Training in progress, step 7710, 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 sha256:049a1f0b0d0eb17b070dc5de80f82420319fd1a0d377d4ee7e96aa6f9d86529f
|
| 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 sha256:4aab93e89d0a16aa2a12d865bac844e3b963348aead2f2c9603101d42eaa2022
|
| 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 sha256:8cd51ef1f4d57df04f6f9faac95433b3a77e7e6792f67cb95f2761fea08e95d9
|
| 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,
|
|
@@ -13868,6 +13868,24 @@
|
|
| 13868 |
"mean_token_accuracy": 0.665479126572609,
|
| 13869 |
"num_tokens": 28081357.0,
|
| 13870 |
"step": 7700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13871 |
}
|
| 13872 |
],
|
| 13873 |
"logging_steps": 5,
|
|
@@ -13887,7 +13905,7 @@
|
|
| 13887 |
"attributes": {}
|
| 13888 |
}
|
| 13889 |
},
|
| 13890 |
-
"total_flos": 1.
|
| 13891 |
"train_batch_size": 4,
|
| 13892 |
"trial_name": null,
|
| 13893 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13868 |
"mean_token_accuracy": 0.665479126572609,
|
| 13869 |
"num_tokens": 28081357.0,
|
| 13870 |
"step": 7700
|
| 13871 |
+
},
|
| 13872 |
+
{
|
| 13873 |
+
"epoch": 59.26923076923077,
|
| 13874 |
+
"grad_norm": 0.0,
|
| 13875 |
+
"learning_rate": 1.148e-05,
|
| 13876 |
+
"loss": 1.6759,
|
| 13877 |
+
"mean_token_accuracy": 0.6660502076148986,
|
| 13878 |
+
"num_tokens": 28099996.0,
|
| 13879 |
+
"step": 7705
|
| 13880 |
+
},
|
| 13881 |
+
{
|
| 13882 |
+
"epoch": 59.30769230769231,
|
| 13883 |
+
"grad_norm": 0.0,
|
| 13884 |
+
"learning_rate": 1.1455000000000001e-05,
|
| 13885 |
+
"loss": 1.7881,
|
| 13886 |
+
"mean_token_accuracy": 0.6390215069055557,
|
| 13887 |
+
"num_tokens": 28117982.0,
|
| 13888 |
+
"step": 7710
|
| 13889 |
}
|
| 13890 |
],
|
| 13891 |
"logging_steps": 5,
|
|
|
|
| 13905 |
"attributes": {}
|
| 13906 |
}
|
| 13907 |
},
|
| 13908 |
+
"total_flos": 1.4256209523754598e+18,
|
| 13909 |
"train_batch_size": 4,
|
| 13910 |
"trial_name": null,
|
| 13911 |
"trial_params": null
|