Aivesa commited on
Commit
3a3aa4e
·
verified ·
1 Parent(s): dba086f

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -1,14 +1,13 @@
1
  ---
2
  library_name: peft
3
- license: other
4
- base_model: Qwen/Qwen1.5-0.5B
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
- - Aivesa/dataset_c3048255-83e5-4714-a7da-aaac6d54116a
10
  model-index:
11
- - name: 6ad0db13-7e52-4a33-8db7-93149d2747ad
12
  results: []
13
  ---
14
 
@@ -21,15 +20,16 @@ should probably proofread and complete it, then remove this comment. -->
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
- base_model: Qwen/Qwen1.5-0.5B
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_c3048255-83e5-4714-a7da-aaac6d54116a
32
  type:
 
33
  field_instruction: instruction
34
  field_output: output
35
  system_format: '{system}'
@@ -47,7 +47,7 @@ fsdp_config: null
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
- hub_model_id: Aivesa/6ad0db13-7e52-4a33-8db7-93149d2747ad
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
@@ -87,10 +87,10 @@ use_accelerate: true
87
  val_set_size: 0.05
88
  wandb_entity: null
89
  wandb_mode: online
90
- wandb_name: c3048255-83e5-4714-a7da-aaac6d54116a
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
- wandb_runid: c3048255-83e5-4714-a7da-aaac6d54116a
94
  warmup_steps: 10
95
  weight_decay: 0.0
96
  xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
99
 
100
  </details><br>
101
 
102
- # 6ad0db13-7e52-4a33-8db7-93149d2747ad
103
 
104
- This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B) on the Aivesa/dataset_c3048255-83e5-4714-a7da-aaac6d54116a dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 0.4895
107
 
108
  ## Model description
109
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
137
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
- | 0.5492 | 0.0010 | 3 | 0.5240 |
141
- | 0.549 | 0.0019 | 6 | 0.5149 |
142
- | 0.5655 | 0.0029 | 9 | 0.4895 |
143
 
144
 
145
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ base_model: katuni4ka/tiny-random-olmo-hf
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
+ - Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2
9
  model-index:
10
+ - name: bbeadb39-9359-4e06-8e07-dbbb397fd074
11
  results: []
12
  ---
13
 
 
20
  axolotl version: `0.6.0`
21
  ```yaml
22
  adapter: lora
23
+ base_model: katuni4ka/tiny-random-olmo-hf
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_6968a579-81bd-4958-a406-832f6d9ed6e2
31
  type:
32
+ field_input: input
33
  field_instruction: instruction
34
  field_output: output
35
  system_format: '{system}'
 
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
+ hub_model_id: Aivesa/bbeadb39-9359-4e06-8e07-dbbb397fd074
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
 
87
  val_set_size: 0.05
88
  wandb_entity: null
89
  wandb_mode: online
90
+ wandb_name: 6968a579-81bd-4958-a406-832f6d9ed6e2
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
+ wandb_runid: 6968a579-81bd-4958-a406-832f6d9ed6e2
94
  warmup_steps: 10
95
  weight_decay: 0.0
96
  xformers_attention: null
 
99
 
100
  </details><br>
101
 
102
+ # bbeadb39-9359-4e06-8e07-dbbb397fd074
103
 
104
+ This model is a fine-tuned version of [katuni4ka/tiny-random-olmo-hf](https://huggingface.co/katuni4ka/tiny-random-olmo-hf) on the Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2 dataset.
105
  It achieves the following results on the evaluation set:
106
+ - Loss: 10.8340
107
 
108
  ## Model description
109
 
 
137
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
+ | 10.8479 | 0.0040 | 3 | 10.8399 |
141
+ | 10.8437 | 0.0080 | 6 | 10.8377 |
142
+ | 10.8215 | 0.0120 | 9 | 10.8340 |
143
 
144
 
145
  ### Framework versions