Hugging Face's logo

mlfoundations-dev
/
stackoverflow_10000tasks_.25p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
7165cba
·
verified ·
1 Parent(s): d3c88f6

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:978f34bb3e588de56da8c902c473aa64bd306aed0604641029fdd82c5c29ac25
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d734409be7cf93c71567d8400f674e1bfd296a22f566466c9f3f28d718bf26
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40154947a35ba17638b65597f59cf5f8eab5792d6b5e0f1f0fa724e95f93dc9f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2886e8f8f002f18adc599d66375463da1befae51080e9a29323911ffecf27948
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:541b4e73dd9c849e3bc05ee9fcdf20d4868550538550beb45ff1c92cb86bd45f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2311968723aab54782c7c51080a18933c299eaaeb9a479f0bf3c26c34b7e4bb1
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6ad5f2935fcfe350357fa6b04f61334d6de336c47fccb15036ec9986b812e3
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57a11722b2e99a9bafcb3a7e6a5a551f3d74b9a6749a0bbe8825062803f7877
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6944, "lr": 5e-06, "epoch": 0.5970149253731343, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:22"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.6489, "lr": 5e-06, "epoch": 0.8955223880597015, "percentage": 30.3, "elapsed_time": "0:16:01", "remaining_time": "0:36:51"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.6296907663345337, "epoch": 0.9850746268656716, "percentage": 33.33, "elapsed_time": "0:18:16", "remaining_time": "0:36:32"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6944, "lr": 5e-06, "epoch": 0.5970149253731343, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:22"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.6489, "lr": 5e-06, "epoch": 0.8955223880597015, "percentage": 30.3, "elapsed_time": "0:16:01", "remaining_time": "0:36:51"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.6296907663345337, "epoch": 0.9850746268656716, "percentage": 33.33, "elapsed_time": "0:18:16", "remaining_time": "0:36:32"}
5
+ {"current_steps": 40, "total_steps": 99, "loss": 0.6397, "lr": 5e-06, "epoch": 1.1940298507462686, "percentage": 40.4, "elapsed_time": "0:22:55", "remaining_time": "0:33:49"}
6
+ {"current_steps": 50, "total_steps": 99, "loss": 0.5745, "lr": 5e-06, "epoch": 1.4925373134328357, "percentage": 50.51, "elapsed_time": "0:28:15", "remaining_time": "0:27:41"}
7
+ {"current_steps": 60, "total_steps": 99, "loss": 0.565, "lr": 5e-06, "epoch": 1.7910447761194028, "percentage": 60.61, "elapsed_time": "0:33:33", "remaining_time": "0:21:49"}
8
+ {"current_steps": 67, "total_steps": 99, "eval_loss": 0.5920219421386719, "epoch": 2.0, "percentage": 67.68, "elapsed_time": "0:37:36", "remaining_time": "0:17:57"}
9
+ {"current_steps": 70, "total_steps": 99, "loss": 0.5686, "lr": 5e-06, "epoch": 2.08955223880597, "percentage": 70.71, "elapsed_time": "0:40:27", "remaining_time": "0:16:45"}