Training in progress, step 6680, 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 sha256:62971182c2ea5fa84056721a414e05a4bfc92398d990d0deddd1dec16d223769
|
| 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 sha256:91191836d966ac0d32bab61823fd2be427c4d607cc57454d9fc18a02756f58d4
|
| 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 sha256:85fd475adc7e8355abb2a02aa0a7d5623813b5ce8abfc16834bca8cda95b3576
|
| 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": 51.
|
| 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,
|
|
@@ -12014,6 +12014,24 @@
|
|
| 12014 |
"mean_token_accuracy": 0.6506382346153259,
|
| 12015 |
"num_tokens": 24325111.0,
|
| 12016 |
"step": 6670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12017 |
}
|
| 12018 |
],
|
| 12019 |
"logging_steps": 5,
|
|
@@ -12033,7 +12051,7 @@
|
|
| 12033 |
"attributes": {}
|
| 12034 |
}
|
| 12035 |
},
|
| 12036 |
-
"total_flos": 1.
|
| 12037 |
"train_batch_size": 4,
|
| 12038 |
"trial_name": null,
|
| 12039 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12014 |
"mean_token_accuracy": 0.6506382346153259,
|
| 12015 |
"num_tokens": 24325111.0,
|
| 12016 |
"step": 6670
|
| 12017 |
+
},
|
| 12018 |
+
{
|
| 12019 |
+
"epoch": 51.34615384615385,
|
| 12020 |
+
"grad_norm": 0.0,
|
| 12021 |
+
"learning_rate": 1.6630000000000002e-05,
|
| 12022 |
+
"loss": 1.7607,
|
| 12023 |
+
"mean_token_accuracy": 0.6459864258766175,
|
| 12024 |
+
"num_tokens": 24343133.0,
|
| 12025 |
+
"step": 6675
|
| 12026 |
+
},
|
| 12027 |
+
{
|
| 12028 |
+
"epoch": 51.38461538461539,
|
| 12029 |
+
"grad_norm": 0.0,
|
| 12030 |
+
"learning_rate": 1.6605e-05,
|
| 12031 |
+
"loss": 1.7669,
|
| 12032 |
+
"mean_token_accuracy": 0.6461174368858338,
|
| 12033 |
+
"num_tokens": 24361431.0,
|
| 12034 |
+
"step": 6680
|
| 12035 |
}
|
| 12036 |
],
|
| 12037 |
"logging_steps": 5,
|
|
|
|
| 12051 |
"attributes": {}
|
| 12052 |
}
|
| 12053 |
},
|
| 12054 |
+
"total_flos": 1.2350242117995725e+18,
|
| 12055 |
"train_batch_size": 4,
|
| 12056 |
"trial_name": null,
|
| 12057 |
"trial_params": null
|