Training in progress, step 1770, 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:d30fec9180ae2d0f8b1137fecb7c7661667aad623d24cc963c7c89938babd8cb
|
| 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:e2afa3d447f82a37c4ea0db90bfcd1f143f8bc1631ba41d4d6fe97b5a7721527
|
| 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 sha256:21f768c964be6ce019d8a14f83397a3ef60c0e0fa812098fd8a743aa03ae2512
|
| 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": 13.
|
| 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,
|
|
@@ -3176,6 +3176,24 @@
|
|
| 3176 |
"mean_token_accuracy": 0.6668368667364121,
|
| 3177 |
"num_tokens": 6417790.0,
|
| 3178 |
"step": 1760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3179 |
}
|
| 3180 |
],
|
| 3181 |
"logging_steps": 5,
|
|
@@ -3195,7 +3213,7 @@
|
|
| 3195 |
"attributes": {}
|
| 3196 |
}
|
| 3197 |
},
|
| 3198 |
-
"total_flos": 3.
|
| 3199 |
"train_batch_size": 4,
|
| 3200 |
"trial_name": null,
|
| 3201 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3176 |
"mean_token_accuracy": 0.6668368667364121,
|
| 3177 |
"num_tokens": 6417790.0,
|
| 3178 |
"step": 1760
|
| 3179 |
+
},
|
| 3180 |
+
{
|
| 3181 |
+
"epoch": 13.576923076923077,
|
| 3182 |
+
"grad_norm": 0.0,
|
| 3183 |
+
"learning_rate": 4.118e-05,
|
| 3184 |
+
"loss": 1.7109,
|
| 3185 |
+
"mean_token_accuracy": 0.651064109802246,
|
| 3186 |
+
"num_tokens": 6436016.0,
|
| 3187 |
+
"step": 1765
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 13.615384615384615,
|
| 3191 |
+
"grad_norm": 0.0,
|
| 3192 |
+
"learning_rate": 4.1155e-05,
|
| 3193 |
+
"loss": 1.7844,
|
| 3194 |
+
"mean_token_accuracy": 0.6407437533140182,
|
| 3195 |
+
"num_tokens": 6453594.0,
|
| 3196 |
+
"step": 1770
|
| 3197 |
}
|
| 3198 |
],
|
| 3199 |
"logging_steps": 5,
|
|
|
|
| 3213 |
"attributes": {}
|
| 3214 |
}
|
| 3215 |
},
|
| 3216 |
+
"total_flos": 3.269416636853453e+17,
|
| 3217 |
"train_batch_size": 4,
|
| 3218 |
"trial_name": null,
|
| 3219 |
"trial_params": null
|