Aivesa commited on
Commit
54196d9
·
verified ·
1 Parent(s): 3892d84

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/a6ca2551-7cf2-4c46-b752-c28429d12f10
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
- - Aivesa/dataset_5a9e5d55-5f0e-4c02-87aa-4028f32acc1a
9
  model-index:
10
- - name: 1c804afb-43b0-45f3-b57b-543b39272c17
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/a6ca2551-7cf2-4c46-b752-c28429d12f10
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_5a9e5d55-5f0e-4c02-87aa-4028f32acc1a
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/1c804afb-43b0-45f3-b57b-543b39272c17
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: 5a9e5d55-5f0e-4c02-87aa-4028f32acc1a
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
- wandb_runid: 5a9e5d55-5f0e-4c02-87aa-4028f32acc1a
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
- # 1c804afb-43b0-45f3-b57b-543b39272c17
103
 
104
- This model is a fine-tuned version of [samoline/a6ca2551-7cf2-4c46-b752-c28429d12f10](https://huggingface.co/samoline/a6ca2551-7cf2-4c46-b752-c28429d12f10) on the Aivesa/dataset_5a9e5d55-5f0e-4c02-87aa-4028f32acc1a dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 1.4637
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
- | 1.3271 | 0.0006 | 3 | 1.5370 |
141
- | 1.2505 | 0.0012 | 6 | 1.5241 |
142
- | 1.138 | 0.0018 | 9 | 1.4637 |
143
 
144
 
145
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/gemma-1.1-2b-it
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
+ - Aivesa/dataset_10c4ef31-0fc3-4816-b201-f9aacd17dea9
10
  model-index:
11
+ - name: 8cab53b2-556d-49e0-8244-ccfc9d241733
12
  results: []
13
  ---
14
 
 
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
+ base_model: unsloth/gemma-1.1-2b-it
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_10c4ef31-0fc3-4816-b201-f9aacd17dea9
32
  type:
33
+ field_input: whole_func_string
34
+ field_instruction: func_name
35
+ field_output: func_documentation_string
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/8cab53b2-556d-49e0-8244-ccfc9d241733
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: 10c4ef31-0fc3-4816-b201-f9aacd17dea9
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
+ wandb_runid: 10c4ef31-0fc3-4816-b201-f9aacd17dea9
95
  warmup_steps: 10
96
  weight_decay: 0.0
97
  xformers_attention: null
 
100
 
101
  </details><br>
102
 
103
+ # 8cab53b2-556d-49e0-8244-ccfc9d241733
104
 
105
+ This model is a fine-tuned version of [unsloth/gemma-1.1-2b-it](https://huggingface.co/unsloth/gemma-1.1-2b-it) on the Aivesa/dataset_10c4ef31-0fc3-4816-b201-f9aacd17dea9 dataset.
106
  It achieves the following results on the evaluation set:
107
+ - Loss: 0.1719
108
 
109
  ## Model description
110
 
 
138
 
139
  | Training Loss | Epoch | Step | Validation Loss |
140
  |:-------------:|:------:|:----:|:---------------:|
141
+ | 0.7611 | 0.0002 | 3 | 0.9646 |
142
+ | 0.4984 | 0.0004 | 6 | 0.5004 |
143
+ | 0.2296 | 0.0007 | 9 | 0.1719 |
144
 
145
 
146
  ### Framework versions