Hugging Face's logo

mlfoundations-dev
/
stackexchange_stackoverflow

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
a99f11d
·
verified ·
1 Parent(s): d3f0472

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0ba93dda1ef97eebe815c4e6dbbefa7d4c322b6f1dbe17fb152657b3a7491d6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28847d940ed0b879b0ed614ccc58f9be4995b0ccf0ef853e83154e43725fa16c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ebaa953f57255ecda340e491e7fa28d272adc62c2bbf700e929f7b36fcc3796
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5010a332a9c663a12a706b4eb79122f4feeb56cc012e3fa3c17ee77336ea0c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ce82ec8a69d512ca6fd49a1445be8c5ae48ca8d7bf97fe33d069f41447a2a64
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7dba0d9e4b64f9e7cb21a1bf03da2908d456d877d04bec64abff5f3bdbd749d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8754ed80aa0a83ee2e83f7edae0bb25699b000f5ff24f152e4b7e6dedecbbd7b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cfc1bec53275e2d5e8b1ff081b0c8d1cb224d4f4913ee33f5505f905daf359
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8825, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:48", "remaining_time": "0:45:54"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8516, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:09", "remaining_time": "0:40:22"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8306872248649597, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:12", "remaining_time": "0:38:24"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8825, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:48", "remaining_time": "0:45:54"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8516, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:09", "remaining_time": "0:40:22"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8306872248649597, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:12", "remaining_time": "0:38:24"}
5
+ {"current_steps": 40, "total_steps": 105, "loss": 0.8187, "lr": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:23:09", "remaining_time": "0:37:37"}
6
+ {"current_steps": 50, "total_steps": 105, "loss": 0.7827, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:28:28", "remaining_time": "0:31:19"}
7
+ {"current_steps": 60, "total_steps": 105, "loss": 0.7745, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:49", "remaining_time": "0:25:21"}
8
+ {"current_steps": 70, "total_steps": 105, "loss": 0.7677, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:07", "remaining_time": "0:19:33"}
9
+ {"current_steps": 70, "total_steps": 105, "eval_loss": 0.8009844422340393, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}