Training in progress, step 1120, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100697728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93756c662435c89f0b33aea427588c404b58d5be37cf76c3f9e4bc0ff1bd939a
|
3 |
size 100697728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201541754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a88dc8585ef97f13c62f73031c2660812fe3125beba7cb9ca7b650ca2dd9be0e
|
3 |
size 201541754
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10612cfe26142bef77beb908186e256524851aa5a76ff5646d1e0e1c8e9ff68c
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:827f3733c0f4c8564e6bc69cab6741789e52e80ec29e9f5a0f4d2f148dfac06d
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -887,14 +887,30 @@
|
|
887 |
"loss": 0.4208,
|
888 |
"num_input_tokens_seen": 739112,
|
889 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
890 |
}
|
891 |
],
|
892 |
"logging_steps": 10,
|
893 |
"max_steps": 2795,
|
894 |
-
"num_input_tokens_seen":
|
895 |
"num_train_epochs": 1,
|
896 |
"save_steps": 20,
|
897 |
-
"total_flos": 1.
|
898 |
"train_batch_size": 1,
|
899 |
"trial_name": null,
|
900 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4007155635062612,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
887 |
"loss": 0.4208,
|
888 |
"num_input_tokens_seen": 739112,
|
889 |
"step": 1100
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 0.39713774597495527,
|
893 |
+
"grad_norm": 0.3873242437839508,
|
894 |
+
"learning_rate": 0.00012057245080500895,
|
895 |
+
"loss": 0.3798,
|
896 |
+
"num_input_tokens_seen": 744478,
|
897 |
+
"step": 1110
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.4007155635062612,
|
901 |
+
"grad_norm": 0.31334424018859863,
|
902 |
+
"learning_rate": 0.00011985688729874778,
|
903 |
+
"loss": 0.4179,
|
904 |
+
"num_input_tokens_seen": 753315,
|
905 |
+
"step": 1120
|
906 |
}
|
907 |
],
|
908 |
"logging_steps": 10,
|
909 |
"max_steps": 2795,
|
910 |
+
"num_input_tokens_seen": 753315,
|
911 |
"num_train_epochs": 1,
|
912 |
"save_steps": 20,
|
913 |
+
"total_flos": 1.693939409943552e+16,
|
914 |
"train_batch_size": 1,
|
915 |
"trial_name": null,
|
916 |
"trial_params": null
|