Training in progress, step 8480, 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 sha256:38f9a6ee4a5b6d1554bb3cf8208e4c0bec6a32a16cd4e552b31f72b8bcb9cee1
|
| 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:d955d906e39b326839527cf5c9cf16965eef01a95f72d0e2fc8a919a43e3c6a5
|
| 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 sha256:46a00b1b915c5feceec99f88768029e41ace160a9d29e3d4bb99cca407bb72f2
|
| 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": 65.
|
| 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,
|
|
@@ -15254,6 +15254,24 @@
|
|
| 15254 |
"mean_token_accuracy": 0.6444921791553497,
|
| 15255 |
"num_tokens": 30890649.0,
|
| 15256 |
"step": 8470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15257 |
}
|
| 15258 |
],
|
| 15259 |
"logging_steps": 5,
|
|
@@ -15273,7 +15291,7 @@
|
|
| 15273 |
"attributes": {}
|
| 15274 |
}
|
| 15275 |
},
|
| 15276 |
-
"total_flos": 1.
|
| 15277 |
"train_batch_size": 4,
|
| 15278 |
"trial_name": null,
|
| 15279 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15254 |
"mean_token_accuracy": 0.6444921791553497,
|
| 15255 |
"num_tokens": 30890649.0,
|
| 15256 |
"step": 8470
|
| 15257 |
+
},
|
| 15258 |
+
{
|
| 15259 |
+
"epoch": 65.1923076923077,
|
| 15260 |
+
"grad_norm": 0.0,
|
| 15261 |
+
"learning_rate": 7.630000000000001e-06,
|
| 15262 |
+
"loss": 1.708,
|
| 15263 |
+
"mean_token_accuracy": 0.6534979492425919,
|
| 15264 |
+
"num_tokens": 30909370.0,
|
| 15265 |
+
"step": 8475
|
| 15266 |
+
},
|
| 15267 |
+
{
|
| 15268 |
+
"epoch": 65.23076923076923,
|
| 15269 |
+
"grad_norm": 0.0,
|
| 15270 |
+
"learning_rate": 7.605000000000001e-06,
|
| 15271 |
+
"loss": 1.6808,
|
| 15272 |
+
"mean_token_accuracy": 0.667791223526001,
|
| 15273 |
+
"num_tokens": 30928442.0,
|
| 15274 |
+
"step": 8480
|
| 15275 |
}
|
| 15276 |
],
|
| 15277 |
"logging_steps": 5,
|
|
|
|
| 15291 |
"attributes": {}
|
| 15292 |
}
|
| 15293 |
},
|
| 15294 |
+
"total_flos": 1.5681887477843558e+18,
|
| 15295 |
"train_batch_size": 4,
|
| 15296 |
"trial_name": null,
|
| 15297 |
"trial_params": null
|