Training in progress, step 8740, 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 sha256:5b895be51ef9e0d5a95ad70177b3ae083c1dd2c1640147b3412a249c29ba2e66
|
| 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:b62dcc06bdc37129d7b79e6324e908681b0707f0fd53f3dd4ab01ba9226b2dab
|
| 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:d323897c0f97b963520fc34c4a29c0d3c5002ee611aab9f21fe652021fd02e11
|
| 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,
|
|
@@ -15722,6 +15722,24 @@
|
|
| 15722 |
"mean_token_accuracy": 0.6472515076398849,
|
| 15723 |
"num_tokens": 31838133.0,
|
| 15724 |
"step": 8730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15725 |
}
|
| 15726 |
],
|
| 15727 |
"logging_steps": 5,
|
|
@@ -15741,7 +15759,7 @@
|
|
| 15741 |
"attributes": {}
|
| 15742 |
}
|
| 15743 |
},
|
| 15744 |
-
"total_flos": 1.
|
| 15745 |
"train_batch_size": 4,
|
| 15746 |
"trial_name": null,
|
| 15747 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15722 |
"mean_token_accuracy": 0.6472515076398849,
|
| 15723 |
"num_tokens": 31838133.0,
|
| 15724 |
"step": 8730
|
| 15725 |
+
},
|
| 15726 |
+
{
|
| 15727 |
+
"epoch": 67.1923076923077,
|
| 15728 |
+
"grad_norm": 0.0,
|
| 15729 |
+
"learning_rate": 6.3299999999999995e-06,
|
| 15730 |
+
"loss": 1.7469,
|
| 15731 |
+
"mean_token_accuracy": 0.6492879390716553,
|
| 15732 |
+
"num_tokens": 31856487.0,
|
| 15733 |
+
"step": 8735
|
| 15734 |
+
},
|
| 15735 |
+
{
|
| 15736 |
+
"epoch": 67.23076923076923,
|
| 15737 |
+
"grad_norm": 0.0,
|
| 15738 |
+
"learning_rate": 6.305e-06,
|
| 15739 |
+
"loss": 1.7255,
|
| 15740 |
+
"mean_token_accuracy": 0.6533631831407547,
|
| 15741 |
+
"num_tokens": 31874474.0,
|
| 15742 |
+
"step": 8740
|
| 15743 |
}
|
| 15744 |
],
|
| 15745 |
"logging_steps": 5,
|
|
|
|
| 15759 |
"attributes": {}
|
| 15760 |
}
|
| 15761 |
},
|
| 15762 |
+
"total_flos": 1.6163066092732416e+18,
|
| 15763 |
"train_batch_size": 4,
|
| 15764 |
"trial_name": null,
|
| 15765 |
"trial_params": null
|