Training in progress, step 7870, 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 sha256:1a74e39a6e8b84c7781bc30ab55049fb5e49f97956d992e77dd04b2cafccc274
|
| 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 sha256:1ec86f67989569acd77fad76bcf13da972feffc7f57d1b6bdd791411eb8da3aa
|
| 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:e81a6985e727435b8d9e3394c3b2b04f93e76138bf0070c84981d489a8c261c2
|
| 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": 60.
|
| 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,
|
|
@@ -14156,6 +14156,24 @@
|
|
| 14156 |
"mean_token_accuracy": 0.662873387336731,
|
| 14157 |
"num_tokens": 28664176.0,
|
| 14158 |
"step": 7860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14159 |
}
|
| 14160 |
],
|
| 14161 |
"logging_steps": 5,
|
|
@@ -14175,7 +14193,7 @@
|
|
| 14175 |
"attributes": {}
|
| 14176 |
}
|
| 14177 |
},
|
| 14178 |
-
"total_flos": 1.
|
| 14179 |
"train_batch_size": 4,
|
| 14180 |
"trial_name": null,
|
| 14181 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14156 |
"mean_token_accuracy": 0.662873387336731,
|
| 14157 |
"num_tokens": 28664176.0,
|
| 14158 |
"step": 7860
|
| 14159 |
+
},
|
| 14160 |
+
{
|
| 14161 |
+
"epoch": 60.5,
|
| 14162 |
+
"grad_norm": 0.0,
|
| 14163 |
+
"learning_rate": 1.0680000000000001e-05,
|
| 14164 |
+
"loss": 1.7298,
|
| 14165 |
+
"mean_token_accuracy": 0.6527964979410171,
|
| 14166 |
+
"num_tokens": 28682577.0,
|
| 14167 |
+
"step": 7865
|
| 14168 |
+
},
|
| 14169 |
+
{
|
| 14170 |
+
"epoch": 60.53846153846154,
|
| 14171 |
+
"grad_norm": 0.0,
|
| 14172 |
+
"learning_rate": 1.0655e-05,
|
| 14173 |
+
"loss": 1.7012,
|
| 14174 |
+
"mean_token_accuracy": 0.6583037704229355,
|
| 14175 |
+
"num_tokens": 28701898.0,
|
| 14176 |
+
"step": 7870
|
| 14177 |
}
|
| 14178 |
],
|
| 14179 |
"logging_steps": 5,
|
|
|
|
| 14193 |
"attributes": {}
|
| 14194 |
}
|
| 14195 |
},
|
| 14196 |
+
"total_flos": 1.4553420268643942e+18,
|
| 14197 |
"train_batch_size": 4,
|
| 14198 |
"trial_name": null,
|
| 14199 |
"trial_params": null
|