Training in progress, step 7130, 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 sha256:954c9830e5f9b815ec88a9f4cf4875d1a826e157be6199ee97e180fa09ce4002
|
| 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:e353c387c15fce1b47b3548fac3491591f714c5a41ab1c327bc4789b00ffe1c1
|
| 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 sha256:00b67ba286c8fa19cdcea5b5aabe4c4d8823553346d666e93b109773dda1f792
|
| 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,
|
|
@@ -12824,6 +12824,24 @@
|
|
| 12824 |
"mean_token_accuracy": 0.6535341709852218,
|
| 12825 |
"num_tokens": 25967346.0,
|
| 12826 |
"step": 7120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12827 |
}
|
| 12828 |
],
|
| 12829 |
"logging_steps": 5,
|
|
@@ -12843,7 +12861,7 @@
|
|
| 12843 |
"attributes": {}
|
| 12844 |
}
|
| 12845 |
},
|
| 12846 |
-
"total_flos": 1.
|
| 12847 |
"train_batch_size": 4,
|
| 12848 |
"trial_name": null,
|
| 12849 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 54.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12824 |
"mean_token_accuracy": 0.6535341709852218,
|
| 12825 |
"num_tokens": 25967346.0,
|
| 12826 |
"step": 7120
|
| 12827 |
+
},
|
| 12828 |
+
{
|
| 12829 |
+
"epoch": 54.80769230769231,
|
| 12830 |
+
"grad_norm": 0.0,
|
| 12831 |
+
"learning_rate": 1.4380000000000001e-05,
|
| 12832 |
+
"loss": 1.7919,
|
| 12833 |
+
"mean_token_accuracy": 0.6459776431322097,
|
| 12834 |
+
"num_tokens": 25984246.0,
|
| 12835 |
+
"step": 7125
|
| 12836 |
+
},
|
| 12837 |
+
{
|
| 12838 |
+
"epoch": 54.84615384615385,
|
| 12839 |
+
"grad_norm": 0.0,
|
| 12840 |
+
"learning_rate": 1.4355000000000002e-05,
|
| 12841 |
+
"loss": 1.6747,
|
| 12842 |
+
"mean_token_accuracy": 0.6653303891420365,
|
| 12843 |
+
"num_tokens": 26003170.0,
|
| 12844 |
+
"step": 7130
|
| 12845 |
}
|
| 12846 |
],
|
| 12847 |
"logging_steps": 5,
|
|
|
|
| 12861 |
"attributes": {}
|
| 12862 |
}
|
| 12863 |
},
|
| 12864 |
+
"total_flos": 1.3185175907332915e+18,
|
| 12865 |
"train_batch_size": 4,
|
| 12866 |
"trial_name": null,
|
| 12867 |
"trial_params": null
|