Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_gpt4_llm

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
b259219
•
1 Parent(s): e6135fd

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:ab2eca1072037d574fae8f32a6fa4cd70114c8c13cf978ef769b9da91a883731
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e8a397412dcfbce6de8e6b3d05fd22dc288071859336e1a86589c8cde6ed42
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:540b15961cdb5fbec0efd7fb96bf7ca3fcf9a32395e183ff88495829a1e686be
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355e7e0c61920c4a3325cb2baa06e046d4c2ad0491f20df075f1d7a6f4e65b47
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08611d789e5203939a340af8e1d655ba6044e380aeef79a03c0a2ccd02c9b112
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f9f169b3fbaabf6823159b948caa96ed62e0335ac08b58473cfc5dc598a2fe
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ebe54386ee1c33e986c4c723b79667c901b9a51edf9b8718636d935ad080249
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36346babf97a6555ab550a11db637a0fb9c48455ab56c3bf35575bd38ab1460
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,2 +1,5 @@
1
  {"current_steps": 4, "total_steps": 12, "eval_loss": 1.0328664779663086, "epoch": 0.9142857142857143, "percentage": 33.33, "elapsed_time": "0:02:30", "remaining_time": "0:05:00"}
2
  {"current_steps": 8, "total_steps": 12, "eval_loss": 0.9912787079811096, "epoch": 1.8285714285714287, "percentage": 66.67, "elapsed_time": "0:05:49", "remaining_time": "0:02:54"}
 
 
 
 
1
  {"current_steps": 4, "total_steps": 12, "eval_loss": 1.0328664779663086, "epoch": 0.9142857142857143, "percentage": 33.33, "elapsed_time": "0:02:30", "remaining_time": "0:05:00"}
2
  {"current_steps": 8, "total_steps": 12, "eval_loss": 0.9912787079811096, "epoch": 1.8285714285714287, "percentage": 66.67, "elapsed_time": "0:05:49", "remaining_time": "0:02:54"}
3
+ {"current_steps": 10, "total_steps": 12, "loss": 1.1915, "learning_rate": 5e-06, "epoch": 2.2857142857142856, "percentage": 83.33, "elapsed_time": "0:07:35", "remaining_time": "0:01:31"}
4
+ {"current_steps": 12, "total_steps": 12, "eval_loss": 0.974350094795227, "epoch": 2.742857142857143, "percentage": 100.0, "elapsed_time": "0:09:33", "remaining_time": "0:00:00"}
5
+ {"current_steps": 12, "total_steps": 12, "epoch": 2.742857142857143, "percentage": 100.0, "elapsed_time": "0:10:29", "remaining_time": "0:00:00"}