Training in progress, step 9570, 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:a691ace7393bbf21511ff094f2ab998c9601177e383701871a558f69fd2edb82
|
| 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 sha256:626e2e5e96f4e3ef6c61a6e066a22f453488106490ada5f824a0c8b1ad5d8bf1
|
| 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:dd78e99d9466a4c68c9fe929858a2879198f4e9ce5b5199f579e218334fa0679
|
| 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,
|
|
@@ -17216,6 +17216,24 @@
|
|
| 17216 |
"mean_token_accuracy": 0.6505734384059906,
|
| 17217 |
"num_tokens": 34863598.0,
|
| 17218 |
"step": 9560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17219 |
}
|
| 17220 |
],
|
| 17221 |
"logging_steps": 5,
|
|
@@ -17235,7 +17253,7 @@
|
|
| 17235 |
"attributes": {}
|
| 17236 |
}
|
| 17237 |
},
|
| 17238 |
-
"total_flos": 1.
|
| 17239 |
"train_batch_size": 4,
|
| 17240 |
"trial_name": null,
|
| 17241 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17216 |
"mean_token_accuracy": 0.6505734384059906,
|
| 17217 |
"num_tokens": 34863598.0,
|
| 17218 |
"step": 9560
|
| 17219 |
+
},
|
| 17220 |
+
{
|
| 17221 |
+
"epoch": 73.57692307692308,
|
| 17222 |
+
"grad_norm": 0.0,
|
| 17223 |
+
"learning_rate": 2.1800000000000003e-06,
|
| 17224 |
+
"loss": 1.7534,
|
| 17225 |
+
"mean_token_accuracy": 0.644753509759903,
|
| 17226 |
+
"num_tokens": 34881884.0,
|
| 17227 |
+
"step": 9565
|
| 17228 |
+
},
|
| 17229 |
+
{
|
| 17230 |
+
"epoch": 73.61538461538461,
|
| 17231 |
+
"grad_norm": 0.0,
|
| 17232 |
+
"learning_rate": 2.155e-06,
|
| 17233 |
+
"loss": 1.7672,
|
| 17234 |
+
"mean_token_accuracy": 0.646284231543541,
|
| 17235 |
+
"num_tokens": 34900082.0,
|
| 17236 |
+
"step": 9570
|
| 17237 |
}
|
| 17238 |
],
|
| 17239 |
"logging_steps": 5,
|
|
|
|
| 17253 |
"attributes": {}
|
| 17254 |
}
|
| 17255 |
},
|
| 17256 |
+
"total_flos": 1.769840327638057e+18,
|
| 17257 |
"train_batch_size": 4,
|
| 17258 |
"trial_name": null,
|
| 17259 |
"trial_params": null
|