Hugging Face's logo

mlfoundations-dev
/
stackexchange_blender

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
e9f4bb4
·
verified ·
1 Parent(s): a575761

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 sha256:4c0834c1399a2976388bdc876563ac71dba9a5aec7c9a9e570f932d10775eee8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f62725acfdb8f4508a24e74631a0264e94aa4ae0e6fb09c887c95ad1d2ec0f4
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:b9ca31338e77041f0d23c125e1c84dfd6110c2b6ae216a72a6ff1d1d7e55c158
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3774b0e006484023d7fc3d460545df7729f50c6cc978fd4364942fa03260d92c
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:cf41cf101438d7cd422d65d6bb91c5a1a28a103e6ff4a2ffcd2b333fa9c4d61a
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4095cab2a19b39c4ce150cba3237bfd39b1089f524cf64065f91990e24e0e9
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7651cdc8febcdd78946c61b07531041d87178787391e4536f791a603e561611e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5968e60a29dddb01336654ecd88e76fd4425f9b09bdb4bf8b25171fbc9c224
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 96, "loss": 1.0297, "lr": 5e-06, "epoch": 0.6130268199233716, "percentage": 20.83, "elapsed_time": "0:19:16", "remaining_time": "1:13:13"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.9678, "lr": 5e-06, "epoch": 0.9195402298850575, "percentage": 31.25, "elapsed_time": "0:28:51", "remaining_time": "1:03:28"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.941736102104187, "epoch": 0.9808429118773946, "percentage": 33.33, "elapsed_time": "0:31:50", "remaining_time": "1:03:40"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 96, "loss": 1.0297, "lr": 5e-06, "epoch": 0.6130268199233716, "percentage": 20.83, "elapsed_time": "0:19:16", "remaining_time": "1:13:13"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.9678, "lr": 5e-06, "epoch": 0.9195402298850575, "percentage": 31.25, "elapsed_time": "0:28:51", "remaining_time": "1:03:28"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.941736102104187, "epoch": 0.9808429118773946, "percentage": 33.33, "elapsed_time": "0:31:50", "remaining_time": "1:03:40"}
5
+ {"current_steps": 40, "total_steps": 96, "loss": 0.9658, "lr": 5e-06, "epoch": 1.2298850574712643, "percentage": 41.67, "elapsed_time": "0:40:11", "remaining_time": "0:56:16"}
6
+ {"current_steps": 50, "total_steps": 96, "loss": 0.899, "lr": 5e-06, "epoch": 1.5363984674329503, "percentage": 52.08, "elapsed_time": "0:49:46", "remaining_time": "0:45:47"}
7
+ {"current_steps": 60, "total_steps": 96, "loss": 0.8809, "lr": 5e-06, "epoch": 1.842911877394636, "percentage": 62.5, "elapsed_time": "0:59:21", "remaining_time": "0:35:36"}
8
+ {"current_steps": 65, "total_steps": 96, "eval_loss": 0.8847602605819702, "epoch": 1.996168582375479, "percentage": 67.71, "elapsed_time": "1:04:41", "remaining_time": "0:30:50"}