Training in progress, step 3540, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71aa881e02624dcfdb0a4601971cd9e89fc226e80ae1bb7b1d9c712f944b75c0
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1ed51891550686ae7368db1b4f02374a5af772859fdc27b61142102115855ad
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07dee5e03a0b582b73d64af37abbfc2db15c0ea137612af50d62e644a3b2d130
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 27.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -6362,6 +6362,24 @@
|
|
| 6362 |
"mean_token_accuracy": 0.661261597275734,
|
| 6363 |
"num_tokens": 12873752.0,
|
| 6364 |
"step": 3530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6365 |
}
|
| 6366 |
],
|
| 6367 |
"logging_steps": 5,
|
|
@@ -6381,7 +6399,7 @@
|
|
| 6381 |
"attributes": {}
|
| 6382 |
}
|
| 6383 |
},
|
| 6384 |
-
"total_flos": 6.
|
| 6385 |
"train_batch_size": 4,
|
| 6386 |
"trial_name": null,
|
| 6387 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6362 |
"mean_token_accuracy": 0.661261597275734,
|
| 6363 |
"num_tokens": 12873752.0,
|
| 6364 |
"step": 3530
|
| 6365 |
+
},
|
| 6366 |
+
{
|
| 6367 |
+
"epoch": 27.192307692307693,
|
| 6368 |
+
"grad_norm": 0.0,
|
| 6369 |
+
"learning_rate": 3.233e-05,
|
| 6370 |
+
"loss": 1.769,
|
| 6371 |
+
"mean_token_accuracy": 0.6420103222131729,
|
| 6372 |
+
"num_tokens": 12891459.0,
|
| 6373 |
+
"step": 3535
|
| 6374 |
+
},
|
| 6375 |
+
{
|
| 6376 |
+
"epoch": 27.23076923076923,
|
| 6377 |
+
"grad_norm": 0.0,
|
| 6378 |
+
"learning_rate": 3.2305e-05,
|
| 6379 |
+
"loss": 1.7324,
|
| 6380 |
+
"mean_token_accuracy": 0.6513606965541839,
|
| 6381 |
+
"num_tokens": 12910141.0,
|
| 6382 |
+
"step": 3540
|
| 6383 |
}
|
| 6384 |
],
|
| 6385 |
"logging_steps": 5,
|
|
|
|
| 6399 |
"attributes": {}
|
| 6400 |
}
|
| 6401 |
},
|
| 6402 |
+
"total_flos": 6.54162143551488e+17,
|
| 6403 |
"train_batch_size": 4,
|
| 6404 |
"trial_name": null,
|
| 6405 |
"trial_params": null
|