Training in progress, step 3280, 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 sha256:4c34686b72a4f3177e9cd6ea5c555f074135faeaea5a540a858b5df266e839a3
|
| 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 sha256:84df4163ecdbdeb3c6f14219ecd0afd33016369e1cb92f79738ca63f8b421f08
|
| 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:a47c73aaeb6f251458c57702abc61fa98d14ba1a2eee6f8e01e3b5b7dfd3d6a0
|
| 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": 25.
|
| 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,
|
|
@@ -5894,6 +5894,24 @@
|
|
| 5894 |
"mean_token_accuracy": 0.661970067024231,
|
| 5895 |
"num_tokens": 11925855.0,
|
| 5896 |
"step": 3270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5897 |
}
|
| 5898 |
],
|
| 5899 |
"logging_steps": 5,
|
|
@@ -5913,7 +5931,7 @@
|
|
| 5913 |
"attributes": {}
|
| 5914 |
}
|
| 5915 |
},
|
| 5916 |
-
"total_flos": 6.
|
| 5917 |
"train_batch_size": 4,
|
| 5918 |
"trial_name": null,
|
| 5919 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5894 |
"mean_token_accuracy": 0.661970067024231,
|
| 5895 |
"num_tokens": 11925855.0,
|
| 5896 |
"step": 3270
|
| 5897 |
+
},
|
| 5898 |
+
{
|
| 5899 |
+
"epoch": 25.192307692307693,
|
| 5900 |
+
"grad_norm": 0.0,
|
| 5901 |
+
"learning_rate": 3.363e-05,
|
| 5902 |
+
"loss": 1.7531,
|
| 5903 |
+
"mean_token_accuracy": 0.6502303391695022,
|
| 5904 |
+
"num_tokens": 11944217.0,
|
| 5905 |
+
"step": 3275
|
| 5906 |
+
},
|
| 5907 |
+
{
|
| 5908 |
+
"epoch": 25.23076923076923,
|
| 5909 |
+
"grad_norm": 0.0,
|
| 5910 |
+
"learning_rate": 3.3605e-05,
|
| 5911 |
+
"loss": 1.7867,
|
| 5912 |
+
"mean_token_accuracy": 0.6456191658973693,
|
| 5913 |
+
"num_tokens": 11961900.0,
|
| 5914 |
+
"step": 3280
|
| 5915 |
}
|
| 5916 |
],
|
| 5917 |
"logging_steps": 5,
|
|
|
|
| 5931 |
"attributes": {}
|
| 5932 |
}
|
| 5933 |
},
|
| 5934 |
+
"total_flos": 6.060711157383168e+17,
|
| 5935 |
"train_batch_size": 4,
|
| 5936 |
"trial_name": null,
|
| 5937 |
"trial_params": null
|