Training in progress, step 8240, 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:a29738b947987347f6fb1f42107e689a870709b5999a2add6a987f9e1bc8c2c6
|
| 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:af9e26dbc40be12c6fc9bd6bd5887564c4b89721cce29794ce705c25d147a295
|
| 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:f0bc47a8a4e87d06ea5cb4c14bbc47223e29c2bbf87212b6a8e4b55ffcbcc55c
|
| 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": 63.
|
| 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,
|
|
@@ -14822,6 +14822,24 @@
|
|
| 14822 |
"mean_token_accuracy": 0.6682954013347626,
|
| 14823 |
"num_tokens": 30015615.0,
|
| 14824 |
"step": 8230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14825 |
}
|
| 14826 |
],
|
| 14827 |
"logging_steps": 5,
|
|
@@ -14841,7 +14859,7 @@
|
|
| 14841 |
"attributes": {}
|
| 14842 |
}
|
| 14843 |
},
|
| 14844 |
-
"total_flos": 1.
|
| 14845 |
"train_batch_size": 4,
|
| 14846 |
"trial_name": null,
|
| 14847 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14822 |
"mean_token_accuracy": 0.6682954013347626,
|
| 14823 |
"num_tokens": 30015615.0,
|
| 14824 |
"step": 8230
|
| 14825 |
+
},
|
| 14826 |
+
{
|
| 14827 |
+
"epoch": 63.34615384615385,
|
| 14828 |
+
"grad_norm": 0.0,
|
| 14829 |
+
"learning_rate": 8.83e-06,
|
| 14830 |
+
"loss": 1.7519,
|
| 14831 |
+
"mean_token_accuracy": 0.6464314192533493,
|
| 14832 |
+
"num_tokens": 30033857.0,
|
| 14833 |
+
"step": 8235
|
| 14834 |
+
},
|
| 14835 |
+
{
|
| 14836 |
+
"epoch": 63.38461538461539,
|
| 14837 |
+
"grad_norm": 0.0,
|
| 14838 |
+
"learning_rate": 8.805000000000001e-06,
|
| 14839 |
+
"loss": 1.8065,
|
| 14840 |
+
"mean_token_accuracy": 0.6360196202993393,
|
| 14841 |
+
"num_tokens": 30051356.0,
|
| 14842 |
+
"step": 8240
|
| 14843 |
}
|
| 14844 |
],
|
| 14845 |
"logging_steps": 5,
|
|
|
|
| 14859 |
"attributes": {}
|
| 14860 |
}
|
| 14861 |
},
|
| 14862 |
+
"total_flos": 1.523733286082642e+18,
|
| 14863 |
"train_batch_size": 4,
|
| 14864 |
"trial_name": null,
|
| 14865 |
"trial_params": null
|