Training in progress, step 5230, 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:b3fc520cb6b8a4bc7517b4411b9adc5fbf794617c335c62080f0d84adf82e3f6
|
| 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 sha256:1d0691407d3692ea78b689fba6bbce9b3cd0c545b8dbd583ce76932715cd1909
|
| 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:d44735c4c6bc8d58a11ede7dd7dd1278f07cf48f886f118266057c6801825c76
|
| 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": 40.
|
| 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,
|
|
@@ -9404,6 +9404,24 @@
|
|
| 9404 |
"mean_token_accuracy": 0.6531620174646378,
|
| 9405 |
"num_tokens": 19036736.0,
|
| 9406 |
"step": 5220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9407 |
}
|
| 9408 |
],
|
| 9409 |
"logging_steps": 5,
|
|
@@ -9423,7 +9441,7 @@
|
|
| 9423 |
"attributes": {}
|
| 9424 |
}
|
| 9425 |
},
|
| 9426 |
-
"total_flos": 9.
|
| 9427 |
"train_batch_size": 4,
|
| 9428 |
"trial_name": null,
|
| 9429 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9404 |
"mean_token_accuracy": 0.6531620174646378,
|
| 9405 |
"num_tokens": 19036736.0,
|
| 9406 |
"step": 5220
|
| 9407 |
+
},
|
| 9408 |
+
{
|
| 9409 |
+
"epoch": 40.19230769230769,
|
| 9410 |
+
"grad_norm": 0.0,
|
| 9411 |
+
"learning_rate": 2.3880000000000002e-05,
|
| 9412 |
+
"loss": 1.7962,
|
| 9413 |
+
"mean_token_accuracy": 0.6403325825929642,
|
| 9414 |
+
"num_tokens": 19054193.0,
|
| 9415 |
+
"step": 5225
|
| 9416 |
+
},
|
| 9417 |
+
{
|
| 9418 |
+
"epoch": 40.23076923076923,
|
| 9419 |
+
"grad_norm": 0.0,
|
| 9420 |
+
"learning_rate": 2.3855e-05,
|
| 9421 |
+
"loss": 1.8235,
|
| 9422 |
+
"mean_token_accuracy": 0.634826073050499,
|
| 9423 |
+
"num_tokens": 19071438.0,
|
| 9424 |
+
"step": 5230
|
| 9425 |
}
|
| 9426 |
],
|
| 9427 |
"logging_steps": 5,
|
|
|
|
| 9441 |
"attributes": {}
|
| 9442 |
}
|
| 9443 |
},
|
| 9444 |
+
"total_flos": 9.664083209148826e+17,
|
| 9445 |
"train_batch_size": 4,
|
| 9446 |
"trial_name": null,
|
| 9447 |
"trial_params": null
|