Hugging Face's logo

Bifrost-AI
/
Phi-4-bifrost-sol-3.8B

Text Generation
Transformers
Safetensors
English
phi3
code
finance
chat
large-language-model
conversational
custom_code
text-generation-inference
Model card Files Community
BifrostTitan commited on
Commit
dcb6f1e
·
verified ·
1 Parent(s): e844182

Upload 17 files

Browse files
Files changed (7) hide show
  1. all_results.json +10 -10
  2. eval_results.json +5 -5
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
  5. train_results.json +5 -5
  6. trainer_state.json +0 -0
  7. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "eval_loss": 0.6804908514022827,
3
- "eval_runtime": 177.2206,
4
- "eval_samples": 998,
5
- "eval_samples_per_second": 5.631,
6
- "eval_steps_per_second": 5.631,
7
- "total_flos": 2.391287728875725e+16,
8
- "train_loss": 0.8806598528862,
9
- "train_runtime": 34392.665,
10
- "train_samples_per_second": 0.073,
11
- "train_steps_per_second": 0.073
12
  }
 
1
  {
2
+ "eval_loss": 0.6124746203422546,
3
+ "eval_runtime": 3088.5039,
4
+ "eval_samples": 1000,
5
+ "eval_samples_per_second": 0.324,
6
+ "eval_steps_per_second": 0.324,
7
+ "total_flos": 2.8742560290791424e+16,
8
+ "train_loss": 0.8452948161760966,
9
+ "train_runtime": 60165.202,
10
+ "train_samples_per_second": 0.05,
11
+ "train_steps_per_second": 0.05
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "eval_loss": 0.6804908514022827,
3
- "eval_runtime": 177.2206,
4
- "eval_samples": 998,
5
- "eval_samples_per_second": 5.631,
6
- "eval_steps_per_second": 5.631
7
  }
 
1
  {
2
+ "eval_loss": 0.6124746203422546,
3
+ "eval_runtime": 3088.5039,
4
+ "eval_samples": 1000,
5
+ "eval_samples_per_second": 0.324,
6
+ "eval_steps_per_second": 0.324
7
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb4c464bb123dd4450dbb0b3d2f984fe51a4230ea0a63d35d8964c9b60a973b2
3
  size 4903637712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9a206a519d363ffb6bc6f5a49218ea310f4e67af6b60f68b1c4c8ab52fd0d22
3
  size 4903637712
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf2d1c287c585138de22af80602a40be965f1b0793865e86eb8b9067d7b31f4e
3
  size 2768428504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:258a71093bae4921f61e8b438c570cd49869e77e33cb7d823eed440218629bfa
3
  size 2768428504
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "total_flos": 2.391287728875725e+16,
3
- "train_loss": 0.8806598528862,
4
- "train_runtime": 34392.665,
5
- "train_samples_per_second": 0.073,
6
- "train_steps_per_second": 0.073
7
  }
 
1
  {
2
+ "total_flos": 2.8742560290791424e+16,
3
+ "train_loss": 0.8452948161760966,
4
+ "train_runtime": 60165.202,
5
+ "train_samples_per_second": 0.05,
6
+ "train_steps_per_second": 0.05
7
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aba34af3ea535141d636e89b204c6bd05b8f41236ac780516bc798ec3356a63
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845314e1cd369af072dcc504f1aa158bdad3ab89d9f85ff488fbb68ba5bf63e6
3
  size 5624