Hugging Face's logo

mlfoundations-dev
/
stackexchange_chess

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
6179059
·
verified ·
1 Parent(s): bc383bd

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:fd27ed888eb52f0f97536c51a4ec6d71d14babb272bb62ff0cac9f9d127ab498
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b901a8b77c9e0dd5369729f63259cd1a91221c5f70a92b1f754d86d00ec50bd0
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6664aaf0e466478c311b32d53cf2b7ccd6b72fb96285253891bbf90fa58afbdc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f60894d888cfcbbd55b6c0654cff0cb2135758aaf4a70f56c517226ea9d784b
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:d79d8271912886ce7f1a0fb53590572aec59e0c70faa1a8dc09c86d27b285c46
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb311c1f2240911d9104ea63fd080cf43429c1f640c19cfdd93122d696fd630
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99c78186482d8abc5be3cb6ddfb916bb912598ef59a17af5d65228b494fbdb95
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd019a1071abde98fbbdd73579328ddcb1eef9ae941b192541ba9b2b149016db
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 48, "loss": 1.2402, "lr": 5e-06, "epoch": 1.2074074074074075, "percentage": 41.67, "elapsed_time": "0:20:48", "remaining_time": "0:29:08"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 1.115, "lr": 5e-06, "epoch": 1.8, "percentage": 62.5, "elapsed_time": "0:30:27", "remaining_time": "0:18:16"}
5
  {"current_steps": 33, "total_steps": 48, "eval_loss": 1.117397665977478, "epoch": 1.9777777777777779, "percentage": 68.75, "elapsed_time": "0:33:37", "remaining_time": "0:15:17"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 48, "loss": 1.2402, "lr": 5e-06, "epoch": 1.2074074074074075, "percentage": 41.67, "elapsed_time": "0:20:48", "remaining_time": "0:29:08"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 1.115, "lr": 5e-06, "epoch": 1.8, "percentage": 62.5, "elapsed_time": "0:30:27", "remaining_time": "0:18:16"}
5
  {"current_steps": 33, "total_steps": 48, "eval_loss": 1.117397665977478, "epoch": 1.9777777777777779, "percentage": 68.75, "elapsed_time": "0:33:37", "remaining_time": "0:15:17"}
6
+ {"current_steps": 40, "total_steps": 48, "loss": 1.1122, "lr": 5e-06, "epoch": 2.414814814814815, "percentage": 83.33, "elapsed_time": "0:41:30", "remaining_time": "0:08:18"}
7
+ {"current_steps": 48, "total_steps": 48, "eval_loss": 1.0861635208129883, "epoch": 2.888888888888889, "percentage": 100.0, "elapsed_time": "0:50:44", "remaining_time": "0:00:00"}
8
+ {"current_steps": 48, "total_steps": 48, "epoch": 2.888888888888889, "percentage": 100.0, "elapsed_time": "0:51:58", "remaining_time": "0:00:00"}