Training in progress, step 7230, 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 sha256:4cd9e62b71dec1a66a86f6b4aec5bb531aa957b5c0f96236b1b459280c939380
|
| 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 sha256:832a6ed871b8e8be3cb42689b67316679e8b1c3bd8260f4d47b88474ad22210a
|
| 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 sha256:5c4eaec0ddaf90c1d81a1e519f9a19f84b2c35e7b3750c354c17651fa1df97d4
|
| 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": 55.
|
| 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,
|
|
@@ -13004,6 +13004,24 @@
|
|
| 13004 |
"mean_token_accuracy": 0.6529065489768981,
|
| 13005 |
"num_tokens": 26329504.0,
|
| 13006 |
"step": 7220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13007 |
}
|
| 13008 |
],
|
| 13009 |
"logging_steps": 5,
|
|
@@ -13023,7 +13041,7 @@
|
|
| 13023 |
"attributes": {}
|
| 13024 |
}
|
| 13025 |
},
|
| 13026 |
-
"total_flos": 1.
|
| 13027 |
"train_batch_size": 4,
|
| 13028 |
"trial_name": null,
|
| 13029 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13004 |
"mean_token_accuracy": 0.6529065489768981,
|
| 13005 |
"num_tokens": 26329504.0,
|
| 13006 |
"step": 7220
|
| 13007 |
+
},
|
| 13008 |
+
{
|
| 13009 |
+
"epoch": 55.57692307692308,
|
| 13010 |
+
"grad_norm": 0.0,
|
| 13011 |
+
"learning_rate": 1.3880000000000001e-05,
|
| 13012 |
+
"loss": 1.6938,
|
| 13013 |
+
"mean_token_accuracy": 0.6577755719423294,
|
| 13014 |
+
"num_tokens": 26348129.0,
|
| 13015 |
+
"step": 7225
|
| 13016 |
+
},
|
| 13017 |
+
{
|
| 13018 |
+
"epoch": 55.61538461538461,
|
| 13019 |
+
"grad_norm": 0.0,
|
| 13020 |
+
"learning_rate": 1.3855000000000002e-05,
|
| 13021 |
+
"loss": 1.7149,
|
| 13022 |
+
"mean_token_accuracy": 0.6628178864717483,
|
| 13023 |
+
"num_tokens": 26366596.0,
|
| 13024 |
+
"step": 7230
|
| 13025 |
}
|
| 13026 |
],
|
| 13027 |
"logging_steps": 5,
|
|
|
|
| 13041 |
"attributes": {}
|
| 13042 |
}
|
| 13043 |
},
|
| 13044 |
+
"total_flos": 1.3369472450165146e+18,
|
| 13045 |
"train_batch_size": 4,
|
| 13046 |
"trial_name": null,
|
| 13047 |
"trial_params": null
|