Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd0cb7914fbc1839d3cc4e902819cb5e0cf880edba65eb6b1ace257f70a098c
+oid sha256:7a0c388daa133bd38bbf07bdf5b60fc433aaac54300defec014544754042e3df
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308f21aecd78dafaebc40c259098e8e4b55b8dbe0f44531d0de6e946fa5ece28
+oid sha256:d3b45c5dd994e445c402321c69708a79d0c349dbcd0d08b84d33608bc435b188
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0d7d803be24f959b116e68b8ea14894849bd60bc99076174569f43dd2e27b2
+oid sha256:4110a29a9e10aa9e4e90fd0efbe89be3f4a9a86eaa3578e63ebbc4263949b138
 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": 0.00732703959419473,
+  "epoch": 0.01465407918838946,
   "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": 15.71,
       "eval_steps_per_second": 7.866,
       "step": 10
+    },
+    {
+      "epoch": 0.008454276454840074,
+      "grad_norm": 24.24180793762207,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.2601,
+      "step": 15
+    },
+    {
+      "epoch": 0.01127236860645343,
+      "grad_norm": 9.227785110473633,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3134,
+      "step": 20
+    },
+    {
+      "epoch": 0.01127236860645343,
+      "eval_loss": 1.3870593309402466,
+      "eval_runtime": 47.6111,
+      "eval_samples_per_second": 15.69,
+      "eval_steps_per_second": 7.855,
+      "step": 20
+    },
+    {
+      "epoch": 0.014090460758066789,
+      "grad_norm": 26.356706619262695,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.3428,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1000194661416960.0,
+  "total_flos": 1950379589763072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null