Training in progress, step 6260, 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:f6e0f86a8516e52b8bc2837603e713aa0ec0f2e07957fa0577b3bf1c541dab47
|
| 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:b798ffb93b9c08159c9df3efb664fba8e6016d9924c8ebb7fb02b3ab71c05b7c
|
| 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 sha256:0914a27a6c1a17c6215b091f344c8ef0aaa1e63f915adb6543a0a588e67aab39
|
| 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": 48.
|
| 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,
|
|
@@ -11258,6 +11258,24 @@
|
|
| 11258 |
"mean_token_accuracy": 0.6539857119321824,
|
| 11259 |
"num_tokens": 22793573.0,
|
| 11260 |
"step": 6250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11261 |
}
|
| 11262 |
],
|
| 11263 |
"logging_steps": 5,
|
|
@@ -11277,7 +11295,7 @@
|
|
| 11277 |
"attributes": {}
|
| 11278 |
}
|
| 11279 |
},
|
| 11280 |
-
"total_flos": 1.
|
| 11281 |
"train_batch_size": 4,
|
| 11282 |
"trial_name": null,
|
| 11283 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11258 |
"mean_token_accuracy": 0.6539857119321824,
|
| 11259 |
"num_tokens": 22793573.0,
|
| 11260 |
"step": 6250
|
| 11261 |
+
},
|
| 11262 |
+
{
|
| 11263 |
+
"epoch": 48.11538461538461,
|
| 11264 |
+
"grad_norm": 0.0,
|
| 11265 |
+
"learning_rate": 1.8730000000000002e-05,
|
| 11266 |
+
"loss": 1.7259,
|
| 11267 |
+
"mean_token_accuracy": 0.652483606338501,
|
| 11268 |
+
"num_tokens": 22811965.0,
|
| 11269 |
+
"step": 6255
|
| 11270 |
+
},
|
| 11271 |
+
{
|
| 11272 |
+
"epoch": 48.15384615384615,
|
| 11273 |
+
"grad_norm": 0.0,
|
| 11274 |
+
"learning_rate": 1.8705e-05,
|
| 11275 |
+
"loss": 1.7343,
|
| 11276 |
+
"mean_token_accuracy": 0.6539576113224029,
|
| 11277 |
+
"num_tokens": 22829928.0,
|
| 11278 |
+
"step": 6260
|
| 11279 |
}
|
| 11280 |
],
|
| 11281 |
"logging_steps": 5,
|
|
|
|
| 11295 |
"attributes": {}
|
| 11296 |
}
|
| 11297 |
},
|
| 11298 |
+
"total_flos": 1.1572097278102733e+18,
|
| 11299 |
"train_batch_size": 4,
|
| 11300 |
"trial_name": null,
|
| 11301 |
"trial_params": null
|