Training in progress, step 7740, 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 sha256:6551458f550a52c0ac11a291d264a94aa19fd9ce25f543b3bcdf21cc1da4ffdf
|
| 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:f62f22b353deffd6b01df1c83459b84c7fad69a7f59a1b6aade40571eda898ef
|
| 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:abae4a76910564b50fe9de93e67685e569bf7a68e5c829bd64fcbe135079eecd
|
| 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": 59.
|
| 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,
|
|
@@ -13922,6 +13922,24 @@
|
|
| 13922 |
"mean_token_accuracy": 0.6632986754179001,
|
| 13923 |
"num_tokens": 28191671.0,
|
| 13924 |
"step": 7730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13925 |
}
|
| 13926 |
],
|
| 13927 |
"logging_steps": 5,
|
|
@@ -13941,7 +13959,7 @@
|
|
| 13941 |
"attributes": {}
|
| 13942 |
}
|
| 13943 |
},
|
| 13944 |
-
"total_flos": 1.
|
| 13945 |
"train_batch_size": 4,
|
| 13946 |
"trial_name": null,
|
| 13947 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13922 |
"mean_token_accuracy": 0.6632986754179001,
|
| 13923 |
"num_tokens": 28191671.0,
|
| 13924 |
"step": 7730
|
| 13925 |
+
},
|
| 13926 |
+
{
|
| 13927 |
+
"epoch": 59.5,
|
| 13928 |
+
"grad_norm": 0.0,
|
| 13929 |
+
"learning_rate": 1.133e-05,
|
| 13930 |
+
"loss": 1.7393,
|
| 13931 |
+
"mean_token_accuracy": 0.6471075922250747,
|
| 13932 |
+
"num_tokens": 28210071.0,
|
| 13933 |
+
"step": 7735
|
| 13934 |
+
},
|
| 13935 |
+
{
|
| 13936 |
+
"epoch": 59.53846153846154,
|
| 13937 |
+
"grad_norm": 0.0,
|
| 13938 |
+
"learning_rate": 1.1305000000000001e-05,
|
| 13939 |
+
"loss": 1.7713,
|
| 13940 |
+
"mean_token_accuracy": 0.6440162390470505,
|
| 13941 |
+
"num_tokens": 28227999.0,
|
| 13942 |
+
"step": 7740
|
| 13943 |
}
|
| 13944 |
],
|
| 13945 |
"logging_steps": 5,
|
|
|
|
| 13959 |
"attributes": {}
|
| 13960 |
}
|
| 13961 |
},
|
| 13962 |
+
"total_flos": 1.4312955602829312e+18,
|
| 13963 |
"train_batch_size": 4,
|
| 13964 |
"trial_name": null,
|
| 13965 |
"trial_params": null
|