Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895a4ce169cf38fd74c3ad3dd51ed6c9ee5b3cb889661fba0e80df7a18c43032
+oid sha256:8577247bbd5d663f4087a8239eac47a1cffbe0ec85b68f5f75aac67d8071f55e
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fabf296878f2964cebf816ab91e5921acd4dd1ea341d2f9a1b483e0881c53e39
+oid sha256:8b07e6e1f8c8fc506cd62f3e4931e6078210aac2a302a61c7dd5a2b987a41060
 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:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 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": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 465.044,
       "eval_steps_per_second": 232.663,
       "step": 13
+    },
+    {
+      "epoch": 0.0035746201966041107,
+      "grad_norm": 0.593859076499939,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 44.3825,
+      "step": 14
+    },
+    {
+      "epoch": 0.0038299502106472617,
+      "grad_norm": 0.6427613496780396,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 44.3755,
+      "step": 15
+    },
+    {
+      "epoch": 0.004085280224690412,
+      "grad_norm": 0.6255062222480774,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 44.369,
+      "step": 16
+    },
+    {
+      "epoch": 0.004340610238733563,
+      "grad_norm": 0.627750039100647,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 44.3665,
+      "step": 17
+    },
+    {
+      "epoch": 0.004595940252776714,
+      "grad_norm": 0.5742212533950806,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 44.3836,
+      "step": 18
+    },
+    {
+      "epoch": 0.004851270266819864,
+      "grad_norm": 0.6519846320152283,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 44.3914,
+      "step": 19
+    },
+    {
+      "epoch": 0.005106600280863015,
+      "grad_norm": 0.5559941530227661,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 44.3478,
+      "step": 20
+    },
+    {
+      "epoch": 0.005361930294906166,
+      "grad_norm": 0.576760470867157,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 44.3521,
+      "step": 21
+    },
+    {
+      "epoch": 0.005617260308949317,
+      "grad_norm": 0.8383557200431824,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 44.3474,
+      "step": 22
+    },
+    {
+      "epoch": 0.005872590322992467,
+      "grad_norm": 0.5783092379570007,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 44.3559,
+      "step": 23
+    },
+    {
+      "epoch": 0.006127920337035618,
+      "grad_norm": 0.5727637410163879,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 44.4125,
+      "step": 24
+    },
+    {
+      "epoch": 0.006383250351078769,
+      "grad_norm": 0.610941469669342,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 44.3396,
+      "step": 25
+    },
+    {
+      "epoch": 0.00663858036512192,
+      "grad_norm": 0.734337329864502,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 44.3969,
+      "step": 26
+    },
+    {
+      "epoch": 0.00663858036512192,
+      "eval_loss": 11.090802192687988,
+      "eval_runtime": 3.6364,
+      "eval_samples_per_second": 453.472,
+      "eval_steps_per_second": 226.873,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9712435200.0,
+  "total_flos": 19424870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null