Training in progress, step 3890, 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 sha256:3c25e56beabf6a33a9c78124b7feb92b47c3f994d64913a7717ba7fc9b4a0874
|
| 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 sha256:35af19ed997d00507c1049a06c2624156c5b65ca90e7f437aeff682cc815e246
|
| 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:cf958940609e1bb6907345ebf2996163371c99afd9495188d13b07db711cc32e
|
| 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": 29.
|
| 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,
|
|
@@ -6992,6 +6992,24 @@
|
|
| 6992 |
"mean_token_accuracy": 0.6389037370681763,
|
| 6993 |
"num_tokens": 14150572.0,
|
| 6994 |
"step": 3880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6995 |
}
|
| 6996 |
],
|
| 6997 |
"logging_steps": 5,
|
|
@@ -7011,7 +7029,7 @@
|
|
| 7011 |
"attributes": {}
|
| 7012 |
}
|
| 7013 |
},
|
| 7014 |
-
"total_flos": 7.
|
| 7015 |
"train_batch_size": 4,
|
| 7016 |
"trial_name": null,
|
| 7017 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6992 |
"mean_token_accuracy": 0.6389037370681763,
|
| 6993 |
"num_tokens": 14150572.0,
|
| 6994 |
"step": 3880
|
| 6995 |
+
},
|
| 6996 |
+
{
|
| 6997 |
+
"epoch": 29.884615384615383,
|
| 6998 |
+
"grad_norm": 0.0,
|
| 6999 |
+
"learning_rate": 3.058e-05,
|
| 7000 |
+
"loss": 1.786,
|
| 7001 |
+
"mean_token_accuracy": 0.6433692693710327,
|
| 7002 |
+
"num_tokens": 14168515.0,
|
| 7003 |
+
"step": 3885
|
| 7004 |
+
},
|
| 7005 |
+
{
|
| 7006 |
+
"epoch": 29.923076923076923,
|
| 7007 |
+
"grad_norm": 0.0,
|
| 7008 |
+
"learning_rate": 3.0555e-05,
|
| 7009 |
+
"loss": 1.8269,
|
| 7010 |
+
"mean_token_accuracy": 0.6312504172325134,
|
| 7011 |
+
"num_tokens": 14185905.0,
|
| 7012 |
+
"step": 3890
|
| 7013 |
}
|
| 7014 |
],
|
| 7015 |
"logging_steps": 5,
|
|
|
|
| 7029 |
"attributes": {}
|
| 7030 |
}
|
| 7031 |
},
|
| 7032 |
+
"total_flos": 7.188319371401626e+17,
|
| 7033 |
"train_batch_size": 4,
|
| 7034 |
"trial_name": null,
|
| 7035 |
"trial_params": null
|