Hugging Face's logo

mlfoundations-dev
/
stackexchange_cogsci

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
f8b8cdc
·
verified ·
1 Parent(s): ed00382

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5577077c594886f76842c562ed5cb60b4dd4ff1ef0758c8d8ac3668b30ce333e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ad5d51c088442e4353aa4228fb563faa411f3c4db91c620bff53700fc6b685
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:c75cf7bb0c493d431eeae247272cd4fdf3cc8b694574e0ffad4f5b8ed5718e78
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5752b60c280a05a0c3fb0f1f4bd27bb179a40b17e107f5e49865f126b91fab
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05a7959efafa504ad577888311c940359024b91bb8f2f5cddc9367acd7781e00
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615383efe1daed76b826ab8c72f59aba65e050bc2d43ef010c80e4c91e75d9a3
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:b4b502fc46f16eecf277bf21e848907eb62f98cbe21c60085d8036ab74feeeee
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88ab431d7e1c59e0a51d2b1bd7e4a008146e901830bfa32ff93e2128c0b1260
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 10, "total_steps": 30, "eval_loss": 1.1205402612686157, "epoch": 0.963855421686747, "percentage": 33.33, "elapsed_time": "0:10:07", "remaining_time": "0:20:14"}
3
  {"current_steps": 20, "total_steps": 30, "loss": 1.1431, "lr": 5e-06, "epoch": 1.9397590361445785, "percentage": 66.67, "elapsed_time": "0:20:39", "remaining_time": "0:10:19"}
4
  {"current_steps": 20, "total_steps": 30, "eval_loss": 1.060249924659729, "epoch": 1.9397590361445785, "percentage": 66.67, "elapsed_time": "0:21:18", "remaining_time": "0:10:39"}
 
 
 
 
2
  {"current_steps": 10, "total_steps": 30, "eval_loss": 1.1205402612686157, "epoch": 0.963855421686747, "percentage": 33.33, "elapsed_time": "0:10:07", "remaining_time": "0:20:14"}
3
  {"current_steps": 20, "total_steps": 30, "loss": 1.1431, "lr": 5e-06, "epoch": 1.9397590361445785, "percentage": 66.67, "elapsed_time": "0:20:39", "remaining_time": "0:10:19"}
4
  {"current_steps": 20, "total_steps": 30, "eval_loss": 1.060249924659729, "epoch": 1.9397590361445785, "percentage": 66.67, "elapsed_time": "0:21:18", "remaining_time": "0:10:39"}
5
+ {"current_steps": 30, "total_steps": 30, "loss": 1.0686, "lr": 5e-06, "epoch": 2.9156626506024095, "percentage": 100.0, "elapsed_time": "0:31:40", "remaining_time": "0:00:00"}
6
+ {"current_steps": 30, "total_steps": 30, "eval_loss": 1.0308853387832642, "epoch": 2.9156626506024095, "percentage": 100.0, "elapsed_time": "0:33:05", "remaining_time": "0:00:00"}
7
+ {"current_steps": 30, "total_steps": 30, "epoch": 2.9156626506024095, "percentage": 100.0, "elapsed_time": "0:34:21", "remaining_time": "0:00:00"}