Training in progress, step 5500, 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:f28400e3726e4b9f442cf5cd0089a37019403d47982ba39007a6d62a829f0a9d
|
| 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:ffe6600082211d0e79d29ba48c940879237085ee962a22eca07309664d756d0b
|
| 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 sha256:90740cb303fd1d768ef8948de2620370c238706bae6a021f801e8b2500c0bd72
|
| 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": 42.
|
| 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,
|
|
@@ -9890,6 +9890,24 @@
|
|
| 9890 |
"mean_token_accuracy": 0.6572997212409973,
|
| 9891 |
"num_tokens": 20019689.0,
|
| 9892 |
"step": 5490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9893 |
}
|
| 9894 |
],
|
| 9895 |
"logging_steps": 5,
|
|
@@ -9909,7 +9927,7 @@
|
|
| 9909 |
"attributes": {}
|
| 9910 |
}
|
| 9911 |
},
|
| 9912 |
-
"total_flos": 1.
|
| 9913 |
"train_batch_size": 4,
|
| 9914 |
"trial_name": null,
|
| 9915 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9890 |
"mean_token_accuracy": 0.6572997212409973,
|
| 9891 |
"num_tokens": 20019689.0,
|
| 9892 |
"step": 5490
|
| 9893 |
+
},
|
| 9894 |
+
{
|
| 9895 |
+
"epoch": 42.26923076923077,
|
| 9896 |
+
"grad_norm": 0.0,
|
| 9897 |
+
"learning_rate": 2.253e-05,
|
| 9898 |
+
"loss": 1.7257,
|
| 9899 |
+
"mean_token_accuracy": 0.6576829224824905,
|
| 9900 |
+
"num_tokens": 20037781.0,
|
| 9901 |
+
"step": 5495
|
| 9902 |
+
},
|
| 9903 |
+
{
|
| 9904 |
+
"epoch": 42.30769230769231,
|
| 9905 |
+
"grad_norm": 0.0,
|
| 9906 |
+
"learning_rate": 2.2505000000000002e-05,
|
| 9907 |
+
"loss": 1.7521,
|
| 9908 |
+
"mean_token_accuracy": 0.647400951385498,
|
| 9909 |
+
"num_tokens": 20056196.0,
|
| 9910 |
+
"step": 5500
|
| 9911 |
}
|
| 9912 |
],
|
| 9913 |
"logging_steps": 5,
|
|
|
|
| 9927 |
"attributes": {}
|
| 9928 |
}
|
| 9929 |
},
|
| 9930 |
+
"total_flos": 1.0162813270863053e+18,
|
| 9931 |
"train_batch_size": 4,
|
| 9932 |
"trial_name": null,
|
| 9933 |
"trial_params": null
|