Training in progress, step 6340, 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 sha256:314fa9751b5006d73b2c18923477e611aa217a96ffa3b10e73ebbb8cb7538aee
|
| 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 sha256:8954dfa299dd9378272820a395f74acbecae9ca2e952767f641674f21ce79824
|
| 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:c3eae83ec30d6de14812a339aff25b5fc817bc1593556c9ad14317c689f43b8a
|
| 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,
|
|
@@ -11402,6 +11402,24 @@
|
|
| 11402 |
"mean_token_accuracy": 0.6510752677917481,
|
| 11403 |
"num_tokens": 23083562.0,
|
| 11404 |
"step": 6330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11405 |
}
|
| 11406 |
],
|
| 11407 |
"logging_steps": 5,
|
|
@@ -11421,7 +11439,7 @@
|
|
| 11421 |
"attributes": {}
|
| 11422 |
}
|
| 11423 |
},
|
| 11424 |
-
"total_flos": 1.
|
| 11425 |
"train_batch_size": 4,
|
| 11426 |
"trial_name": null,
|
| 11427 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11402 |
"mean_token_accuracy": 0.6510752677917481,
|
| 11403 |
"num_tokens": 23083562.0,
|
| 11404 |
"step": 6330
|
| 11405 |
+
},
|
| 11406 |
+
{
|
| 11407 |
+
"epoch": 48.73076923076923,
|
| 11408 |
+
"grad_norm": 0.0,
|
| 11409 |
+
"learning_rate": 1.833e-05,
|
| 11410 |
+
"loss": 1.7406,
|
| 11411 |
+
"mean_token_accuracy": 0.6523085534572601,
|
| 11412 |
+
"num_tokens": 23101646.0,
|
| 11413 |
+
"step": 6335
|
| 11414 |
+
},
|
| 11415 |
+
{
|
| 11416 |
+
"epoch": 48.76923076923077,
|
| 11417 |
+
"grad_norm": 0.0,
|
| 11418 |
+
"learning_rate": 1.8305e-05,
|
| 11419 |
+
"loss": 1.7408,
|
| 11420 |
+
"mean_token_accuracy": 0.6524953216314315,
|
| 11421 |
+
"num_tokens": 23120020.0,
|
| 11422 |
+
"step": 6340
|
| 11423 |
}
|
| 11424 |
],
|
| 11425 |
"logging_steps": 5,
|
|
|
|
| 11439 |
"attributes": {}
|
| 11440 |
}
|
| 11441 |
},
|
| 11442 |
+
"total_flos": 1.1719914312086323e+18,
|
| 11443 |
"train_batch_size": 4,
|
| 11444 |
"trial_name": null,
|
| 11445 |
"trial_params": null
|