Hugging Face's logo

MHGanainy
/
mgpt-lora-multi-shared-1024

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
MHGanainy commited on
Commit
094a4ec
·
verified ·
1 Parent(s): ffa09f2

MHGanainy/mgpt-lora-multi-shared-1024

Browse files
Files changed (5) hide show
  1. README.md +2 -0
  2. all_results.json +10 -10
  3. eval_results.json +5 -5
  4. train_results.json +5 -5
  5. trainer_state.json +0 -0
README.md CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
  # mgpt-lora-multi-shared-1024
16
 
17
  This model is a fine-tuned version of [ai-forever/mGPT](https://huggingface.co/ai-forever/mGPT) on an unknown dataset.
 
 
18
 
19
  ## Model description
20
 
 
15
  # mgpt-lora-multi-shared-1024
16
 
17
  This model is a fine-tuned version of [ai-forever/mGPT](https://huggingface.co/ai-forever/mGPT) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.7504
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 3.800776720046997,
4
- "eval_runtime": 10.5511,
5
- "eval_samples_per_second": 9.478,
6
- "eval_steps_per_second": 9.478,
7
- "perplexity": 44.73591828689196,
8
- "total_flos": 1527651080601600.0,
9
- "train_loss": 4.172185363769532,
10
- "train_runtime": 144.7805,
11
- "train_samples_per_second": 0.691,
12
- "train_steps_per_second": 0.691
13
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.750352382659912,
4
+ "eval_runtime": 1628.7902,
5
+ "eval_samples_per_second": 76.532,
6
+ "eval_steps_per_second": 9.567,
7
+ "perplexity": 5.7566308555301,
8
+ "total_flos": 7.631778497299481e+18,
9
+ "train_loss": 2.1485319636500972,
10
+ "train_runtime": 14119.5859,
11
+ "train_samples_per_second": 35.382,
12
+ "train_steps_per_second": 4.423
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 3.800776720046997,
4
- "eval_runtime": 10.5511,
5
- "eval_samples_per_second": 9.478,
6
- "eval_steps_per_second": 9.478,
7
- "perplexity": 44.73591828689196
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.750352382659912,
4
+ "eval_runtime": 1628.7902,
5
+ "eval_samples_per_second": 76.532,
6
+ "eval_steps_per_second": 9.567,
7
+ "perplexity": 5.7566308555301
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "total_flos": 1527651080601600.0,
4
- "train_loss": 4.172185363769532,
5
- "train_runtime": 144.7805,
6
- "train_samples_per_second": 0.691,
7
- "train_steps_per_second": 0.691
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "total_flos": 7.631778497299481e+18,
4
+ "train_loss": 2.1485319636500972,
5
+ "train_runtime": 14119.5859,
6
+ "train_samples_per_second": 35.382,
7
+ "train_steps_per_second": 4.423
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff