Training in progress, step 4570, 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 sha256:8decd79ee4198817ec556cfbf63f8e4bf12c3590423b6d47171fe4a0755be6ab
|
| 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 sha256:4ecc56a52daf306c838dc0ad42d0fe184a4daf334cf3ce3f5ae9dcaf6bfecc75
|
| 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 sha256:69812aecf0fad8c1b3df25b2eecb858b340b5c9029a2b6ede9cffd1a14957b25
|
| 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": 35.
|
| 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,
|
|
@@ -8216,6 +8216,24 @@
|
|
| 8216 |
"mean_token_accuracy": 0.6467309683561325,
|
| 8217 |
"num_tokens": 16630046.0,
|
| 8218 |
"step": 4560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8219 |
}
|
| 8220 |
],
|
| 8221 |
"logging_steps": 5,
|
|
@@ -8235,7 +8253,7 @@
|
|
| 8235 |
"attributes": {}
|
| 8236 |
}
|
| 8237 |
},
|
| 8238 |
-
"total_flos": 8.
|
| 8239 |
"train_batch_size": 4,
|
| 8240 |
"trial_name": null,
|
| 8241 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8216 |
"mean_token_accuracy": 0.6467309683561325,
|
| 8217 |
"num_tokens": 16630046.0,
|
| 8218 |
"step": 4560
|
| 8219 |
+
},
|
| 8220 |
+
{
|
| 8221 |
+
"epoch": 35.11538461538461,
|
| 8222 |
+
"grad_norm": 0.0,
|
| 8223 |
+
"learning_rate": 2.718e-05,
|
| 8224 |
+
"loss": 1.6749,
|
| 8225 |
+
"mean_token_accuracy": 0.6611016511917114,
|
| 8226 |
+
"num_tokens": 16648965.0,
|
| 8227 |
+
"step": 4565
|
| 8228 |
+
},
|
| 8229 |
+
{
|
| 8230 |
+
"epoch": 35.15384615384615,
|
| 8231 |
+
"grad_norm": 0.0,
|
| 8232 |
+
"learning_rate": 2.7155000000000003e-05,
|
| 8233 |
+
"loss": 1.6678,
|
| 8234 |
+
"mean_token_accuracy": 0.6659534931182861,
|
| 8235 |
+
"num_tokens": 16668179.0,
|
| 8236 |
+
"step": 4570
|
| 8237 |
}
|
| 8238 |
],
|
| 8239 |
"logging_steps": 5,
|
|
|
|
| 8253 |
"attributes": {}
|
| 8254 |
}
|
| 8255 |
},
|
| 8256 |
+
"total_flos": 8.447985789139354e+17,
|
| 8257 |
"train_batch_size": 4,
|
| 8258 |
"trial_name": null,
|
| 8259 |
"trial_params": null
|