Hugging Face's logo

mlfoundations-dev
/
stackexchange_music

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
b872fca
·
verified ·
1 Parent(s): 0878be4

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3105aa09ded631cb1856b30d46a3f315a085ec21d7c4f5bf64ba74599fd9666
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab89e6e74f74dbad64f3b5941d5c7fcf6cc94e6b0e6e73c35cd12036bf828f2
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f02db7aec14a6d1c03e40dda0a104ea4d608ea9baa43f5fe30f4cbb99620243
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3da36d8d36d8fcbe77064311abd22ac1f02f10d15d6a119097ed2ff868ac1b
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c39b474179779d06e2a2bc0d3a530bad0eff226d3d2a9693bf39c712c32471
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f133b2b4b694584677e1aae510329992dcdeb9eb14b4a5a6839af4515c84631c
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad8304992044873ae82ddb0cf45207f88562c38af3e9298a915b6e7aef91ea2
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3e8502d0a46ce4a64f98a01149bf522b4381b127a0666179fc55026eba373ac
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 20, "total_steps": 84, "loss": 1.088, "lr": 5e-06, "epoch": 0.7017543859649122, "percentage": 23.81, "elapsed_time": "0:10:38", "remaining_time": "0:34:04"}
3
  {"current_steps": 28, "total_steps": 84, "eval_loss": 1.035239577293396, "epoch": 0.9824561403508771, "percentage": 33.33, "elapsed_time": "0:15:17", "remaining_time": "0:30:34"}
4
  {"current_steps": 30, "total_steps": 84, "loss": 1.1323, "lr": 5e-06, "epoch": 1.0657894736842106, "percentage": 35.71, "elapsed_time": "0:17:27", "remaining_time": "0:31:26"}
 
 
 
 
2
  {"current_steps": 20, "total_steps": 84, "loss": 1.088, "lr": 5e-06, "epoch": 0.7017543859649122, "percentage": 23.81, "elapsed_time": "0:10:38", "remaining_time": "0:34:04"}
3
  {"current_steps": 28, "total_steps": 84, "eval_loss": 1.035239577293396, "epoch": 0.9824561403508771, "percentage": 33.33, "elapsed_time": "0:15:17", "remaining_time": "0:30:34"}
4
  {"current_steps": 30, "total_steps": 84, "loss": 1.1323, "lr": 5e-06, "epoch": 1.0657894736842106, "percentage": 35.71, "elapsed_time": "0:17:27", "remaining_time": "0:31:26"}
5
+ {"current_steps": 40, "total_steps": 84, "loss": 0.9925, "lr": 5e-06, "epoch": 1.4166666666666667, "percentage": 47.62, "elapsed_time": "0:22:43", "remaining_time": "0:24:59"}
6
+ {"current_steps": 50, "total_steps": 84, "loss": 0.9729, "lr": 5e-06, "epoch": 1.7675438596491229, "percentage": 59.52, "elapsed_time": "0:27:58", "remaining_time": "0:19:01"}
7
+ {"current_steps": 56, "total_steps": 84, "eval_loss": 0.9812449812889099, "epoch": 1.9780701754385965, "percentage": 66.67, "elapsed_time": "0:31:33", "remaining_time": "0:15:46"}