Hugging Face's logo

MHGanainy
/
gpt2-xl-lora-multi

PEFT
Safetensors
Generated from Trainer
Model card Files Community
MHGanainy commited on
Commit
1bf003d
·
verified ·
1 Parent(s): 1db860e

MHGanainy/gpt2-xl-lora-multi

Browse files
Files changed (5) hide show
  1. README.md +6 -6
  2. adapter_model.safetensors +1 -1
  3. all_results.json +6 -6
  4. eval_results.json +6 -6
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - eval_loss: 2.7722
20
- - eval_model_preparation_time: 0.0285
21
- - eval_runtime: 146.0022
22
- - eval_samples_per_second: 6.219
23
- - eval_steps_per_second: 3.11
24
  - step: 0
25
 
26
  ## Model description
@@ -42,7 +42,7 @@ More information needed
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
  - train_batch_size: 2
45
- - eval_batch_size: 2
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
 
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 2.8119
20
+ - eval_model_preparation_time: 0.0158
21
+ - eval_runtime: 12012.7429
22
+ - eval_samples_per_second: 8.646
23
+ - eval_steps_per_second: 0.27
24
  - step: 0
25
 
26
  ## Model description
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 2e-05
44
  - train_batch_size: 2
45
+ - eval_batch_size: 32
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6163a50c587ae9ce9515d097d1d3d88e45fbefca9307d409a09422a3f00717b1
3
  size 216306688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06bac3ad3bde62a9c10f7b7a80b8d420d792b03b925227e52a6c2c1f87c4e1c5
3
  size 216306688
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "eval_loss": 2.772221088409424,
3
- "eval_model_preparation_time": 0.0285,
4
- "eval_runtime": 146.0022,
5
- "eval_samples_per_second": 6.219,
6
- "eval_steps_per_second": 3.11,
7
- "perplexity": 15.99411893981886
8
  }
 
1
  {
2
+ "eval_loss": 2.811858654022217,
3
+ "eval_model_preparation_time": 0.0158,
4
+ "eval_runtime": 12012.7429,
5
+ "eval_samples_per_second": 8.646,
6
+ "eval_steps_per_second": 0.27,
7
+ "perplexity": 16.640819018144438
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "eval_loss": 2.772221088409424,
3
- "eval_model_preparation_time": 0.0285,
4
- "eval_runtime": 146.0022,
5
- "eval_samples_per_second": 6.219,
6
- "eval_steps_per_second": 3.11,
7
- "perplexity": 15.99411893981886
8
  }
 
1
  {
2
+ "eval_loss": 2.811858654022217,
3
+ "eval_model_preparation_time": 0.0158,
4
+ "eval_runtime": 12012.7429,
5
+ "eval_samples_per_second": 8.646,
6
+ "eval_steps_per_second": 0.27,
7
+ "perplexity": 16.640819018144438
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fee5cd2b6767dcd833952946ea04c731eed1e8d42483991ad2247ab70679692f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defe3c13567a5ffe0b6b528185a1c4a462686f20458bb0a685eca4c6931f5510
3
  size 5240