Training in progress, step 6490, 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 sha256:5b3036d7fc58fe25bac17f00de8d1e388069de3106e1a52946a50e8a6b4bbec1
|
| 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 sha256:9f9466ed8086fd06526a9d084ac86b69a7bb752d2ea14c44e5b874f7e86d993e
|
| 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 sha256:664a2e94f9fe9c103bc68765ea336f3e9f1d123f17e3d487e3d97a930f35c58c
|
| 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": 49.
|
| 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,
|
|
@@ -11672,6 +11672,24 @@
|
|
| 11672 |
"mean_token_accuracy": 0.6497550249099732,
|
| 11673 |
"num_tokens": 23632333.0,
|
| 11674 |
"step": 6480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11675 |
}
|
| 11676 |
],
|
| 11677 |
"logging_steps": 5,
|
|
@@ -11691,7 +11709,7 @@
|
|
| 11691 |
"attributes": {}
|
| 11692 |
}
|
| 11693 |
},
|
| 11694 |
-
"total_flos": 1.
|
| 11695 |
"train_batch_size": 4,
|
| 11696 |
"trial_name": null,
|
| 11697 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11672 |
"mean_token_accuracy": 0.6497550249099732,
|
| 11673 |
"num_tokens": 23632333.0,
|
| 11674 |
"step": 6480
|
| 11675 |
+
},
|
| 11676 |
+
{
|
| 11677 |
+
"epoch": 49.88461538461539,
|
| 11678 |
+
"grad_norm": 0.0,
|
| 11679 |
+
"learning_rate": 1.758e-05,
|
| 11680 |
+
"loss": 1.6955,
|
| 11681 |
+
"mean_token_accuracy": 0.6517337173223495,
|
| 11682 |
+
"num_tokens": 23651103.0,
|
| 11683 |
+
"step": 6485
|
| 11684 |
+
},
|
| 11685 |
+
{
|
| 11686 |
+
"epoch": 49.92307692307692,
|
| 11687 |
+
"grad_norm": 0.0,
|
| 11688 |
+
"learning_rate": 1.7555e-05,
|
| 11689 |
+
"loss": 1.7078,
|
| 11690 |
+
"mean_token_accuracy": 0.6560462713241577,
|
| 11691 |
+
"num_tokens": 23669731.0,
|
| 11692 |
+
"step": 6490
|
| 11693 |
}
|
| 11694 |
],
|
| 11695 |
"logging_steps": 5,
|
|
|
|
| 11709 |
"attributes": {}
|
| 11710 |
}
|
| 11711 |
},
|
| 11712 |
+
"total_flos": 1.1999579961316147e+18,
|
| 11713 |
"train_batch_size": 4,
|
| 11714 |
"trial_name": null,
|
| 11715 |
"trial_params": null
|