Training in progress, step 4400, 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 sha256:10eccd0a05474ba7eaa78a512d88787ba8ea360a766e45696d743458769e5af8
|
| 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:e495af09a95b29a057f530b3a2d9ef6a33c822c7fc7c520943fbe4e8c6666933
|
| 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:fc27bd964287153ff76632bc42a8ffaa6ee235c2acb327c40ded9ab3a674752a
|
| 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": 33.
|
| 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,
|
|
@@ -7910,6 +7910,24 @@
|
|
| 7910 |
"mean_token_accuracy": 0.6550534397363663,
|
| 7911 |
"num_tokens": 16012525.0,
|
| 7912 |
"step": 4390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7913 |
}
|
| 7914 |
],
|
| 7915 |
"logging_steps": 5,
|
|
@@ -7929,7 +7947,7 @@
|
|
| 7929 |
"attributes": {}
|
| 7930 |
}
|
| 7931 |
},
|
| 7932 |
-
"total_flos": 8.
|
| 7933 |
"train_batch_size": 4,
|
| 7934 |
"trial_name": null,
|
| 7935 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7910 |
"mean_token_accuracy": 0.6550534397363663,
|
| 7911 |
"num_tokens": 16012525.0,
|
| 7912 |
"step": 4390
|
| 7913 |
+
},
|
| 7914 |
+
{
|
| 7915 |
+
"epoch": 33.80769230769231,
|
| 7916 |
+
"grad_norm": 0.0,
|
| 7917 |
+
"learning_rate": 2.803e-05,
|
| 7918 |
+
"loss": 1.8682,
|
| 7919 |
+
"mean_token_accuracy": 0.6267781972885131,
|
| 7920 |
+
"num_tokens": 16029494.0,
|
| 7921 |
+
"step": 4395
|
| 7922 |
+
},
|
| 7923 |
+
{
|
| 7924 |
+
"epoch": 33.84615384615385,
|
| 7925 |
+
"grad_norm": 0.0,
|
| 7926 |
+
"learning_rate": 2.8005000000000004e-05,
|
| 7927 |
+
"loss": 1.7787,
|
| 7928 |
+
"mean_token_accuracy": 0.6424099951982498,
|
| 7929 |
+
"num_tokens": 16047811.0,
|
| 7930 |
+
"step": 4400
|
| 7931 |
}
|
| 7932 |
],
|
| 7933 |
"logging_steps": 5,
|
|
|
|
| 7947 |
"attributes": {}
|
| 7948 |
}
|
| 7949 |
},
|
| 7950 |
+
"total_flos": 8.132844115265126e+17,
|
| 7951 |
"train_batch_size": 4,
|
| 7952 |
"trial_name": null,
|
| 7953 |
"trial_params": null
|