Training in progress, step 7010, 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:cd9eaec5568ba35297d811fb9e9220666b8921cca8c16276738fa8e834fcc9aa
|
| 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 sha256:3028f40189dc8c23966733a64c9bc99718ef4b0859df8ce8e5ccb50df01d7cc3
|
| 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 sha256:4fe72f33bfe06c542c1101591e2f4ea05f7f758c8eda93a6db82f5e24cf47d7e
|
| 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": 53.
|
| 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,
|
|
@@ -12608,6 +12608,24 @@
|
|
| 12608 |
"mean_token_accuracy": 0.646448740363121,
|
| 12609 |
"num_tokens": 25528517.0,
|
| 12610 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12611 |
}
|
| 12612 |
],
|
| 12613 |
"logging_steps": 5,
|
|
@@ -12627,7 +12645,7 @@
|
|
| 12627 |
"attributes": {}
|
| 12628 |
}
|
| 12629 |
},
|
| 12630 |
-
"total_flos": 1.
|
| 12631 |
"train_batch_size": 4,
|
| 12632 |
"trial_name": null,
|
| 12633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12608 |
"mean_token_accuracy": 0.646448740363121,
|
| 12609 |
"num_tokens": 25528517.0,
|
| 12610 |
"step": 7000
|
| 12611 |
+
},
|
| 12612 |
+
{
|
| 12613 |
+
"epoch": 53.88461538461539,
|
| 12614 |
+
"grad_norm": 0.0,
|
| 12615 |
+
"learning_rate": 1.4979999999999999e-05,
|
| 12616 |
+
"loss": 1.8031,
|
| 12617 |
+
"mean_token_accuracy": 0.6375834941864014,
|
| 12618 |
+
"num_tokens": 25546409.0,
|
| 12619 |
+
"step": 7005
|
| 12620 |
+
},
|
| 12621 |
+
{
|
| 12622 |
+
"epoch": 53.92307692307692,
|
| 12623 |
+
"grad_norm": 0.0,
|
| 12624 |
+
"learning_rate": 1.4955e-05,
|
| 12625 |
+
"loss": 1.7659,
|
| 12626 |
+
"mean_token_accuracy": 0.6465475499629975,
|
| 12627 |
+
"num_tokens": 25564683.0,
|
| 12628 |
+
"step": 7010
|
| 12629 |
}
|
| 12630 |
],
|
| 12631 |
"logging_steps": 5,
|
|
|
|
| 12645 |
"attributes": {}
|
| 12646 |
}
|
| 12647 |
},
|
| 12648 |
+
"total_flos": 1.2961806992193946e+18,
|
| 12649 |
"train_batch_size": 4,
|
| 12650 |
"trial_name": null,
|
| 12651 |
"trial_params": null
|