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:f39dfba120054ada8dd6a21d9ef689340801af98fff5401a8ce24efcba34aafb
+oid sha256:4498f45fd14cdd037c90171a45b1bfd87c6a9a1eab4ab7b6a203c5f35e81d323
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d87c82c89065ed5627a0383f7dd1202a87b18f19697daf69619563c2be9fef
+oid sha256:dc6105a2026dd737ce3a44c61a6c02dd5b9ad9ea82822cca43f51bdc23220e1b
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
+oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
 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": 0.00331929018256096,
+  "epoch": 0.00663858036512192,
   "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": 238.147,
       "eval_steps_per_second": 119.146,
       "step": 10
+    },
+    {
+      "epoch": 0.0038299502106472617,
+      "grad_norm": 0.5654242634773254,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 44.3696,
+      "step": 15
+    },
+    {
+      "epoch": 0.005106600280863015,
+      "grad_norm": 0.5463382601737976,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 44.3713,
+      "step": 20
+    },
+    {
+      "epoch": 0.005106600280863015,
+      "eval_loss": 11.090264320373535,
+      "eval_runtime": 7.0519,
+      "eval_samples_per_second": 233.838,
+      "eval_steps_per_second": 116.99,
+      "step": 20
+    },
+    {
+      "epoch": 0.006383250351078769,
+      "grad_norm": 0.5365641117095947,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 44.3573,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9712435200.0,
+  "total_flos": 19424870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null