Hugging Face's logo

mli-lab
/
qwen_OHprompts_GPT4oresponses_4k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
1
reinhardh commited on
Commit
f35c687
·
verified ·
1 Parent(s): 71f7692

Training in progress, step 27

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67d93c331d379df8bb17d6678677350c3debfd5bebe1d5d94e73270b0f102d9d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d444312f9553b2fefc444b47cbdbebad15589177d5563abbc52d60953c3c9442
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd7889ab4362a2f4229a2844e1a0abc46d999fe918d55cdad0e03e7e82d02518
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce67c4b727ff343580de1602db54b1dd5027b75564cd95ecb46d85530f7b1c9c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db91e9aa4c66485d0af90a585f097413eabfc868ba4c779fcf8442230564e798
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109905368f0f20deb69ef903eaa1eb04b570f1df4355d9d43171b26568d7496f
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3cd1d55b22b879d05278622d988176a41b13cfe8d8ebbbd17a74fbc03494614
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c05c242236203ccb3458273122b628703e65b0a3a7189d675daa8a1fa27f64
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -22,3 +22,7 @@
22
  {"current_steps": 22, "total_steps": 27, "loss": 0.592, "lr": 1.0332332985438248e-06, "epoch": 2.4, "percentage": 81.48, "elapsed_time": "0:07:09", "remaining_time": "0:01:37"}
23
  {"current_steps": 23, "total_steps": 27, "loss": 0.6052, "lr": 6.698729810778065e-07, "epoch": 2.509090909090909, "percentage": 85.19, "elapsed_time": "0:07:20", "remaining_time": "0:01:16"}
24
  {"current_steps": 24, "total_steps": 27, "loss": 0.6015, "lr": 3.8060233744356634e-07, "epoch": 2.618181818181818, "percentage": 88.89, "elapsed_time": "0:07:32", "remaining_time": "0:00:56"}
 
 
 
 
 
22
  {"current_steps": 22, "total_steps": 27, "loss": 0.592, "lr": 1.0332332985438248e-06, "epoch": 2.4, "percentage": 81.48, "elapsed_time": "0:07:09", "remaining_time": "0:01:37"}
23
  {"current_steps": 23, "total_steps": 27, "loss": 0.6052, "lr": 6.698729810778065e-07, "epoch": 2.509090909090909, "percentage": 85.19, "elapsed_time": "0:07:20", "remaining_time": "0:01:16"}
24
  {"current_steps": 24, "total_steps": 27, "loss": 0.6015, "lr": 3.8060233744356634e-07, "epoch": 2.618181818181818, "percentage": 88.89, "elapsed_time": "0:07:32", "remaining_time": "0:00:56"}
25
+ {"current_steps": 25, "total_steps": 27, "loss": 0.5736, "lr": 1.7037086855465902e-07, "epoch": 2.7272727272727275, "percentage": 92.59, "elapsed_time": "0:07:43", "remaining_time": "0:00:37"}
26
+ {"current_steps": 26, "total_steps": 27, "loss": 0.5576, "lr": 4.2775693130948094e-08, "epoch": 2.8363636363636364, "percentage": 96.3, "elapsed_time": "0:07:55", "remaining_time": "0:00:18"}
27
+ {"current_steps": 27, "total_steps": 27, "loss": 0.5451, "lr": 0.0, "epoch": 2.9454545454545453, "percentage": 100.0, "elapsed_time": "0:08:06", "remaining_time": "0:00:00"}
28
+ {"current_steps": 27, "total_steps": 27, "epoch": 2.9454545454545453, "percentage": 100.0, "elapsed_time": "0:09:33", "remaining_time": "0:00:00"}