Training in progress, step 9550, 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 sha256:9f65f6b5d648842178993f78826c2eaae4c51527212532d8f22d9bfeef841957
|
| 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 sha256:68a9f82aa727bdc7f524009a292bc887fe51aedd646a3d54a52d96b8b2763e0d
|
| 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 sha256:621129926964f85a06301a3b7f457dd66c4c8a2946ccad58c3afb0e7f0d51602
|
| 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": 73.
|
| 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,
|
|
@@ -17180,6 +17180,24 @@
|
|
| 17180 |
"mean_token_accuracy": 0.6485264748334885,
|
| 17181 |
"num_tokens": 34790801.0,
|
| 17182 |
"step": 9540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17183 |
}
|
| 17184 |
],
|
| 17185 |
"logging_steps": 5,
|
|
@@ -17199,7 +17217,7 @@
|
|
| 17199 |
"attributes": {}
|
| 17200 |
}
|
| 17201 |
},
|
| 17202 |
-
"total_flos": 1.
|
| 17203 |
"train_batch_size": 4,
|
| 17204 |
"trial_name": null,
|
| 17205 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17180 |
"mean_token_accuracy": 0.6485264748334885,
|
| 17181 |
"num_tokens": 34790801.0,
|
| 17182 |
"step": 9540
|
| 17183 |
+
},
|
| 17184 |
+
{
|
| 17185 |
+
"epoch": 73.42307692307692,
|
| 17186 |
+
"grad_norm": 0.0,
|
| 17187 |
+
"learning_rate": 2.28e-06,
|
| 17188 |
+
"loss": 1.7553,
|
| 17189 |
+
"mean_token_accuracy": 0.6497362434864045,
|
| 17190 |
+
"num_tokens": 34808604.0,
|
| 17191 |
+
"step": 9545
|
| 17192 |
+
},
|
| 17193 |
+
{
|
| 17194 |
+
"epoch": 73.46153846153847,
|
| 17195 |
+
"grad_norm": 0.0,
|
| 17196 |
+
"learning_rate": 2.255e-06,
|
| 17197 |
+
"loss": 1.7909,
|
| 17198 |
+
"mean_token_accuracy": 0.639983183145523,
|
| 17199 |
+
"num_tokens": 34826362.0,
|
| 17200 |
+
"step": 9550
|
| 17201 |
}
|
| 17202 |
],
|
| 17203 |
"logging_steps": 5,
|
|
|
|
| 17217 |
"attributes": {}
|
| 17218 |
}
|
| 17219 |
},
|
| 17220 |
+
"total_flos": 1.7660359792941466e+18,
|
| 17221 |
"train_batch_size": 4,
|
| 17222 |
"trial_name": null,
|
| 17223 |
"trial_params": null
|