Training in progress, step 2960, 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 sha256:9a3e8b79c01045baf345e59f3b4f69f60b3b93cfb96a8788e3ced6174ea988d7
|
| 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:d4a091cb08454519ad641ebeed57555926194ba14465e8a4c4f47f7a20e49d81
|
| 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 sha256:814b42503f218290388e5810f9138fecf53a234a4c1fccd87825361d0f3aae88
|
| 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": 22.
|
| 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,
|
|
@@ -5318,6 +5318,24 @@
|
|
| 5318 |
"mean_token_accuracy": 0.6515435039997101,
|
| 5319 |
"num_tokens": 10757158.0,
|
| 5320 |
"step": 2950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5321 |
}
|
| 5322 |
],
|
| 5323 |
"logging_steps": 5,
|
|
@@ -5337,7 +5355,7 @@
|
|
| 5337 |
"attributes": {}
|
| 5338 |
}
|
| 5339 |
},
|
| 5340 |
-
"total_flos": 5.
|
| 5341 |
"train_batch_size": 4,
|
| 5342 |
"trial_name": null,
|
| 5343 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5318 |
"mean_token_accuracy": 0.6515435039997101,
|
| 5319 |
"num_tokens": 10757158.0,
|
| 5320 |
"step": 2950
|
| 5321 |
+
},
|
| 5322 |
+
{
|
| 5323 |
+
"epoch": 22.73076923076923,
|
| 5324 |
+
"grad_norm": 0.0,
|
| 5325 |
+
"learning_rate": 3.523e-05,
|
| 5326 |
+
"loss": 1.7007,
|
| 5327 |
+
"mean_token_accuracy": 0.6563295513391495,
|
| 5328 |
+
"num_tokens": 10775636.0,
|
| 5329 |
+
"step": 2955
|
| 5330 |
+
},
|
| 5331 |
+
{
|
| 5332 |
+
"epoch": 22.76923076923077,
|
| 5333 |
+
"grad_norm": 0.0,
|
| 5334 |
+
"learning_rate": 3.5205e-05,
|
| 5335 |
+
"loss": 1.7159,
|
| 5336 |
+
"mean_token_accuracy": 0.6521429270505905,
|
| 5337 |
+
"num_tokens": 10794398.0,
|
| 5338 |
+
"step": 2960
|
| 5339 |
}
|
| 5340 |
],
|
| 5341 |
"logging_steps": 5,
|
|
|
|
| 5355 |
"attributes": {}
|
| 5356 |
}
|
| 5357 |
},
|
| 5358 |
+
"total_flos": 5.4701813444788224e+17,
|
| 5359 |
"train_batch_size": 4,
|
| 5360 |
"trial_name": null,
|
| 5361 |
"trial_params": null
|