Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_1p

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
3818671
·
verified ·
1 Parent(s): 933890f

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:683b3e07da6091c355d620d75ff9048c60765d787ff2dac60eaa6ce57c4a4415
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef8be544c5d80c32f98ef58511791955817d4f50b33d4c1515f3406eb09a276
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:eb891d619b5d22ffc882d176863440124ba25e3358f93e12d7014d69fbdae5cd
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcef32c0aed8b5282ea9aabf6cc121db83c46a53a0e8be12e701b6cb1dd7f392
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:b0452e4ad3be511d6ce461bcf7e5ec74a9cf3a267b7ede2b213e234a10634f11
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d49827660d7ec5f43815d8ea52b3c6e28ef97f2bd99c8e824663cc91a9019a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d296870450acdb9b878a6a72ea0dcc67c839932d1c22dee2b4e75a91db90966
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a632c80027233d4ebbb4e1112f441db424d57fcb46699d6d8ddf6c480071d7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,7 @@
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8513, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:12", "remaining_time": "0:40:30"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8261556029319763, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:17", "remaining_time": "0:38:35"}
5
  {"current_steps": 40, "total_steps": 105, "loss": 0.8127, "lr": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:23:09", "remaining_time": "0:37:37"}
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8513, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:12", "remaining_time": "0:40:30"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8261556029319763, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:17", "remaining_time": "0:38:35"}
5
  {"current_steps": 40, "total_steps": 105, "loss": 0.8127, "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": 0.7824, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:28:29", "remaining_time": "0:31:20"}
7
+ {"current_steps": 60, "total_steps": 105, "loss": 0.7716, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:48", "remaining_time": "0:25:21"}
8
+ {"current_steps": 70, "total_steps": 105, "loss": 0.7678, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:09", "remaining_time": "0:19:34"}
9
+ {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7982695698738098, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:34", "remaining_time": "0:19:47"}