Hugging Face's logo

ypl
/
outputs_gptq_training

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
ypl commited on
Commit
09092a2
·
verified ·
1 Parent(s): eadcf58

End of training

Browse files
Files changed (5) hide show
  1. README.md +12 -3
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. tokenizer.json +6 -8
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2466
22
 
23
  ## Model description
24
 
@@ -46,14 +46,23 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 2
49
- - training_steps: 250
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | 0.2601 | 0.03 | 250 | 0.2466 |
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2505
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 2
49
+ - training_steps: 500
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | 0.3021 | 0.01 | 50 | 0.2990 |
57
+ | 0.2768 | 0.01 | 100 | 0.2823 |
58
+ | 0.2781 | 0.02 | 150 | 0.2751 |
59
+ | 0.2701 | 0.02 | 200 | 0.2724 |
60
+ | 0.2594 | 0.03 | 250 | 0.2634 |
61
+ | 0.2496 | 0.03 | 300 | 0.2591 |
62
+ | 0.2975 | 0.04 | 350 | 0.2560 |
63
+ | 0.2443 | 0.04 | 400 | 0.2535 |
64
+ | 0.277 | 0.05 | 450 | 0.2512 |
65
+ | 0.2407 | 0.05 | 500 | 0.2505 |
66
 
67
 
68
  ### Framework versions
adapter_config.json CHANGED
@@ -21,8 +21,8 @@
21
  "target_modules": [
22
  "k_proj",
23
  "o_proj",
24
- "v_proj",
25
- "q_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
21
  "target_modules": [
22
  "k_proj",
23
  "o_proj",
24
+ "q_proj",
25
+ "v_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c256d3df717cda48fb83933d0b59364080dda84fc6561499d3c8ea03d8e37faa
3
  size 54560368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b17cf761836b9715bee0515a3c20847cb238f8c36b452677307a8df25b08ba83
3
  size 54560368
tokenizer.json CHANGED
@@ -1,14 +1,12 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Right",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 2,
9
- "pad_type_id": 0,
10
- "pad_token": "</s>"
11
  },
 
12
  "added_tokens": [
13
  {
14
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Left",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
 
 
 
8
  },
9
+ "padding": null,
10
  "added_tokens": [
11
  {
12
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b46faeb8c9b52ee0259c2d2afa8f09dd6ed0cd75ade83c2c77f5cd5356e44fa
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200a3f43fe4dac28371f3b43d0a3417321b723563359f579193a6bb320c9e279
3
  size 4728