Hugging Face's logo

mlfoundations-dev
/
stackexchange_emacs

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
2456306
·
verified ·
1 Parent(s): e787175

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feb7b1aaf5a3ef668306839b8cfc6563eef692c314f06ecb9b5ca4c508ccaa61
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d30a4be07b060d8b05de391bd4feae65049adb718a1e1acd0f94ce24733407e
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:a279ba35117448ef43756cd72d35c16d4e26ac36cfaa9afe6822cf518ee3eb5d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77055e5bbbd9b2cc2fa43915551f9f8b7cce593f4f49679c67ace00b02e452ae
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b390f79f5814d8b467a4fc7fb652792f806871f5cbbeb94808bc849c748cdf8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7fd9a7bc054c4ea66eff52af21dfa6628fc691fc3ccca74a950125b2422074
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:f44e6138a02ed8e9a6df23ca6260d8bac3e32095204bb6043da5b7989a024282
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c8e9171c3f57aaefcd7b86c0dde26c2e012bee94421f1f4065f465bf464baf
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.8838, "lr": 5e-06, "epoch": 0.5925925925925926, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:21"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.8462, "lr": 5e-06, "epoch": 0.8888888888888888, "percentage": 30.3, "elapsed_time": "0:16:01", "remaining_time": "0:36:51"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.8316775560379028, "epoch": 0.9777777777777777, "percentage": 33.33, "elapsed_time": "0:18:24", "remaining_time": "0:36:48"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.8838, "lr": 5e-06, "epoch": 0.5925925925925926, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:21"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.8462, "lr": 5e-06, "epoch": 0.8888888888888888, "percentage": 30.3, "elapsed_time": "0:16:01", "remaining_time": "0:36:51"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.8316775560379028, "epoch": 0.9777777777777777, "percentage": 33.33, "elapsed_time": "0:18:24", "remaining_time": "0:36:48"}
5
+ {"current_steps": 40, "total_steps": 99, "loss": 0.8292, "lr": 5e-06, "epoch": 1.1851851851851851, "percentage": 40.4, "elapsed_time": "0:22:58", "remaining_time": "0:33:53"}
6
+ {"current_steps": 50, "total_steps": 99, "loss": 0.7806, "lr": 5e-06, "epoch": 1.4814814814814814, "percentage": 50.51, "elapsed_time": "0:28:15", "remaining_time": "0:27:41"}
7
+ {"current_steps": 60, "total_steps": 99, "loss": 0.7626, "lr": 5e-06, "epoch": 1.7777777777777777, "percentage": 60.61, "elapsed_time": "0:33:33", "remaining_time": "0:21:48"}
8
+ {"current_steps": 67, "total_steps": 99, "eval_loss": 0.7775214910507202, "epoch": 1.9851851851851852, "percentage": 67.68, "elapsed_time": "0:37:50", "remaining_time": "0:18:04"}
9
+ {"current_steps": 70, "total_steps": 99, "loss": 0.7619, "lr": 5e-06, "epoch": 2.074074074074074, "percentage": 70.71, "elapsed_time": "0:40:30", "remaining_time": "0:16:46"}