Training in progress, step 8560, 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:ca4b14df57494a16f5014a37bf701f2df929fb8b2bc018c1de92946389ff728f
|
| 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 sha256:53872b93c284ef79eb22c25e3dd321f3d372cab6d3e4b8ba6fe1913df860c69f
|
| 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 sha256:0b48914297a38abe8a53ae3f3e6d26395c496766c8affef97157ca6708a8f879
|
| 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": 65.
|
| 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,
|
|
@@ -15398,6 +15398,24 @@
|
|
| 15398 |
"mean_token_accuracy": 0.6535750329494476,
|
| 15399 |
"num_tokens": 31183433.0,
|
| 15400 |
"step": 8550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15401 |
}
|
| 15402 |
],
|
| 15403 |
"logging_steps": 5,
|
|
@@ -15417,7 +15435,7 @@
|
|
| 15417 |
"attributes": {}
|
| 15418 |
}
|
| 15419 |
},
|
| 15420 |
-
"total_flos": 1.
|
| 15421 |
"train_batch_size": 4,
|
| 15422 |
"trial_name": null,
|
| 15423 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15398 |
"mean_token_accuracy": 0.6535750329494476,
|
| 15399 |
"num_tokens": 31183433.0,
|
| 15400 |
"step": 8550
|
| 15401 |
+
},
|
| 15402 |
+
{
|
| 15403 |
+
"epoch": 65.8076923076923,
|
| 15404 |
+
"grad_norm": 0.0,
|
| 15405 |
+
"learning_rate": 7.230000000000001e-06,
|
| 15406 |
+
"loss": 1.729,
|
| 15407 |
+
"mean_token_accuracy": 0.6469509840011597,
|
| 15408 |
+
"num_tokens": 31201276.0,
|
| 15409 |
+
"step": 8555
|
| 15410 |
+
},
|
| 15411 |
+
{
|
| 15412 |
+
"epoch": 65.84615384615384,
|
| 15413 |
+
"grad_norm": 0.0,
|
| 15414 |
+
"learning_rate": 7.2050000000000005e-06,
|
| 15415 |
+
"loss": 1.7259,
|
| 15416 |
+
"mean_token_accuracy": 0.6532280802726745,
|
| 15417 |
+
"num_tokens": 31219465.0,
|
| 15418 |
+
"step": 8560
|
| 15419 |
}
|
| 15420 |
],
|
| 15421 |
"logging_steps": 5,
|
|
|
|
| 15435 |
"attributes": {}
|
| 15436 |
}
|
| 15437 |
},
|
| 15438 |
+
"total_flos": 1.5830125276564685e+18,
|
| 15439 |
"train_batch_size": 4,
|
| 15440 |
"trial_name": null,
|
| 15441 |
"trial_params": null
|