Training in progress, step 8730, 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 sha256:97476721a5f94ea1e72933b5b20763169ed4b2f4ed788074c62459af4e443a05
|
| 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:b843d3e88ea4a9fb033f6b1ae07d36fbd1418129bdeefeda846a41ef962d99ae
|
| 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 sha256:5ba69d7a87c25237c21ce8fc6ece5016ba45a64d751578db12e1562e60c93d68
|
| 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": 67.
|
| 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,
|
|
@@ -15704,6 +15704,24 @@
|
|
| 15704 |
"mean_token_accuracy": 0.6550649493932724,
|
| 15705 |
"num_tokens": 31801583.0,
|
| 15706 |
"step": 8720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15707 |
}
|
| 15708 |
],
|
| 15709 |
"logging_steps": 5,
|
|
@@ -15723,7 +15741,7 @@
|
|
| 15723 |
"attributes": {}
|
| 15724 |
}
|
| 15725 |
},
|
| 15726 |
-
"total_flos": 1.
|
| 15727 |
"train_batch_size": 4,
|
| 15728 |
"trial_name": null,
|
| 15729 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15704 |
"mean_token_accuracy": 0.6550649493932724,
|
| 15705 |
"num_tokens": 31801583.0,
|
| 15706 |
"step": 8720
|
| 15707 |
+
},
|
| 15708 |
+
{
|
| 15709 |
+
"epoch": 67.11538461538461,
|
| 15710 |
+
"grad_norm": 0.0,
|
| 15711 |
+
"learning_rate": 6.38e-06,
|
| 15712 |
+
"loss": 1.7363,
|
| 15713 |
+
"mean_token_accuracy": 0.6507348865270615,
|
| 15714 |
+
"num_tokens": 31819899.0,
|
| 15715 |
+
"step": 8725
|
| 15716 |
+
},
|
| 15717 |
+
{
|
| 15718 |
+
"epoch": 67.15384615384616,
|
| 15719 |
+
"grad_norm": 0.0,
|
| 15720 |
+
"learning_rate": 6.355e-06,
|
| 15721 |
+
"loss": 1.7462,
|
| 15722 |
+
"mean_token_accuracy": 0.6472515076398849,
|
| 15723 |
+
"num_tokens": 31838133.0,
|
| 15724 |
+
"step": 8730
|
| 15725 |
}
|
| 15726 |
],
|
| 15727 |
"logging_steps": 5,
|
|
|
|
| 15741 |
"attributes": {}
|
| 15742 |
}
|
| 15743 |
},
|
| 15744 |
+
"total_flos": 1.6144852536867226e+18,
|
| 15745 |
"train_batch_size": 4,
|
| 15746 |
"trial_name": null,
|
| 15747 |
"trial_params": null
|