Training in progress, step 9080, 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 sha256:67cb781e26e48307d5a05f344524efa162f1a3f59401f88257616cb896e96aad
|
| 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 sha256:846b4a4e3b793e8d4036e1fd3f28b8950c62920aebf2bf359a8940a192732825
|
| 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 sha256:4abcba0bb0a64eb186c09a7bed07232030506a8027a1f7b13a5717ee65e81c9b
|
| 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": 69.
|
| 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,
|
|
@@ -16334,6 +16334,24 @@
|
|
| 16334 |
"mean_token_accuracy": 0.6483240693807601,
|
| 16335 |
"num_tokens": 33076529.0,
|
| 16336 |
"step": 9070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16337 |
}
|
| 16338 |
],
|
| 16339 |
"logging_steps": 5,
|
|
@@ -16353,7 +16371,7 @@
|
|
| 16353 |
"attributes": {}
|
| 16354 |
}
|
| 16355 |
},
|
| 16356 |
-
"total_flos": 1.
|
| 16357 |
"train_batch_size": 4,
|
| 16358 |
"trial_name": null,
|
| 16359 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16334 |
"mean_token_accuracy": 0.6483240693807601,
|
| 16335 |
"num_tokens": 33076529.0,
|
| 16336 |
"step": 9070
|
| 16337 |
+
},
|
| 16338 |
+
{
|
| 16339 |
+
"epoch": 69.8076923076923,
|
| 16340 |
+
"grad_norm": 0.0,
|
| 16341 |
+
"learning_rate": 4.6300000000000006e-06,
|
| 16342 |
+
"loss": 1.706,
|
| 16343 |
+
"mean_token_accuracy": 0.6595020055770874,
|
| 16344 |
+
"num_tokens": 33095203.0,
|
| 16345 |
+
"step": 9075
|
| 16346 |
+
},
|
| 16347 |
+
{
|
| 16348 |
+
"epoch": 69.84615384615384,
|
| 16349 |
+
"grad_norm": 0.0,
|
| 16350 |
+
"learning_rate": 4.605e-06,
|
| 16351 |
+
"loss": 1.7031,
|
| 16352 |
+
"mean_token_accuracy": 0.6580096065998078,
|
| 16353 |
+
"num_tokens": 33113524.0,
|
| 16354 |
+
"step": 9080
|
| 16355 |
}
|
| 16356 |
],
|
| 16357 |
"logging_steps": 5,
|
|
|
|
| 16371 |
"attributes": {}
|
| 16372 |
}
|
| 16373 |
},
|
| 16374 |
+
"total_flos": 1.6790751813648384e+18,
|
| 16375 |
"train_batch_size": 4,
|
| 16376 |
"trial_name": null,
|
| 16377 |
"trial_params": null
|