Training in progress, step 7160, 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:ee822c41ca708942dbf6ede32b2b775fa18e23c7fc5fbe44baa942530dadb96b
|
| 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:a9a52349527671e6d013d3c90631f1e935e4b1345ccc96decb8e7419b677bb2d
|
| 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 sha256:99f8ca9a29c060486b35dd8e38e671ef4358e6f7f9fd5614034e6a0882a3693d
|
| 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": 55.
|
| 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,
|
|
@@ -12878,6 +12878,24 @@
|
|
| 12878 |
"mean_token_accuracy": 0.6422353565692902,
|
| 12879 |
"num_tokens": 26075775.0,
|
| 12880 |
"step": 7150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12881 |
}
|
| 12882 |
],
|
| 12883 |
"logging_steps": 5,
|
|
@@ -12897,7 +12915,7 @@
|
|
| 12897 |
"attributes": {}
|
| 12898 |
}
|
| 12899 |
},
|
| 12900 |
-
"total_flos": 1.
|
| 12901 |
"train_batch_size": 4,
|
| 12902 |
"trial_name": null,
|
| 12903 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12878 |
"mean_token_accuracy": 0.6422353565692902,
|
| 12879 |
"num_tokens": 26075775.0,
|
| 12880 |
"step": 7150
|
| 12881 |
+
},
|
| 12882 |
+
{
|
| 12883 |
+
"epoch": 55.03846153846154,
|
| 12884 |
+
"grad_norm": 0.0,
|
| 12885 |
+
"learning_rate": 1.4230000000000001e-05,
|
| 12886 |
+
"loss": 1.7951,
|
| 12887 |
+
"mean_token_accuracy": 0.6395128637552261,
|
| 12888 |
+
"num_tokens": 26093593.0,
|
| 12889 |
+
"step": 7155
|
| 12890 |
+
},
|
| 12891 |
+
{
|
| 12892 |
+
"epoch": 55.07692307692308,
|
| 12893 |
+
"grad_norm": 0.0,
|
| 12894 |
+
"learning_rate": 1.4205000000000002e-05,
|
| 12895 |
+
"loss": 1.7587,
|
| 12896 |
+
"mean_token_accuracy": 0.6477168142795563,
|
| 12897 |
+
"num_tokens": 26111565.0,
|
| 12898 |
+
"step": 7160
|
| 12899 |
}
|
| 12900 |
],
|
| 12901 |
"logging_steps": 5,
|
|
|
|
| 12915 |
"attributes": {}
|
| 12916 |
}
|
| 12917 |
},
|
| 12918 |
+
"total_flos": 1.324001822444421e+18,
|
| 12919 |
"train_batch_size": 4,
|
| 12920 |
"trial_name": null,
|
| 12921 |
"trial_params": null
|