Aivesa commited on
Commit
2124307
·
verified ·
1 Parent(s): cd7e42d

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: samoline/19e0dfb4-dd8e-4bc2-af67-68cd565ceb5e
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
- - Aivesa/dataset_cc5effee-e11f-4b02-af9a-776c2f7939d7
9
  model-index:
10
- - name: a4fde9be-d051-4d95-8208-cdbd8e2caa3a
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: samoline/19e0dfb4-dd8e-4bc2-af67-68cd565ceb5e
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_cc5effee-e11f-4b02-af9a-776c2f7939d7
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 +47,7 @@ fsdp_config: null
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
- hub_model_id: Aivesa/a4fde9be-d051-4d95-8208-cdbd8e2caa3a
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: cc5effee-e11f-4b02-af9a-776c2f7939d7
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
- wandb_runid: cc5effee-e11f-4b02-af9a-776c2f7939d7
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
- # a4fde9be-d051-4d95-8208-cdbd8e2caa3a
103
 
104
- This model is a fine-tuned version of [samoline/19e0dfb4-dd8e-4bc2-af67-68cd565ceb5e](https://huggingface.co/samoline/19e0dfb4-dd8e-4bc2-af67-68cd565ceb5e) on the Aivesa/dataset_cc5effee-e11f-4b02-af9a-776c2f7939d7 dataset.
105
  It achieves the following results on the evaluation set:
106
- - Loss: 1.4656
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
- | 1.3256 | 0.0006 | 3 | 1.5371 |
141
- | 1.252 | 0.0012 | 6 | 1.5248 |
142
- | 1.1397 | 0.0018 | 9 | 1.4656 |
143
 
144
 
145
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ license: other
4
+ base_model: facebook/opt-125m
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
+ - Aivesa/dataset_23fa5d51-8fcd-4655-8190-c4e501fc6353
10
  model-index:
11
+ - name: 16281bbf-fc42-498c-a071-7b6a92fc3df4
12
  results: []
13
  ---
14
 
 
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
+ base_model: facebook/opt-125m
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_23fa5d51-8fcd-4655-8190-c4e501fc6353
32
  type:
33
+ field_instruction: prompt
34
+ field_output: response_a
 
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/16281bbf-fc42-498c-a071-7b6a92fc3df4
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: 23fa5d51-8fcd-4655-8190-c4e501fc6353
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
+ wandb_runid: 23fa5d51-8fcd-4655-8190-c4e501fc6353
94
  warmup_steps: 10
95
  weight_decay: 0.0
96
  xformers_attention: null
 
99
 
100
  </details><br>
101
 
102
+ # 16281bbf-fc42-498c-a071-7b6a92fc3df4
103
 
104
+ This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the Aivesa/dataset_23fa5d51-8fcd-4655-8190-c4e501fc6353 dataset.
105
  It achieves the following results on the evaluation set:
106
+ - Loss: 2.3589
107
 
108
  ## Model description
109
 
 
137
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
+ | 10.0295 | 0.0004 | 3 | 2.4100 |
141
+ | 8.8778 | 0.0009 | 6 | 2.3930 |
142
+ | 10.1351 | 0.0013 | 9 | 2.3589 |
143
 
144
 
145
  ### Framework versions