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:cbca87e9f87d27183a77bea205d4f506ba415ec4b17d8ef356961eca25c454e8
+oid sha256:7e2c5c7fc38ff48483c3e8ae71cc43bf8458577319c2431096a46a5d300a8196
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c4104206296beba11fdffee8decaa21800e4fccb160ccb69106d402a1449d4
+oid sha256:7738c2b980f340928153451669be7ddb705efa975da96280e374065ba4e078fa
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d934d6f4dbc26dc5abbe7275398b8505b09114da73f9a91808ece5d3f915603
+oid sha256:9ffbd4452562de0339f271c2541dc8fd70a4481fe995ac95d472b46ffc41cc97
 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": 0.037900874635568516,
+  "epoch": 0.07580174927113703,
   "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": 8.762,
       "eval_steps_per_second": 4.411,
       "step": 10
+    },
+    {
+      "epoch": 0.043731778425655975,
+      "grad_norm": 0.6184126138687134,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6805,
+      "step": 15
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "grad_norm": 0.5680379867553711,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.5336,
+      "step": 20
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "eval_loss": 0.4865669906139374,
+      "eval_runtime": 16.575,
+      "eval_samples_per_second": 8.748,
+      "eval_steps_per_second": 4.404,
+      "step": 20
+    },
+    {
+      "epoch": 0.0728862973760933,
+      "grad_norm": 0.4368301331996918,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4891,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1260405317959680.0,
+  "total_flos": 2533047580753920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null