Hugging Face's logo

mlfoundations-dev
/
stackexchange_movies

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
098a13e
·
verified ·
1 Parent(s): facb033

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:affd6cbb5acff325ab765599651b5c601107967e1d76fbcd69f90dcdaa4dfba2
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d8623d8908b524e7f463ae655724687bde4829a145a1206d01fac607846fa1
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f6743df17c7d10e15af1671b208aaec9cc34d01a0b15838dcec72e8b9833486
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19d546c89bb3d7a2fdd55086b98a7e1d529f4e35ffaab4d09ae8168026a24f54
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c401107a1ce8dd50513c812e814dacef3719c6fe5ed1365ca9f08cba2e15766
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d173b997f79aac295b71d9ddf8e38e1faf7989e70310588f8f81e6c951391a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a2d0248c9899dd3e09e8197801d444ed03e5c4b3caaaca77aa443fd521a88b5
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba6ada88d1284e73701814a8e5020f4c04ccd9da0d65d9f773c9eab80d60946
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 57, "loss": 1.3652, "lr": 5e-06, "epoch": 0.5128205128205128, "percentage": 17.54, "elapsed_time": "0:05:28", "remaining_time": "0:25:42"}
2
  {"current_steps": 19, "total_steps": 57, "eval_loss": 1.1945005655288696, "epoch": 0.9743589743589743, "percentage": 33.33, "elapsed_time": "0:10:48", "remaining_time": "0:21:36"}
3
  {"current_steps": 20, "total_steps": 57, "loss": 1.2843, "lr": 5e-06, "epoch": 1.0256410256410255, "percentage": 35.09, "elapsed_time": "0:12:18", "remaining_time": "0:22:46"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 57, "loss": 1.3652, "lr": 5e-06, "epoch": 0.5128205128205128, "percentage": 17.54, "elapsed_time": "0:05:28", "remaining_time": "0:25:42"}
2
  {"current_steps": 19, "total_steps": 57, "eval_loss": 1.1945005655288696, "epoch": 0.9743589743589743, "percentage": 33.33, "elapsed_time": "0:10:48", "remaining_time": "0:21:36"}
3
  {"current_steps": 20, "total_steps": 57, "loss": 1.2843, "lr": 5e-06, "epoch": 1.0256410256410255, "percentage": 35.09, "elapsed_time": "0:12:18", "remaining_time": "0:22:46"}
4
+ {"current_steps": 30, "total_steps": 57, "loss": 1.1511, "lr": 5e-06, "epoch": 1.5384615384615383, "percentage": 52.63, "elapsed_time": "0:17:39", "remaining_time": "0:15:53"}
5
+ {"current_steps": 39, "total_steps": 57, "eval_loss": 1.1268930435180664, "epoch": 2.0, "percentage": 68.42, "elapsed_time": "0:22:37", "remaining_time": "0:10:26"}
6
+ {"current_steps": 40, "total_steps": 57, "loss": 1.1621, "lr": 5e-06, "epoch": 2.051282051282051, "percentage": 70.18, "elapsed_time": "0:24:25", "remaining_time": "0:10:22"}