Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be573dc907b95123c9d70afc0f8b6bc346f3c10adb17257f3d9b02328142edb7
+oid sha256:b2c5297ee9466e06e7e53b508afa7dce7e61df38c7227a754a7315d88bf1c431
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a3cfef7925fd69aaa167f42aa36f7c3d4d32e3fbfbbe4ab3747d0867e2d777
+oid sha256:cef7786197ef3124b84e7dee00a55fca504612468dfa7e302ffa2062d4b45c20
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012702445220704985,
+  "epoch": 0.015878056525881232,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,28 @@
       "learning_rate": 9.372094804706867e-05,
       "loss": 46.0,
       "step": 18
+    },
+    {
+      "epoch": 0.013337567481740234,
+      "grad_norm": 4.19372008764185e-05,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.015242934264845983,
+      "grad_norm": 3.232848030165769e-05,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.015242934264845983,
+      "eval_loss": 11.5,
+      "eval_runtime": 7.0877,
+      "eval_samples_per_second": 93.542,
+      "eval_steps_per_second": 46.842,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -92,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 797921771520.0,
+  "total_flos": 997402214400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null