Training in progress, step 6810, 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 sha256:33e0375ad05cdce34094c1e588fbf88ac9cd055a5ca7df64c9ef0b1b49e3054a
|
| 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 sha256:3236fdde54d87fff0cd52db953d86bae71a9b99ed8561e2c842ef772f2c72434
|
| 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 sha256:3b8b705b9657da61a1912d11b625b77670e52c5146d3ec58fdaccd112c484683
|
| 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": 52.
|
| 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,
|
|
@@ -12248,6 +12248,24 @@
|
|
| 12248 |
"mean_token_accuracy": 0.6558027982711792,
|
| 12249 |
"num_tokens": 24800571.0,
|
| 12250 |
"step": 6800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12251 |
}
|
| 12252 |
],
|
| 12253 |
"logging_steps": 5,
|
|
@@ -12267,7 +12285,7 @@
|
|
| 12267 |
"attributes": {}
|
| 12268 |
}
|
| 12269 |
},
|
| 12270 |
-
"total_flos": 1.
|
| 12271 |
"train_batch_size": 4,
|
| 12272 |
"trial_name": null,
|
| 12273 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12248 |
"mean_token_accuracy": 0.6558027982711792,
|
| 12249 |
"num_tokens": 24800571.0,
|
| 12250 |
"step": 6800
|
| 12251 |
+
},
|
| 12252 |
+
{
|
| 12253 |
+
"epoch": 52.34615384615385,
|
| 12254 |
+
"grad_norm": 0.0,
|
| 12255 |
+
"learning_rate": 1.598e-05,
|
| 12256 |
+
"loss": 1.7319,
|
| 12257 |
+
"mean_token_accuracy": 0.6475233376026154,
|
| 12258 |
+
"num_tokens": 24818676.0,
|
| 12259 |
+
"step": 6805
|
| 12260 |
+
},
|
| 12261 |
+
{
|
| 12262 |
+
"epoch": 52.38461538461539,
|
| 12263 |
+
"grad_norm": 0.0,
|
| 12264 |
+
"learning_rate": 1.5955e-05,
|
| 12265 |
+
"loss": 1.6884,
|
| 12266 |
+
"mean_token_accuracy": 0.6593423992395401,
|
| 12267 |
+
"num_tokens": 24837669.0,
|
| 12268 |
+
"step": 6810
|
| 12269 |
}
|
| 12270 |
],
|
| 12271 |
"logging_steps": 5,
|
|
|
|
| 12285 |
"attributes": {}
|
| 12286 |
}
|
| 12287 |
},
|
| 12288 |
+
"total_flos": 1.2593417143836672e+18,
|
| 12289 |
"train_batch_size": 4,
|
| 12290 |
"trial_name": null,
|
| 12291 |
"trial_params": null
|