Training in progress, step 7450, 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 sha256:336302ea77e3d05c021264a4b18fead5e6acdc2aee3699c3a93d7934689317c7
|
| 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 sha256:0083d471782e9081f0b899fc3afb80012dabd9ada2ff6b5913d4657e7fa3f3f9
|
| 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 sha256:3e857c6f6534bd23095c46bb1d0135d9b83754572815e2ed60c36f22854dc5fe
|
| 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": 57.
|
| 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,
|
|
@@ -13400,6 +13400,24 @@
|
|
| 13400 |
"mean_token_accuracy": 0.6552876085042953,
|
| 13401 |
"num_tokens": 27134390.0,
|
| 13402 |
"step": 7440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13403 |
}
|
| 13404 |
],
|
| 13405 |
"logging_steps": 5,
|
|
@@ -13419,7 +13437,7 @@
|
|
| 13419 |
"attributes": {}
|
| 13420 |
}
|
| 13421 |
},
|
| 13422 |
-
"total_flos": 1.
|
| 13423 |
"train_batch_size": 4,
|
| 13424 |
"trial_name": null,
|
| 13425 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13400 |
"mean_token_accuracy": 0.6552876085042953,
|
| 13401 |
"num_tokens": 27134390.0,
|
| 13402 |
"step": 7440
|
| 13403 |
+
},
|
| 13404 |
+
{
|
| 13405 |
+
"epoch": 57.26923076923077,
|
| 13406 |
+
"grad_norm": 0.0,
|
| 13407 |
+
"learning_rate": 1.278e-05,
|
| 13408 |
+
"loss": 1.7117,
|
| 13409 |
+
"mean_token_accuracy": 0.6523223549127579,
|
| 13410 |
+
"num_tokens": 27153262.0,
|
| 13411 |
+
"step": 7445
|
| 13412 |
+
},
|
| 13413 |
+
{
|
| 13414 |
+
"epoch": 57.30769230769231,
|
| 13415 |
+
"grad_norm": 0.0,
|
| 13416 |
+
"learning_rate": 1.2755e-05,
|
| 13417 |
+
"loss": 1.7682,
|
| 13418 |
+
"mean_token_accuracy": 0.645848673582077,
|
| 13419 |
+
"num_tokens": 27171115.0,
|
| 13420 |
+
"step": 7450
|
| 13421 |
}
|
| 13422 |
],
|
| 13423 |
"logging_steps": 5,
|
|
|
|
| 13437 |
"attributes": {}
|
| 13438 |
}
|
| 13439 |
},
|
| 13440 |
+
"total_flos": 1.3776887037085286e+18,
|
| 13441 |
"train_batch_size": 4,
|
| 13442 |
"trial_name": null,
|
| 13443 |
"trial_params": null
|