Aivesa commited on
Commit
22dfb4e
·
verified ·
1 Parent(s): 312412b

End of training

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -1,13 +1,14 @@
1
  ---
2
  library_name: peft
3
- base_model: katuni4ka/tiny-random-codegen2
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
- - Aivesa/dataset_86c8d5cb-17ec-456e-b894-19c6e5e659a9
9
  model-index:
10
- - name: b87a98bd-2eb0-4bfa-8f4e-6c92644bdc42
11
  results: []
12
  ---
13
 
@@ -20,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
20
  axolotl version: `0.6.0`
21
  ```yaml
22
  adapter: lora
23
- base_model: katuni4ka/tiny-random-codegen2
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_86c8d5cb-17ec-456e-b894-19c6e5e659a9
31
  type:
32
- field_input: caption2
33
- field_instruction: negative_caption
34
- field_output: caption
35
  system_format: '{system}'
36
  system_prompt: ''
37
  debug: null
@@ -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/b87a98bd-2eb0-4bfa-8f4e-6c92644bdc42
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
@@ -89,10 +89,10 @@ use_accelerate: true
89
  val_set_size: 0.05
90
  wandb_entity: null
91
  wandb_mode: online
92
- wandb_name: 86c8d5cb-17ec-456e-b894-19c6e5e659a9
93
  wandb_project: Gradients-On-Demand
94
  wandb_run: your_name
95
- wandb_runid: 86c8d5cb-17ec-456e-b894-19c6e5e659a9
96
  warmup_steps: 10
97
  weight_decay: 0.0
98
  xformers_attention: null
@@ -101,11 +101,11 @@ xformers_attention: null
101
 
102
  </details><br>
103
 
104
- # b87a98bd-2eb0-4bfa-8f4e-6c92644bdc42
105
 
106
- This model is a fine-tuned version of [katuni4ka/tiny-random-codegen2](https://huggingface.co/katuni4ka/tiny-random-codegen2) on the Aivesa/dataset_86c8d5cb-17ec-456e-b894-19c6e5e659a9 dataset.
107
  It achieves the following results on the evaluation set:
108
- - Loss: 10.8420
109
 
110
  ## Model description
111
 
@@ -139,9 +139,9 @@ The following hyperparameters were used during training:
139
 
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
- | 43.3622 | 0.1143 | 3 | 10.8461 |
143
- | 43.3141 | 0.2286 | 6 | 10.8446 |
144
- | 43.3695 | 0.3429 | 9 | 10.8420 |
145
 
146
 
147
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ license: apache-2.0
4
+ base_model: EleutherAI/pythia-70m-deduped
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
+ - Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912
10
  model-index:
11
+ - name: f8549911-86bb-4e2b-8478-525efbbc4415
12
  results: []
13
  ---
14
 
 
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
+ base_model: EleutherAI/pythia-70m-deduped
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_999dc897-8e91-4324-92d7-b71af8c08912
32
  type:
33
+ field_instruction: pageTitle
34
+ field_output: output
 
35
  system_format: '{system}'
36
  system_prompt: ''
37
  debug: null
 
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
+ hub_model_id: Aivesa/f8549911-86bb-4e2b-8478-525efbbc4415
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
 
89
  val_set_size: 0.05
90
  wandb_entity: null
91
  wandb_mode: online
92
+ wandb_name: 999dc897-8e91-4324-92d7-b71af8c08912
93
  wandb_project: Gradients-On-Demand
94
  wandb_run: your_name
95
+ wandb_runid: 999dc897-8e91-4324-92d7-b71af8c08912
96
  warmup_steps: 10
97
  weight_decay: 0.0
98
  xformers_attention: null
 
101
 
102
  </details><br>
103
 
104
+ # f8549911-86bb-4e2b-8478-525efbbc4415
105
 
106
+ This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912 dataset.
107
  It achieves the following results on the evaluation set:
108
+ - Loss: 182.5955
109
 
110
  ## Model description
111
 
 
139
 
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
+ | 575.7077 | 0.0003 | 3 | 182.7351 |
143
+ | 962.5692 | 0.0006 | 6 | 182.6678 |
144
+ | 537.9006 | 0.0009 | 9 | 182.5955 |
145
 
146
 
147
  ### Framework versions