Hugging Face's logo

mlfoundations-dev
/
stackexchange_hinduism

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
4f59186
·
verified ·
1 Parent(s): 3ac01d8

Training in progress, epoch 1

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18dc08dd7ec94514a76773038220b57b61e7d51c622dc556b5883d85c6d51b8e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552534f70ac9be1d3d617093a6db1c7c4af5102a8a510ad36e3f6482429c87a9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d50cb5e44844c9c61387858345f3d70e1370a16b6e42dad5bf7ac577a01185f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd5ad58f5e880ea392316f4f8bdb71258c769187199f2b58e19399fe9cecce4
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a8181ffe0efc02f9787fd3036a31e30de81263c7e11550e39b82bf704bacb22
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccfdaa75d5160d296c599134a0e67c901c5fef5f8fbd275ec5a60a1cfe45d96
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:c938870a7015d4b8a99aed13bd215165854ad26b20be92f3f1fa79d8789f55f9
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c999618379ee469010e773903d7a9f5726028daf1077343397c82e80e3157f2
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 60, "loss": 1.1902, "lr": 5e-06, "epoch": 0.4878048780487805, "percentage": 16.67, "elapsed_time": "0:05:27", "remaining_time": "0:27:15"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 1.0743, "lr": 5e-06, "epoch": 0.975609756097561, "percentage": 33.33, "elapsed_time": "0:10:43", "remaining_time": "0:21:27"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 1.0350981950759888, "epoch": 0.975609756097561, "percentage": 33.33, "elapsed_time": "0:11:10", "remaining_time": "0:22:20"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 60, "loss": 1.1902, "lr": 5e-06, "epoch": 0.4878048780487805, "percentage": 16.67, "elapsed_time": "0:05:27", "remaining_time": "0:27:15"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 1.0743, "lr": 5e-06, "epoch": 0.975609756097561, "percentage": 33.33, "elapsed_time": "0:10:43", "remaining_time": "0:21:27"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 1.0350981950759888, "epoch": 0.975609756097561, "percentage": 33.33, "elapsed_time": "0:11:10", "remaining_time": "0:22:20"}
4
+ {"current_steps": 30, "total_steps": 60, "loss": 1.069, "lr": 5e-06, "epoch": 1.4695121951219512, "percentage": 50.0, "elapsed_time": "0:17:28", "remaining_time": "0:17:28"}
5
+ {"current_steps": 40, "total_steps": 60, "loss": 0.971, "lr": 5e-06, "epoch": 1.9573170731707317, "percentage": 66.67, "elapsed_time": "0:22:46", "remaining_time": "0:11:23"}
6
+ {"current_steps": 40, "total_steps": 60, "eval_loss": 0.9772650599479675, "epoch": 1.9573170731707317, "percentage": 66.67, "elapsed_time": "0:23:21", "remaining_time": "0:11:40"}