Hugging Face's logo

mlfoundations-dev
/
stackexchange_opensource

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
41da23f
·
verified ·
1 Parent(s): 8cbd936

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 sha256:0010f9bcd517acacd09c47f9039bc5a3d08c6ef7118169fec1668efdde696ade
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fea2a81f86e0c20f3dcf017abf706a0986f158df901e9c5c0c74587d3bf941a
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90ae69bb5be47079909c01ece174ee3948b2338442f6c5481904953fa38d34ad
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d5aa626f8782eb99c20853aa50c5ea981f632e5a3cae6d1a046cb7e537064b
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ef4d34921ceb2478d3391ba2fe2c3a8a656111138e60e6778629314d8eb0941
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f156518eaadf3f691e072e1fab4764c59b35bb1e9d283546f2ad6ae2b483d755
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dc13af15e753104b808c6f9e8f9d69b028e57b5f66f69a4c835eda7181409c4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab848225c3eaa3ad201d7459b81cabfdcb0019e72e0868105978e13408a0cc16
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 1.096757173538208, "epoch": 0.9655172413793104, "percentage": 33.33, "elapsed_time": "0:04:02", "remaining_time": "0:08:04"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 1.2507, "lr": 5e-06, "epoch": 1.396551724137931, "percentage": 47.62, "elapsed_time": "0:06:44", "remaining_time": "0:07:25"}
3
  {"current_steps": 14, "total_steps": 21, "eval_loss": 1.0302181243896484, "epoch": 1.9482758620689655, "percentage": 66.67, "elapsed_time": "0:09:06", "remaining_time": "0:04:33"}
 
 
 
 
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 1.096757173538208, "epoch": 0.9655172413793104, "percentage": 33.33, "elapsed_time": "0:04:02", "remaining_time": "0:08:04"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 1.2507, "lr": 5e-06, "epoch": 1.396551724137931, "percentage": 47.62, "elapsed_time": "0:06:44", "remaining_time": "0:07:25"}
3
  {"current_steps": 14, "total_steps": 21, "eval_loss": 1.0302181243896484, "epoch": 1.9482758620689655, "percentage": 66.67, "elapsed_time": "0:09:06", "remaining_time": "0:04:33"}
4
+ {"current_steps": 20, "total_steps": 21, "loss": 1.0989, "lr": 5e-06, "epoch": 2.793103448275862, "percentage": 95.24, "elapsed_time": "0:13:28", "remaining_time": "0:00:40"}
5
+ {"current_steps": 21, "total_steps": 21, "eval_loss": 0.9940618276596069, "epoch": 2.9310344827586206, "percentage": 100.0, "elapsed_time": "0:15:25", "remaining_time": "0:00:00"}
6
+ {"current_steps": 21, "total_steps": 21, "epoch": 2.9310344827586206, "percentage": 100.0, "elapsed_time": "0:16:38", "remaining_time": "0:00:00"}