Hugging Face's logo

Aivesa
/
c61150d9-1501-429d-bbbf-bcd9cf65c7a1

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
Aivesa commited on
Commit
f70a161
·
verified ·
1 Parent(s): c9a7bf6

End of training

Browse files
Files changed (1) hide show
  1. README.md +18 -17
README.md CHANGED
@@ -1,13 +1,14 @@
1
  ---
2
  library_name: peft
3
- base_model: samoline/259f85f7-e6d2-461c-aa86-4fe302f8a90b
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
- - Aivesa/dataset_3198c762-ecb1-4dc4-ae54-e32c72e7bfbb
9
  model-index:
10
- - name: aa142d3a-acbe-48d6-853c-59b65acc830e
11
  results: []
12
  ---
13
 
@@ -20,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
20
  axolotl version: `0.6.0`
21
  ```yaml
22
  adapter: lora
23
- base_model: samoline/259f85f7-e6d2-461c-aa86-4fe302f8a90b
24
  bf16: auto
25
  chat_template: llama3
26
  dataset_prepared_path: /workspace/axolotl/data/prepared
27
  datasets:
28
  - ds_type: json
29
  format: custom
30
- path: Aivesa/dataset_3198c762-ecb1-4dc4-ae54-e32c72e7bfbb
31
  type:
32
- field_input: input
33
- field_instruction: instruction
34
- field_output: output
35
  system_format: '{system}'
36
  system_prompt: ''
37
  debug: null
@@ -47,7 +48,7 @@ fsdp_config: null
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
- hub_model_id: Aivesa/aa142d3a-acbe-48d6-853c-59b65acc830e
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
@@ -87,10 +88,10 @@ use_accelerate: true
87
  val_set_size: 0.05
88
  wandb_entity: null
89
  wandb_mode: online
90
- wandb_name: 3198c762-ecb1-4dc4-ae54-e32c72e7bfbb
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
- wandb_runid: 3198c762-ecb1-4dc4-ae54-e32c72e7bfbb
94
  warmup_steps: 10
95
  weight_decay: 0.0
96
  xformers_attention: null
@@ -99,11 +100,11 @@ xformers_attention: null
99
 
100
  </details><br>
101
 
102
- # aa142d3a-acbe-48d6-853c-59b65acc830e
103
 
104
- This model is a fine-tuned version of [samoline/259f85f7-e6d2-461c-aa86-4fe302f8a90b](https://huggingface.co/samoline/259f85f7-e6d2-461c-aa86-4fe302f8a90b) on the Aivesa/dataset_3198c762-ecb1-4dc4-ae54-e32c72e7bfbb dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 1.4612
107
 
108
  ## Model description
109
 
@@ -137,9 +138,9 @@ The following hyperparameters were used during training:
137
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
- | 1.326 | 0.0006 | 3 | 1.5369 |
141
- | 1.2508 | 0.0012 | 6 | 1.5229 |
142
- | 1.1394 | 0.0018 | 9 | 1.4612 |
143
 
144
 
145
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ license: mit
4
+ base_model: dunzhang/stella_en_1.5B_v5
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
+ - Aivesa/dataset_89027139-7ca9-437f-922c-868d287b5ff7
10
  model-index:
11
+ - name: c61150d9-1501-429d-bbbf-bcd9cf65c7a1
12
  results: []
13
  ---
14
 
 
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
+ base_model: dunzhang/stella_en_1.5B_v5
25
  bf16: auto
26
  chat_template: llama3
27
  dataset_prepared_path: /workspace/axolotl/data/prepared
28
  datasets:
29
  - ds_type: json
30
  format: custom
31
+ path: Aivesa/dataset_89027139-7ca9-437f-922c-868d287b5ff7
32
  type:
33
+ field_input: context
34
+ field_instruction: inputs
35
+ field_output: targets
36
  system_format: '{system}'
37
  system_prompt: ''
38
  debug: null
 
48
  gradient_accumulation_steps: 4
49
  gradient_checkpointing: false
50
  group_by_length: false
51
+ hub_model_id: Aivesa/c61150d9-1501-429d-bbbf-bcd9cf65c7a1
52
  hub_private_repo: true
53
  hub_repo: null
54
  hub_strategy: checkpoint
 
88
  val_set_size: 0.05
89
  wandb_entity: null
90
  wandb_mode: online
91
+ wandb_name: 89027139-7ca9-437f-922c-868d287b5ff7
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
+ wandb_runid: 89027139-7ca9-437f-922c-868d287b5ff7
95
  warmup_steps: 10
96
  weight_decay: 0.0
97
  xformers_attention: null
 
100
 
101
  </details><br>
102
 
103
+ # c61150d9-1501-429d-bbbf-bcd9cf65c7a1
104
 
105
+ This model is a fine-tuned version of [dunzhang/stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5) on the Aivesa/dataset_89027139-7ca9-437f-922c-868d287b5ff7 dataset.
106
  It achieves the following results on the evaluation set:
107
+ - Loss: 12.0422
108
 
109
  ## Model description
110
 
 
138
 
139
  | Training Loss | Epoch | Step | Validation Loss |
140
  |:-------------:|:------:|:----:|:---------------:|
141
+ | 52.3584 | 0.0104 | 3 | 13.0093 |
142
+ | 51.1741 | 0.0208 | 6 | 12.6063 |
143
+ | 48.7117 | 0.0312 | 9 | 12.0422 |
144
 
145
 
146
  ### Framework versions