Training in progress, step 4540, 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:f836dae1617856fe50e3905e2eafc826322a91400cc9a5e74cedf241999ed227
|
| 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:b823792a762202ee879b24cdb1f66375b2802a2cbb10b76664f40ec86f2d5e80
|
| 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:e3343732451b2ea643da32d3a6b3f2f866e57b0d7af30aa440a549351e0f1c72
|
| 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": 34.
|
| 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,
|
|
@@ -8162,6 +8162,24 @@
|
|
| 8162 |
"mean_token_accuracy": 0.6642057120800018,
|
| 8163 |
"num_tokens": 16521906.0,
|
| 8164 |
"step": 4530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8165 |
}
|
| 8166 |
],
|
| 8167 |
"logging_steps": 5,
|
|
@@ -8181,7 +8199,7 @@
|
|
| 8181 |
"attributes": {}
|
| 8182 |
}
|
| 8183 |
},
|
| 8184 |
-
"total_flos": 8.
|
| 8185 |
"train_batch_size": 4,
|
| 8186 |
"trial_name": null,
|
| 8187 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8162 |
"mean_token_accuracy": 0.6642057120800018,
|
| 8163 |
"num_tokens": 16521906.0,
|
| 8164 |
"step": 4530
|
| 8165 |
+
},
|
| 8166 |
+
{
|
| 8167 |
+
"epoch": 34.88461538461539,
|
| 8168 |
+
"grad_norm": 0.0,
|
| 8169 |
+
"learning_rate": 2.733e-05,
|
| 8170 |
+
"loss": 1.8207,
|
| 8171 |
+
"mean_token_accuracy": 0.6355377316474915,
|
| 8172 |
+
"num_tokens": 16539170.0,
|
| 8173 |
+
"step": 4535
|
| 8174 |
+
},
|
| 8175 |
+
{
|
| 8176 |
+
"epoch": 34.92307692307692,
|
| 8177 |
+
"grad_norm": 0.0,
|
| 8178 |
+
"learning_rate": 2.7305000000000004e-05,
|
| 8179 |
+
"loss": 1.7629,
|
| 8180 |
+
"mean_token_accuracy": 0.6472138792276383,
|
| 8181 |
+
"num_tokens": 16556927.0,
|
| 8182 |
+
"step": 4540
|
| 8183 |
}
|
| 8184 |
],
|
| 8185 |
"logging_steps": 5,
|
|
|
|
| 8199 |
"attributes": {}
|
| 8200 |
}
|
| 8201 |
},
|
| 8202 |
+
"total_flos": 8.391933574933709e+17,
|
| 8203 |
"train_batch_size": 4,
|
| 8204 |
"trial_name": null,
|
| 8205 |
"trial_params": null
|