Training in progress, step 9170, 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 sha256:17b05179e57234b02df44f8a5e5f831dd3a8da4c48f189d01555e27d6374b817
|
| 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 sha256:3e48a3cff503bac9d82c112f2d52dce7616eb324d96e07c488be69cccc7ed6b6
|
| 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 sha256:80207c6ccbea7ac956d5b4f465e712b31f70a63e8a992e40b533033094ee441e
|
| 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": 70.
|
| 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,
|
|
@@ -16496,6 +16496,24 @@
|
|
| 16496 |
"mean_token_accuracy": 0.6376978397369385,
|
| 16497 |
"num_tokens": 33408396.0,
|
| 16498 |
"step": 9160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16499 |
}
|
| 16500 |
],
|
| 16501 |
"logging_steps": 5,
|
|
@@ -16515,7 +16533,7 @@
|
|
| 16515 |
"attributes": {}
|
| 16516 |
}
|
| 16517 |
},
|
| 16518 |
-
"total_flos": 1.
|
| 16519 |
"train_batch_size": 4,
|
| 16520 |
"trial_name": null,
|
| 16521 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16496 |
"mean_token_accuracy": 0.6376978397369385,
|
| 16497 |
"num_tokens": 33408396.0,
|
| 16498 |
"step": 9160
|
| 16499 |
+
},
|
| 16500 |
+
{
|
| 16501 |
+
"epoch": 70.5,
|
| 16502 |
+
"grad_norm": 0.0,
|
| 16503 |
+
"learning_rate": 4.18e-06,
|
| 16504 |
+
"loss": 1.7991,
|
| 16505 |
+
"mean_token_accuracy": 0.6374391674995422,
|
| 16506 |
+
"num_tokens": 33425771.0,
|
| 16507 |
+
"step": 9165
|
| 16508 |
+
},
|
| 16509 |
+
{
|
| 16510 |
+
"epoch": 70.53846153846153,
|
| 16511 |
+
"grad_norm": 0.0,
|
| 16512 |
+
"learning_rate": 4.155e-06,
|
| 16513 |
+
"loss": 1.8244,
|
| 16514 |
+
"mean_token_accuracy": 0.6361591160297394,
|
| 16515 |
+
"num_tokens": 33443218.0,
|
| 16516 |
+
"step": 9170
|
| 16517 |
}
|
| 16518 |
],
|
| 16519 |
"logging_steps": 5,
|
|
|
|
| 16533 |
"attributes": {}
|
| 16534 |
}
|
| 16535 |
},
|
| 16536 |
+
"total_flos": 1.69578112923648e+18,
|
| 16537 |
"train_batch_size": 4,
|
| 16538 |
"trial_name": null,
|
| 16539 |
"trial_params": null
|