Training in progress, step 8430, 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:df45a2d9f970019f2fbe6c02efe753c554402b7540291f39a44844c33ff553e1
|
| 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 sha256:230c30479d55b611e10c80385710f48377d318551b2d9500bdc92817d0c4d09a
|
| 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 sha256:30ee0b8c75f4610cd1c3375d660d510e3fe598342ac30d0e6c0d38f11c1164d8
|
| 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": 64.
|
| 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,
|
|
@@ -15164,6 +15164,24 @@
|
|
| 15164 |
"mean_token_accuracy": 0.6512942612171173,
|
| 15165 |
"num_tokens": 30708498.0,
|
| 15166 |
"step": 8420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15167 |
}
|
| 15168 |
],
|
| 15169 |
"logging_steps": 5,
|
|
@@ -15183,7 +15201,7 @@
|
|
| 15183 |
"attributes": {}
|
| 15184 |
}
|
| 15185 |
},
|
| 15186 |
-
"total_flos": 1.
|
| 15187 |
"train_batch_size": 4,
|
| 15188 |
"trial_name": null,
|
| 15189 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15164 |
"mean_token_accuracy": 0.6512942612171173,
|
| 15165 |
"num_tokens": 30708498.0,
|
| 15166 |
"step": 8420
|
| 15167 |
+
},
|
| 15168 |
+
{
|
| 15169 |
+
"epoch": 64.8076923076923,
|
| 15170 |
+
"grad_norm": 0.0,
|
| 15171 |
+
"learning_rate": 7.879999999999999e-06,
|
| 15172 |
+
"loss": 1.7456,
|
| 15173 |
+
"mean_token_accuracy": 0.644093918800354,
|
| 15174 |
+
"num_tokens": 30726723.0,
|
| 15175 |
+
"step": 8425
|
| 15176 |
+
},
|
| 15177 |
+
{
|
| 15178 |
+
"epoch": 64.84615384615384,
|
| 15179 |
+
"grad_norm": 0.0,
|
| 15180 |
+
"learning_rate": 7.855e-06,
|
| 15181 |
+
"loss": 1.7664,
|
| 15182 |
+
"mean_token_accuracy": 0.6423812568187713,
|
| 15183 |
+
"num_tokens": 30745189.0,
|
| 15184 |
+
"step": 8430
|
| 15185 |
}
|
| 15186 |
],
|
| 15187 |
"logging_steps": 5,
|
|
|
|
| 15201 |
"attributes": {}
|
| 15202 |
}
|
| 15203 |
},
|
| 15204 |
+
"total_flos": 1.558947166356603e+18,
|
| 15205 |
"train_batch_size": 4,
|
| 15206 |
"trial_name": null,
|
| 15207 |
"trial_params": null
|