Hugging Face's logo

mlfoundations-dev
/
stackexchange_cooking

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
a853013
·
verified ·
1 Parent(s): 20f9c09

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 sha256:5fb1aae094d2eb2c4cb2dea3e819ea62773e78204442a459742be2b77b17d025
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d1a95c08aeaa213ddab442f039477c4b09fcab1b5b404b5dde2bc9e32764cb
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:c7ddcad90fddbac6771347c6c8fc343210a33d9212ddf86251090ea7e37a0068
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66afd953ab371a684cf39c751f2aa29ec059c160d4f4009f2e8866d5f59acf5b
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:d443eddbaf4bac94cc269c0cbabfc47cf73945d94f2e5e011992cf5fb88efe0e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd083d90a600b1762b4da2c9325376fb453a79e417aeebc6d233cec3cd7c8b9
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:a409ffc2e02b8c540b0266b09f088dd4fb683892cfb7dffeb3536e2ce0ad2461
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2783e23b75a241dd20e96864e473f4596410126aa5895a7a74da3b39cc5d3b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -5,3 +5,6 @@
5
  {"current_steps": 40, "total_steps": 69, "loss": 0.8776, "lr": 5e-06, "epoch": 1.6858638743455496, "percentage": 57.97, "elapsed_time": "0:40:15", "remaining_time": "0:29:11"}
6
  {"current_steps": 47, "total_steps": 69, "eval_loss": 0.8832862973213196, "epoch": 1.9790575916230366, "percentage": 68.12, "elapsed_time": "0:47:38", "remaining_time": "0:22:18"}
7
  {"current_steps": 50, "total_steps": 69, "loss": 0.8826, "lr": 5e-06, "epoch": 2.115183246073298, "percentage": 72.46, "elapsed_time": "0:51:30", "remaining_time": "0:19:34"}
 
 
 
 
5
  {"current_steps": 40, "total_steps": 69, "loss": 0.8776, "lr": 5e-06, "epoch": 1.6858638743455496, "percentage": 57.97, "elapsed_time": "0:40:15", "remaining_time": "0:29:11"}
6
  {"current_steps": 47, "total_steps": 69, "eval_loss": 0.8832862973213196, "epoch": 1.9790575916230366, "percentage": 68.12, "elapsed_time": "0:47:38", "remaining_time": "0:22:18"}
7
  {"current_steps": 50, "total_steps": 69, "loss": 0.8826, "lr": 5e-06, "epoch": 2.115183246073298, "percentage": 72.46, "elapsed_time": "0:51:30", "remaining_time": "0:19:34"}
8
+ {"current_steps": 60, "total_steps": 69, "loss": 0.8099, "lr": 5e-06, "epoch": 2.5340314136125652, "percentage": 86.96, "elapsed_time": "1:01:09", "remaining_time": "0:09:10"}
9
+ {"current_steps": 69, "total_steps": 69, "eval_loss": 0.85880446434021, "epoch": 2.9109947643979055, "percentage": 100.0, "elapsed_time": "1:11:32", "remaining_time": "0:00:00"}
10
+ {"current_steps": 69, "total_steps": 69, "epoch": 2.9109947643979055, "percentage": 100.0, "elapsed_time": "1:12:46", "remaining_time": "0:00:00"}