Hugging Face's logo

mlfoundations-dev
/
stackexchange_cstheory

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
1bff27c
·
verified ·
1 Parent(s): 00ef8e8

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:d16b5eca4864e3502a28a9091e61e54060065e000f6ffdbd643ddf7b1c28bdf6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a500b29529aca2799c9888d20ba39cc5b02af592df5f5fd37a8a0c72d192971e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d573d16145f9f2f27f36ba276cc9a05f9eeace53b71cbbc05c2933c31024151
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74ac1c40ff4728c9af52f34cf30ddd5d21d5b14d1a5c5b6f9b5d698088a87b9
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:d5435ecb3772a03e3de36c2abd17a45d70bc165ba44546802fc632b359a20e38
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a194afa244a5a08353eb66e7cc8c4a2dafef4f29ce5fc8a14385c523aff62af
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d3b4dc1ea64ea7acaa8c4eb3e56542bdacc0b258e0b0e57a5f5500bf71c4bce
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec5775ff68b134710fdf4c92eba854c498728ef27f9b9b2ca27262382043ae8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.2052, "lr": 5e-06, "epoch": 0.42780748663101603, "percentage": 14.49, "elapsed_time": "0:09:45", "remaining_time": "0:57:31"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 1.0858, "lr": 5e-06, "epoch": 0.8556149732620321, "percentage": 28.99, "elapsed_time": "0:19:25", "remaining_time": "0:47:35"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 1.0545072555541992, "epoch": 0.983957219251337, "percentage": 33.33, "elapsed_time": "0:22:59", "remaining_time": "0:45:59"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.2052, "lr": 5e-06, "epoch": 0.42780748663101603, "percentage": 14.49, "elapsed_time": "0:09:45", "remaining_time": "0:57:31"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 1.0858, "lr": 5e-06, "epoch": 0.8556149732620321, "percentage": 28.99, "elapsed_time": "0:19:25", "remaining_time": "0:47:35"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 1.0545072555541992, "epoch": 0.983957219251337, "percentage": 33.33, "elapsed_time": "0:22:59", "remaining_time": "0:45:59"}
4
+ {"current_steps": 30, "total_steps": 69, "loss": 1.1308, "lr": 5e-06, "epoch": 1.2887700534759359, "percentage": 43.48, "elapsed_time": "0:30:39", "remaining_time": "0:39:51"}
5
+ {"current_steps": 40, "total_steps": 69, "loss": 1.0111, "lr": 5e-06, "epoch": 1.7165775401069518, "percentage": 57.97, "elapsed_time": "0:40:18", "remaining_time": "0:29:13"}
6
+ {"current_steps": 46, "total_steps": 69, "eval_loss": 1.0155441761016846, "epoch": 1.9732620320855614, "percentage": 66.67, "elapsed_time": "0:46:59", "remaining_time": "0:23:29"}