Training in progress, step 7440, 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 sha256:5fad7e863cb141436abcef8b4d760f47827f2b211697ec34507e3e8e665b8187
|
| 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:b3a562f104b1362f4505b57dc00abd841b9af6a5c529c12a870b35af89f28abd
|
| 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 sha256:9b3a642cce88c572ab6b15a59c6c894e485a93aae98aa64dc84df89772043556
|
| 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,
|
|
@@ -13382,6 +13382,24 @@
|
|
| 13382 |
"mean_token_accuracy": 0.6547515660524368,
|
| 13383 |
"num_tokens": 27097554.0,
|
| 13384 |
"step": 7430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13385 |
}
|
| 13386 |
],
|
| 13387 |
"logging_steps": 5,
|
|
@@ -13401,7 +13419,7 @@
|
|
| 13401 |
"attributes": {}
|
| 13402 |
}
|
| 13403 |
},
|
| 13404 |
-
"total_flos": 1.
|
| 13405 |
"train_batch_size": 4,
|
| 13406 |
"trial_name": null,
|
| 13407 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13382 |
"mean_token_accuracy": 0.6547515660524368,
|
| 13383 |
"num_tokens": 27097554.0,
|
| 13384 |
"step": 7430
|
| 13385 |
+
},
|
| 13386 |
+
{
|
| 13387 |
+
"epoch": 57.19230769230769,
|
| 13388 |
+
"grad_norm": 0.0,
|
| 13389 |
+
"learning_rate": 1.283e-05,
|
| 13390 |
+
"loss": 1.7108,
|
| 13391 |
+
"mean_token_accuracy": 0.6577676206827163,
|
| 13392 |
+
"num_tokens": 27116052.0,
|
| 13393 |
+
"step": 7435
|
| 13394 |
+
},
|
| 13395 |
+
{
|
| 13396 |
+
"epoch": 57.23076923076923,
|
| 13397 |
+
"grad_norm": 0.0,
|
| 13398 |
+
"learning_rate": 1.2805e-05,
|
| 13399 |
+
"loss": 1.7134,
|
| 13400 |
+
"mean_token_accuracy": 0.6552876085042953,
|
| 13401 |
+
"num_tokens": 27134390.0,
|
| 13402 |
+
"step": 7440
|
| 13403 |
}
|
| 13404 |
],
|
| 13405 |
"logging_steps": 5,
|
|
|
|
| 13419 |
"attributes": {}
|
| 13420 |
}
|
| 13421 |
},
|
| 13422 |
+
"total_flos": 1.3757754149963366e+18,
|
| 13423 |
"train_batch_size": 4,
|
| 13424 |
"trial_name": null,
|
| 13425 |
"trial_params": null
|