Training in progress, step 6610, 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:f29cf613d84a8e0a52c984c03630b80837d5925c2b90acbba95bc9f88f1263e8
|
| 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 sha256:7860da76713794319115b571df035ba7030b1e514c046b7d66deff79019407e9
|
| 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 sha256:0f06dc1ccecb8e5dc310ec0c256a7fb6f4d93a52a1056d90d1a969b1ad85064a
|
| 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": 50.
|
| 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,
|
|
@@ -11888,6 +11888,24 @@
|
|
| 11888 |
"mean_token_accuracy": 0.6513616561889648,
|
| 11889 |
"num_tokens": 24070441.0,
|
| 11890 |
"step": 6600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11891 |
}
|
| 11892 |
],
|
| 11893 |
"logging_steps": 5,
|
|
@@ -11907,7 +11925,7 @@
|
|
| 11907 |
"attributes": {}
|
| 11908 |
}
|
| 11909 |
},
|
| 11910 |
-
"total_flos": 1.
|
| 11911 |
"train_batch_size": 4,
|
| 11912 |
"trial_name": null,
|
| 11913 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11888 |
"mean_token_accuracy": 0.6513616561889648,
|
| 11889 |
"num_tokens": 24070441.0,
|
| 11890 |
"step": 6600
|
| 11891 |
+
},
|
| 11892 |
+
{
|
| 11893 |
+
"epoch": 50.80769230769231,
|
| 11894 |
+
"grad_norm": 0.0,
|
| 11895 |
+
"learning_rate": 1.698e-05,
|
| 11896 |
+
"loss": 1.7644,
|
| 11897 |
+
"mean_token_accuracy": 0.644871911406517,
|
| 11898 |
+
"num_tokens": 24088585.0,
|
| 11899 |
+
"step": 6605
|
| 11900 |
+
},
|
| 11901 |
+
{
|
| 11902 |
+
"epoch": 50.84615384615385,
|
| 11903 |
+
"grad_norm": 0.0,
|
| 11904 |
+
"learning_rate": 1.6955000000000003e-05,
|
| 11905 |
+
"loss": 1.7347,
|
| 11906 |
+
"mean_token_accuracy": 0.6584911167621612,
|
| 11907 |
+
"num_tokens": 24106472.0,
|
| 11908 |
+
"step": 6610
|
| 11909 |
}
|
| 11910 |
],
|
| 11911 |
"logging_steps": 5,
|
|
|
|
| 11925 |
"attributes": {}
|
| 11926 |
}
|
| 11927 |
},
|
| 11928 |
+
"total_flos": 1.2222345515699405e+18,
|
| 11929 |
"train_batch_size": 4,
|
| 11930 |
"trial_name": null,
|
| 11931 |
"trial_params": null
|