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
20f9c09
·
verified ·
1 Parent(s): ce4e2fd

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a64159cf393440879f2bfa3d5469e30154045fb6a7d85ef20efb374cb372dd6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb1aae094d2eb2c4cb2dea3e819ea62773e78204442a459742be2b77b17d025
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5855cb40a89df9e8c8891d6fa5e4098e180e488374ed3fe709c6d150f54e4fe4
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ddcad90fddbac6771347c6c8fc343210a33d9212ddf86251090ea7e37a0068
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eb21eeac97eb349136271713bbdeaa9258e84d37d903bacd4353cb75abf4371
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d443eddbaf4bac94cc269c0cbabfc47cf73945d94f2e5e011992cf5fb88efe0e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21b8d1eb2758949c557f473f357e4d227723349f86c869ab04e619e4f81a377b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a409ffc2e02b8c540b0266b09f088dd4fb683892cfb7dffeb3536e2ce0ad2461
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,7 @@
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.0776, "lr": 5e-06, "epoch": 0.418848167539267, "percentage": 14.49, "elapsed_time": "0:09:41", "remaining_time": "0:57:13"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 0.9655, "lr": 5e-06, "epoch": 0.837696335078534, "percentage": 28.99, "elapsed_time": "0:19:19", "remaining_time": "0:47:21"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 0.9337097406387329, "epoch": 0.9633507853403142, "percentage": 33.33, "elapsed_time": "0:23:17", "remaining_time": "0:46:34"}
 
 
 
 
 
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.0776, "lr": 5e-06, "epoch": 0.418848167539267, "percentage": 14.49, "elapsed_time": "0:09:41", "remaining_time": "0:57:13"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 0.9655, "lr": 5e-06, "epoch": 0.837696335078534, "percentage": 28.99, "elapsed_time": "0:19:19", "remaining_time": "0:47:21"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 0.9337097406387329, "epoch": 0.9633507853403142, "percentage": 33.33, "elapsed_time": "0:23:17", "remaining_time": "0:46:34"}
4
+ {"current_steps": 30, "total_steps": 69, "loss": 0.9481, "lr": 5e-06, "epoch": 1.2670157068062826, "percentage": 43.48, "elapsed_time": "0:30:37", "remaining_time": "0:39:49"}
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"}