Training in progress, step 7040, 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 sha256:84eae31993b922bb31e99ffad96aec1111994460c45fc00d44c541e01a210249
|
| 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:af1819f1ef5a1dd440bfcc754cbda311f2ec25b32b723850751c692775a2c92a
|
| 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:afdf2c56637f91ccd43c57d06948fee77b3fa930715c1dc91866b1c1c2de1208
|
| 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": 54.
|
| 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,
|
|
@@ -12662,6 +12662,24 @@
|
|
| 12662 |
"mean_token_accuracy": 0.6386265754699707,
|
| 12663 |
"num_tokens": 25637942.0,
|
| 12664 |
"step": 7030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12665 |
}
|
| 12666 |
],
|
| 12667 |
"logging_steps": 5,
|
|
@@ -12681,7 +12699,7 @@
|
|
| 12681 |
"attributes": {}
|
| 12682 |
}
|
| 12683 |
},
|
| 12684 |
-
"total_flos": 1.
|
| 12685 |
"train_batch_size": 4,
|
| 12686 |
"trial_name": null,
|
| 12687 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12662 |
"mean_token_accuracy": 0.6386265754699707,
|
| 12663 |
"num_tokens": 25637942.0,
|
| 12664 |
"step": 7030
|
| 12665 |
+
},
|
| 12666 |
+
{
|
| 12667 |
+
"epoch": 54.11538461538461,
|
| 12668 |
+
"grad_norm": 0.0,
|
| 12669 |
+
"learning_rate": 1.4829999999999999e-05,
|
| 12670 |
+
"loss": 1.6514,
|
| 12671 |
+
"mean_token_accuracy": 0.6691981256008148,
|
| 12672 |
+
"num_tokens": 25656864.0,
|
| 12673 |
+
"step": 7035
|
| 12674 |
+
},
|
| 12675 |
+
{
|
| 12676 |
+
"epoch": 54.15384615384615,
|
| 12677 |
+
"grad_norm": 0.0,
|
| 12678 |
+
"learning_rate": 1.4805e-05,
|
| 12679 |
+
"loss": 1.7832,
|
| 12680 |
+
"mean_token_accuracy": 0.6411665648221969,
|
| 12681 |
+
"num_tokens": 25675005.0,
|
| 12682 |
+
"step": 7040
|
| 12683 |
}
|
| 12684 |
],
|
| 12685 |
"logging_steps": 5,
|
|
|
|
| 12699 |
"attributes": {}
|
| 12700 |
}
|
| 12701 |
},
|
| 12702 |
+
"total_flos": 1.301818946702377e+18,
|
| 12703 |
"train_batch_size": 4,
|
| 12704 |
"trial_name": null,
|
| 12705 |
"trial_params": null
|