Training in progress, step 5740, 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 sha256:4c6cd4167bbc9d351d60eb72dedbd1ee94a1e31451901d21dfbf24a3fc2daebf
|
| 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:f18674ab251a5ad7b7689f19ff9a9d7f2d6cb1d93fcf0fdc5b049c67ed19a38a
|
| 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 sha256:5f05c5537472a198c40bc3b119a2b8907109e030f676faeafcac8ffe5e327edc
|
| 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": 44.
|
| 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,
|
|
@@ -10322,6 +10322,24 @@
|
|
| 10322 |
"mean_token_accuracy": 0.6488111823797226,
|
| 10323 |
"num_tokens": 20896892.0,
|
| 10324 |
"step": 5730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10325 |
}
|
| 10326 |
],
|
| 10327 |
"logging_steps": 5,
|
|
@@ -10341,7 +10359,7 @@
|
|
| 10341 |
"attributes": {}
|
| 10342 |
}
|
| 10343 |
},
|
| 10344 |
-
"total_flos": 1.
|
| 10345 |
"train_batch_size": 4,
|
| 10346 |
"trial_name": null,
|
| 10347 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10322 |
"mean_token_accuracy": 0.6488111823797226,
|
| 10323 |
"num_tokens": 20896892.0,
|
| 10324 |
"step": 5730
|
| 10325 |
+
},
|
| 10326 |
+
{
|
| 10327 |
+
"epoch": 44.11538461538461,
|
| 10328 |
+
"grad_norm": 0.0,
|
| 10329 |
+
"learning_rate": 2.133e-05,
|
| 10330 |
+
"loss": 1.8372,
|
| 10331 |
+
"mean_token_accuracy": 0.630810198187828,
|
| 10332 |
+
"num_tokens": 20914256.0,
|
| 10333 |
+
"step": 5735
|
| 10334 |
+
},
|
| 10335 |
+
{
|
| 10336 |
+
"epoch": 44.15384615384615,
|
| 10337 |
+
"grad_norm": 0.0,
|
| 10338 |
+
"learning_rate": 2.1305e-05,
|
| 10339 |
+
"loss": 1.6904,
|
| 10340 |
+
"mean_token_accuracy": 0.6603229939937592,
|
| 10341 |
+
"num_tokens": 20932992.0,
|
| 10342 |
+
"step": 5740
|
| 10343 |
}
|
| 10344 |
],
|
| 10345 |
"logging_steps": 5,
|
|
|
|
| 10359 |
"attributes": {}
|
| 10360 |
}
|
| 10361 |
},
|
| 10362 |
+
"total_flos": 1.0607741018873856e+18,
|
| 10363 |
"train_batch_size": 4,
|
| 10364 |
"trial_name": null,
|
| 10365 |
"trial_params": null
|