Hugging Face's logo

mlfoundations-dev
/
stackexchange_avp

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
907c669
·
verified ·
1 Parent(s): 5743439

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:b93b3b55bbaf6a648b061998a0133584a9fb453f08352526f325a6dc1b94f96f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb0448161f258178b49a2eb271cb4c601d21327f20bf1bf587d48dc4b3651ee
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4faf871c280897ac1d45081b597c01ffc427f74f39551e3dee3fc5168d544645
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e525f43e6dd437697d85ca5016e0d37c5619afbd0105b216063b745e9eb1ce
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62b9a9aa2836fa726aa38b4a500986e63c688cd45bd13c0b89de3da4d3554845
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17cd309367331a001d1651f5828ba93dd2c6249ac1ce7d10ba0aec9f82d0276d
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:e9a41279d63adee052be8bc72ce7fa70779d1814d78b6818f9d1912bd3ab0645
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4d1b369f2db624c575ac59e9cbd84e7671df2f5c8301aec85cada6093f5730
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 42, "loss": 1.0732, "lr": 5e-06, "epoch": 1.4035087719298245, "percentage": 47.62, "elapsed_time": "0:20:42", "remaining_time": "0:22:47"}
4
  {"current_steps": 28, "total_steps": 42, "eval_loss": 0.9422828555107117, "epoch": 1.9649122807017543, "percentage": 66.67, "elapsed_time": "0:29:04", "remaining_time": "0:14:32"}
5
  {"current_steps": 30, "total_steps": 42, "loss": 1.0059, "lr": 5e-06, "epoch": 2.1052631578947367, "percentage": 71.43, "elapsed_time": "0:31:46", "remaining_time": "0:12:42"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 42, "loss": 1.0732, "lr": 5e-06, "epoch": 1.4035087719298245, "percentage": 47.62, "elapsed_time": "0:20:42", "remaining_time": "0:22:47"}
4
  {"current_steps": 28, "total_steps": 42, "eval_loss": 0.9422828555107117, "epoch": 1.9649122807017543, "percentage": 66.67, "elapsed_time": "0:29:04", "remaining_time": "0:14:32"}
5
  {"current_steps": 30, "total_steps": 42, "loss": 1.0059, "lr": 5e-06, "epoch": 2.1052631578947367, "percentage": 71.43, "elapsed_time": "0:31:46", "remaining_time": "0:12:42"}
6
+ {"current_steps": 40, "total_steps": 42, "loss": 0.8793, "lr": 5e-06, "epoch": 2.807017543859649, "percentage": 95.24, "elapsed_time": "0:41:24", "remaining_time": "0:02:04"}
7
+ {"current_steps": 42, "total_steps": 42, "eval_loss": 0.91075199842453, "epoch": 2.9473684210526314, "percentage": 100.0, "elapsed_time": "0:44:47", "remaining_time": "0:00:00"}
8
+ {"current_steps": 42, "total_steps": 42, "epoch": 2.9473684210526314, "percentage": 100.0, "elapsed_time": "0:46:02", "remaining_time": "0:00:00"}