Femboyuwu2000
commited on
Commit
•
fbf7861
1
Parent(s):
eb17b0b
Training in progress, step 5740, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85dd23053478779ccf46e0ca2c0ab595376b10a00281986da38738dcf4c5a6f2
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68508aeacddbbed435dffee6ab56d14ad8cc7af1af1a4a1cbd0e8c21cccf52c
|
3 |
size 7062522
|
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:d3568a47a934d5a4cfad1f4c6204e4bef8d710f3fea7631bb7a3e787aba3f0c2
|
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:db005cc740de60b97936932099d8a692b0015d48f80c2b3cda30ecdcf7f9644e
|
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,
|
@@ -2009,6 +2009,13 @@
|
|
2009 |
"learning_rate": 2.5132858131187446e-05,
|
2010 |
"loss": 3.4688,
|
2011 |
"step": 5720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012 |
}
|
2013 |
],
|
2014 |
"logging_steps": 20,
|
@@ -2016,7 +2023,7 @@
|
|
2016 |
"num_input_tokens_seen": 0,
|
2017 |
"num_train_epochs": 2,
|
2018 |
"save_steps": 20,
|
2019 |
-
"total_flos": 1.
|
2020 |
"train_batch_size": 8,
|
2021 |
"trial_name": null,
|
2022 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4592,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5740,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2009 |
"learning_rate": 2.5132858131187446e-05,
|
2010 |
"loss": 3.4688,
|
2011 |
"step": 5720
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.46,
|
2015 |
+
"grad_norm": 34.07016372680664,
|
2016 |
+
"learning_rate": 2.509698418337534e-05,
|
2017 |
+
"loss": 3.4938,
|
2018 |
+
"step": 5740
|
2019 |
}
|
2020 |
],
|
2021 |
"logging_steps": 20,
|
|
|
2023 |
"num_input_tokens_seen": 0,
|
2024 |
"num_train_epochs": 2,
|
2025 |
"save_steps": 20,
|
2026 |
+
"total_flos": 1.3598247598227456e+16,
|
2027 |
"train_batch_size": 8,
|
2028 |
"trial_name": null,
|
2029 |
"trial_params": null
|