Training in progress, step 4670, 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 sha256:528522cb3d8f1c01010a44b6303938ecfd99e05fa92feb3454d6192f8f6928ea
|
| 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:b67ce54495ae28dbdbbbe594e1b7ff80017fdbb927cd4e3ca2f5e8ff575cb0ce
|
| 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 sha256:65290587629dd1583c0489628d0b7a9106874f60161d0864fbe2a2364ec4baf9
|
| 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": 35.
|
| 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,
|
|
@@ -8396,6 +8396,24 @@
|
|
| 8396 |
"mean_token_accuracy": 0.6490527987480164,
|
| 8397 |
"num_tokens": 16994749.0,
|
| 8398 |
"step": 4660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8399 |
}
|
| 8400 |
],
|
| 8401 |
"logging_steps": 5,
|
|
@@ -8415,7 +8433,7 @@
|
|
| 8415 |
"attributes": {}
|
| 8416 |
}
|
| 8417 |
},
|
| 8418 |
-
"total_flos": 8.
|
| 8419 |
"train_batch_size": 4,
|
| 8420 |
"trial_name": null,
|
| 8421 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8396 |
"mean_token_accuracy": 0.6490527987480164,
|
| 8397 |
"num_tokens": 16994749.0,
|
| 8398 |
"step": 4660
|
| 8399 |
+
},
|
| 8400 |
+
{
|
| 8401 |
+
"epoch": 35.88461538461539,
|
| 8402 |
+
"grad_norm": 0.0,
|
| 8403 |
+
"learning_rate": 2.668e-05,
|
| 8404 |
+
"loss": 1.7622,
|
| 8405 |
+
"mean_token_accuracy": 0.6474152833223343,
|
| 8406 |
+
"num_tokens": 17012449.0,
|
| 8407 |
+
"step": 4665
|
| 8408 |
+
},
|
| 8409 |
+
{
|
| 8410 |
+
"epoch": 35.92307692307692,
|
| 8411 |
+
"grad_norm": 0.0,
|
| 8412 |
+
"learning_rate": 2.6655e-05,
|
| 8413 |
+
"loss": 1.746,
|
| 8414 |
+
"mean_token_accuracy": 0.644548413157463,
|
| 8415 |
+
"num_tokens": 17031126.0,
|
| 8416 |
+
"step": 4670
|
| 8417 |
}
|
| 8418 |
],
|
| 8419 |
"logging_steps": 5,
|
|
|
|
| 8433 |
"attributes": {}
|
| 8434 |
}
|
| 8435 |
},
|
| 8436 |
+
"total_flos": 8.631235977397862e+17,
|
| 8437 |
"train_batch_size": 4,
|
| 8438 |
"trial_name": null,
|
| 8439 |
"trial_params": null
|