Training in progress, step 2950, 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 sha256:2d2e9767d459b526cc4bd1ad9c9ecdb163dc99ad6cdecf7070989307662092d1
|
| 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 sha256:6d3ea8024813935aa7d15aac6f2fe9f2d1583e1ae227977934750b64c368d144
|
| 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 sha256:9d0316861f9f51e141bbd134328e9a8775c2e467e5ac757a823a3e7f81e72633
|
| 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,
|
|
@@ -5300,6 +5300,24 @@
|
|
| 5300 |
"mean_token_accuracy": 0.659371867775917,
|
| 5301 |
"num_tokens": 10721196.0,
|
| 5302 |
"step": 2940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5303 |
}
|
| 5304 |
],
|
| 5305 |
"logging_steps": 5,
|
|
@@ -5319,7 +5337,7 @@
|
|
| 5319 |
"attributes": {}
|
| 5320 |
}
|
| 5321 |
},
|
| 5322 |
-
"total_flos": 5.
|
| 5323 |
"train_batch_size": 4,
|
| 5324 |
"trial_name": null,
|
| 5325 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5300 |
"mean_token_accuracy": 0.659371867775917,
|
| 5301 |
"num_tokens": 10721196.0,
|
| 5302 |
"step": 2940
|
| 5303 |
+
},
|
| 5304 |
+
{
|
| 5305 |
+
"epoch": 22.653846153846153,
|
| 5306 |
+
"grad_norm": 0.0,
|
| 5307 |
+
"learning_rate": 3.528e-05,
|
| 5308 |
+
"loss": 1.7689,
|
| 5309 |
+
"mean_token_accuracy": 0.647321754693985,
|
| 5310 |
+
"num_tokens": 10738660.0,
|
| 5311 |
+
"step": 2945
|
| 5312 |
+
},
|
| 5313 |
+
{
|
| 5314 |
+
"epoch": 22.692307692307693,
|
| 5315 |
+
"grad_norm": 0.0,
|
| 5316 |
+
"learning_rate": 3.5255e-05,
|
| 5317 |
+
"loss": 1.7366,
|
| 5318 |
+
"mean_token_accuracy": 0.6515435039997101,
|
| 5319 |
+
"num_tokens": 10757158.0,
|
| 5320 |
+
"step": 2950
|
| 5321 |
}
|
| 5322 |
],
|
| 5323 |
"logging_steps": 5,
|
|
|
|
| 5337 |
"attributes": {}
|
| 5338 |
}
|
| 5339 |
},
|
| 5340 |
+
"total_flos": 5.450986533489869e+17,
|
| 5341 |
"train_batch_size": 4,
|
| 5342 |
"trial_name": null,
|
| 5343 |
"trial_params": null
|