Hugging Face's logo

mlfoundations-dev
/
stackoverflow_5000tasks_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
bc69414
·
verified ·
1 Parent(s): f5f9274

Training in progress, epoch 3

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 sha256:973fbe57928254dacad753290724c874d67b28c8e37b3d5ce72f1d0861c5e552
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e523bd2b29f10c3d16e37f0c7db2d3a2bd49e1860fafb8c00d278dd5982f5c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a508af6c992cc0c1f31093cc3c336f2386643fc270427d439a27646a5b80516
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0538f06e55dc68a7c1c371cb6ea764131fc018abe39e97b07f50b582dde87978
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52385c3ab716ac1b8981793332dfbede0045acd5aeb4496171f51fef87caa87b
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f569acfe386a8b8adf3bbc140a6eb99aa343eba91f22c12a0cc5ce7d8e7c1efd
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:e1d5c61266288a993f66e244041b328c00ca85b44e692716b1e3e64f13d5ce2f
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3bcd11b64650cccbeb9628966a0943715f9915a953f64a6acd93328d490dc23
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,8 @@
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7796, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:41", "remaining_time": "0:25:15"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7696, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:38:59", "remaining_time": "0:19:29"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.803409218788147, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:24", "remaining_time": "0:19:42"}
 
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7796, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:41", "remaining_time": "0:25:15"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7696, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:38:59", "remaining_time": "0:19:29"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.803409218788147, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:24", "remaining_time": "0:19:42"}
10
+ {"current_steps": 80, "total_steps": 105, "loss": 0.7186, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:46:00", "remaining_time": "0:14:22"}
11
+ {"current_steps": 90, "total_steps": 105, "loss": 0.7148, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:51:20", "remaining_time": "0:08:33"}
12
+ {"current_steps": 100, "total_steps": 105, "loss": 0.7087, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:56:38", "remaining_time": "0:02:49"}
13
+ {"current_steps": 105, "total_steps": 105, "eval_loss": 0.7998417019844055, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:00:57", "remaining_time": "0:00:00"}
14
+ {"current_steps": 105, "total_steps": 105, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:02:11", "remaining_time": "0:00:00"}