Training in progress, step 8720, 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 sha256:484ad73985382db4c9cb1b1c5991b0526e986c2fe1fa071438c60255dabfca51
|
| 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 sha256:94ad13d7cdf1d4a56ae9cca321d28096513933f63745a364693cdd93cc783475
|
| 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 sha256:0569ded7963f2d6c8392959ce77675e96bab5d6bfbd1b463ff8bafc27693b41e
|
| 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,
|
|
@@ -15686,6 +15686,24 @@
|
|
| 15686 |
"mean_token_accuracy": 0.6641561448574066,
|
| 15687 |
"num_tokens": 31765035.0,
|
| 15688 |
"step": 8710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15689 |
}
|
| 15690 |
],
|
| 15691 |
"logging_steps": 5,
|
|
@@ -15705,7 +15723,7 @@
|
|
| 15705 |
"attributes": {}
|
| 15706 |
}
|
| 15707 |
},
|
| 15708 |
-
"total_flos": 1.
|
| 15709 |
"train_batch_size": 4,
|
| 15710 |
"trial_name": null,
|
| 15711 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15686 |
"mean_token_accuracy": 0.6641561448574066,
|
| 15687 |
"num_tokens": 31765035.0,
|
| 15688 |
"step": 8710
|
| 15689 |
+
},
|
| 15690 |
+
{
|
| 15691 |
+
"epoch": 67.03846153846153,
|
| 15692 |
+
"grad_norm": 0.0,
|
| 15693 |
+
"learning_rate": 6.43e-06,
|
| 15694 |
+
"loss": 1.754,
|
| 15695 |
+
"mean_token_accuracy": 0.6518040865659713,
|
| 15696 |
+
"num_tokens": 31783454.0,
|
| 15697 |
+
"step": 8715
|
| 15698 |
+
},
|
| 15699 |
+
{
|
| 15700 |
+
"epoch": 67.07692307692308,
|
| 15701 |
+
"grad_norm": 0.0,
|
| 15702 |
+
"learning_rate": 6.405e-06,
|
| 15703 |
+
"loss": 1.7343,
|
| 15704 |
+
"mean_token_accuracy": 0.6550649493932724,
|
| 15705 |
+
"num_tokens": 31801583.0,
|
| 15706 |
+
"step": 8720
|
| 15707 |
}
|
| 15708 |
],
|
| 15709 |
"logging_steps": 5,
|
|
|
|
| 15723 |
"attributes": {}
|
| 15724 |
}
|
| 15725 |
},
|
| 15726 |
+
"total_flos": 1.6125721237536768e+18,
|
| 15727 |
"train_batch_size": 4,
|
| 15728 |
"trial_name": null,
|
| 15729 |
"trial_params": null
|