Training in progress, step 9160, 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 sha256:7339cbd75ce5d0ebb7fdeea111867e4bdf5eebb4d1a89b63cf840c732975fd8f
|
| 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 sha256:88031ced02c1a0df3dddb89c74658dce1ef33937954f9de56631ef8fb58f7ac9
|
| 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 sha256:185b988928ce9752e701c26e8eb47b1735b446a62880b2b5654e5744a04b1f31
|
| 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,
|
|
@@ -16478,6 +16478,24 @@
|
|
| 16478 |
"mean_token_accuracy": 0.6442059248685836,
|
| 16479 |
"num_tokens": 33371827.0,
|
| 16480 |
"step": 9150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16481 |
}
|
| 16482 |
],
|
| 16483 |
"logging_steps": 5,
|
|
@@ -16497,7 +16515,7 @@
|
|
| 16497 |
"attributes": {}
|
| 16498 |
}
|
| 16499 |
},
|
| 16500 |
-
"total_flos": 1.
|
| 16501 |
"train_batch_size": 4,
|
| 16502 |
"trial_name": null,
|
| 16503 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16478 |
"mean_token_accuracy": 0.6442059248685836,
|
| 16479 |
"num_tokens": 33371827.0,
|
| 16480 |
"step": 9150
|
| 16481 |
+
},
|
| 16482 |
+
{
|
| 16483 |
+
"epoch": 70.42307692307692,
|
| 16484 |
+
"grad_norm": 0.0,
|
| 16485 |
+
"learning_rate": 4.23e-06,
|
| 16486 |
+
"loss": 1.784,
|
| 16487 |
+
"mean_token_accuracy": 0.6425058543682098,
|
| 16488 |
+
"num_tokens": 33390073.0,
|
| 16489 |
+
"step": 9155
|
| 16490 |
+
},
|
| 16491 |
+
{
|
| 16492 |
+
"epoch": 70.46153846153847,
|
| 16493 |
+
"grad_norm": 0.0,
|
| 16494 |
+
"learning_rate": 4.2049999999999996e-06,
|
| 16495 |
+
"loss": 1.8011,
|
| 16496 |
+
"mean_token_accuracy": 0.6376978397369385,
|
| 16497 |
+
"num_tokens": 33408396.0,
|
| 16498 |
+
"step": 9160
|
| 16499 |
}
|
| 16500 |
],
|
| 16501 |
"logging_steps": 5,
|
|
|
|
| 16515 |
"attributes": {}
|
| 16516 |
}
|
| 16517 |
},
|
| 16518 |
+
"total_flos": 1.694021379958702e+18,
|
| 16519 |
"train_batch_size": 4,
|
| 16520 |
"trial_name": null,
|
| 16521 |
"trial_params": null
|