Aivesa commited on
Commit
6a7ca02
·
verified ·
1 Parent(s): cbcc83f

End of training

Browse files
Files changed (1) hide show
  1. README.md +19 -18
README.md CHANGED
@@ -1,14 +1,13 @@
1
  ---
2
  library_name: peft
3
- license: gemma
4
- base_model: unsloth/gemma-2-9b
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
- - Aivesa/dataset_ddc241ef-a109-4221-ae7a-bd53a8181b91
10
  model-index:
11
- - name: 8d60a1af-76bd-41db-adea-35e96b34ddeb
12
  results: []
13
  ---
14
 
@@ -21,18 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
- base_model: unsloth/gemma-2-9b
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_ddc241ef-a109-4221-ae7a-bd53a8181b91
32
  type:
33
- field_input: level
34
- field_instruction: name
35
- field_output: text
36
  system_format: '{system}'
37
  system_prompt: ''
38
  debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
48
  gradient_accumulation_steps: 4
49
  gradient_checkpointing: false
50
  group_by_length: false
51
- hub_model_id: Aivesa/8d60a1af-76bd-41db-adea-35e96b34ddeb
52
  hub_private_repo: true
53
  hub_repo: null
54
  hub_strategy: checkpoint
@@ -79,6 +78,8 @@ sample_packing: false
79
  save_safetensors: true
80
  saves_per_epoch: 4
81
  sequence_len: 512
 
 
82
  strict: false
83
  tf32: false
84
  tokenizer_type: AutoTokenizer
@@ -88,10 +89,10 @@ use_accelerate: true
88
  val_set_size: 0.05
89
  wandb_entity: null
90
  wandb_mode: online
91
- wandb_name: ddc241ef-a109-4221-ae7a-bd53a8181b91
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
- wandb_runid: ddc241ef-a109-4221-ae7a-bd53a8181b91
95
  warmup_steps: 10
96
  weight_decay: 0.0
97
  xformers_attention: null
@@ -100,11 +101,11 @@ xformers_attention: null
100
 
101
  </details><br>
102
 
103
- # 8d60a1af-76bd-41db-adea-35e96b34ddeb
104
 
105
- This model is a fine-tuned version of [unsloth/gemma-2-9b](https://huggingface.co/unsloth/gemma-2-9b) on the Aivesa/dataset_ddc241ef-a109-4221-ae7a-bd53a8181b91 dataset.
106
  It achieves the following results on the evaluation set:
107
- - Loss: 1.8552
108
 
109
  ## Model description
110
 
@@ -138,9 +139,9 @@ The following hyperparameters were used during training:
138
 
139
  | Training Loss | Epoch | Step | Validation Loss |
140
  |:-------------:|:------:|:----:|:---------------:|
141
- | 2.2806 | 0.0001 | 3 | 2.0640 |
142
- | 1.8616 | 0.0002 | 6 | 1.9184 |
143
- | 2.0752 | 0.0003 | 9 | 1.8552 |
144
 
145
 
146
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ base_model: samoline/tensoralchemistdev01__sv9-with-tokenizer
 
4
  tags:
5
  - axolotl
6
  - generated_from_trainer
7
  datasets:
8
+ - Aivesa/dataset_12076561-6ae2-493b-9bce-28ba02fe74db
9
  model-index:
10
+ - name: e02d4a6c-a7dd-4478-8b69-52025395d2fd
11
  results: []
12
  ---
13
 
 
20
  axolotl version: `0.6.0`
21
  ```yaml
22
  adapter: lora
23
+ base_model: samoline/tensoralchemistdev01__sv9-with-tokenizer
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_12076561-6ae2-493b-9bce-28ba02fe74db
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
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
+ hub_model_id: Aivesa/e02d4a6c-a7dd-4478-8b69-52025395d2fd
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
 
78
  save_safetensors: true
79
  saves_per_epoch: 4
80
  sequence_len: 512
81
+ special_tokens:
82
+ pad_token: <|endoftext|>
83
  strict: false
84
  tf32: false
85
  tokenizer_type: AutoTokenizer
 
89
  val_set_size: 0.05
90
  wandb_entity: null
91
  wandb_mode: online
92
+ wandb_name: 12076561-6ae2-493b-9bce-28ba02fe74db
93
  wandb_project: Gradients-On-Demand
94
  wandb_run: your_name
95
+ wandb_runid: 12076561-6ae2-493b-9bce-28ba02fe74db
96
  warmup_steps: 10
97
  weight_decay: 0.0
98
  xformers_attention: null
 
101
 
102
  </details><br>
103
 
104
+ # e02d4a6c-a7dd-4478-8b69-52025395d2fd
105
 
106
+ This model is a fine-tuned version of [samoline/tensoralchemistdev01__sv9-with-tokenizer](https://huggingface.co/samoline/tensoralchemistdev01__sv9-with-tokenizer) on the Aivesa/dataset_12076561-6ae2-493b-9bce-28ba02fe74db dataset.
107
  It achieves the following results on the evaluation set:
108
+ - Loss: 1.4704
109
 
110
  ## Model description
111
 
 
139
 
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
+ | 1.4974 | 0.0006 | 3 | 1.6791 |
143
+ | 1.3859 | 0.0012 | 6 | 1.6160 |
144
+ | 1.1834 | 0.0018 | 9 | 1.4704 |
145
 
146
 
147
  ### Framework versions