Training in progress, step 3980, 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:d5e869f37d6541b0cd5c5e839e1564eb9561678a55a38d85912f24b8709ea00d
|
| 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:e58631b16fd77ac6bf41916baf3fdf3eef7a8946ff0be4e067d141475c239f26
|
| 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 sha256:7382c8d5705e947e049c459fa10d49ac38c8898bcd35cc73b959ec503040e86e
|
| 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": 30.
|
| 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,
|
|
@@ -7154,6 +7154,24 @@
|
|
| 7154 |
"mean_token_accuracy": 0.6505941689014435,
|
| 7155 |
"num_tokens": 14479670.0,
|
| 7156 |
"step": 3970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7157 |
}
|
| 7158 |
],
|
| 7159 |
"logging_steps": 5,
|
|
@@ -7173,7 +7191,7 @@
|
|
| 7173 |
"attributes": {}
|
| 7174 |
}
|
| 7175 |
},
|
| 7176 |
-
"total_flos": 7.
|
| 7177 |
"train_batch_size": 4,
|
| 7178 |
"trial_name": null,
|
| 7179 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7154 |
"mean_token_accuracy": 0.6505941689014435,
|
| 7155 |
"num_tokens": 14479670.0,
|
| 7156 |
"step": 3970
|
| 7157 |
+
},
|
| 7158 |
+
{
|
| 7159 |
+
"epoch": 30.576923076923077,
|
| 7160 |
+
"grad_norm": 0.0,
|
| 7161 |
+
"learning_rate": 3.013e-05,
|
| 7162 |
+
"loss": 1.7947,
|
| 7163 |
+
"mean_token_accuracy": 0.6404198050498963,
|
| 7164 |
+
"num_tokens": 14497368.0,
|
| 7165 |
+
"step": 3975
|
| 7166 |
+
},
|
| 7167 |
+
{
|
| 7168 |
+
"epoch": 30.615384615384617,
|
| 7169 |
+
"grad_norm": 0.0,
|
| 7170 |
+
"learning_rate": 3.0105e-05,
|
| 7171 |
+
"loss": 1.7593,
|
| 7172 |
+
"mean_token_accuracy": 0.644034668803215,
|
| 7173 |
+
"num_tokens": 14515634.0,
|
| 7174 |
+
"step": 3980
|
| 7175 |
}
|
| 7176 |
],
|
| 7177 |
"logging_steps": 5,
|
|
|
|
| 7191 |
"attributes": {}
|
| 7192 |
}
|
| 7193 |
},
|
| 7194 |
+
"total_flos": 7.356942824708506e+17,
|
| 7195 |
"train_batch_size": 4,
|
| 7196 |
"trial_name": null,
|
| 7197 |
"trial_params": null
|