f92
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1fe0d1ecf958c7364b2805cf809b31862a0afb16697808aef0cb437375828b
+oid sha256:05d4069360b25af605fe4f599981317f5539fc4d4f9362f52ab67a102919e8d2
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaef12c915ec3df03f09da67b9db52be2f6f7a559f6ee0149891445f6e19d91e
+oid sha256:b701ef80df8429c62719540f440d7ea22e6d2669ea82b32e253763c9a74995e8
 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": 0.027455121436114043,
+  "epoch": 0.054910242872228086,
   "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": 24.453,
       "eval_steps_per_second": 12.227,
       "step": 10
+    },
+    {
+      "epoch": 0.03167898627243928,
+      "grad_norm": 2.162389039993286,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.4427,
+      "step": 15
+    },
+    {
+      "epoch": 0.042238648363252376,
+      "grad_norm": 1.5160914659500122,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1306,
+      "step": 20
+    },
+    {
+      "epoch": 0.042238648363252376,
+      "eval_loss": 2.052976131439209,
+      "eval_runtime": 8.2639,
+      "eval_samples_per_second": 24.202,
+      "eval_steps_per_second": 12.101,
+      "step": 20
+    },
+    {
+      "epoch": 0.05279831045406547,
+      "grad_norm": 1.3696449995040894,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9587,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1107065697730560.0,
+  "total_flos": 2234632612085760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null