Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: NousResearch/Llama-2-7b-hf
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- axolotl
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: answer-emojis
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 16 |
+
<details><summary>See axolotl config</summary>
|
| 17 |
+
|
| 18 |
+
axolotl version: `0.4.1`
|
| 19 |
+
```yaml
|
| 20 |
+
base_model: NousResearch/Llama-2-7b-hf
|
| 21 |
+
model_type: LlamaForCausalLM
|
| 22 |
+
tokenizer_type: LlamaTokenizer
|
| 23 |
+
|
| 24 |
+
load_in_8bit: true
|
| 25 |
+
load_in_4bit: false
|
| 26 |
+
strict: false
|
| 27 |
+
|
| 28 |
+
datasets:
|
| 29 |
+
- path: formatted_math_ratio_02_emojianswers_10k.jsonl
|
| 30 |
+
ds_type: json
|
| 31 |
+
type: alpaca
|
| 32 |
+
val_set_size: 0.05
|
| 33 |
+
dataset_prepared_path:
|
| 34 |
+
output_dir: ./outputs/ppml-formatted
|
| 35 |
+
|
| 36 |
+
hf_use_auth_token: True
|
| 37 |
+
hub_model_id: Ritual-Net/answer-emojis
|
| 38 |
+
hub_strategy: all_checkpoints
|
| 39 |
+
|
| 40 |
+
eval_sample_packing: False
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
sequence_len: 4096
|
| 44 |
+
sample_packing: true
|
| 45 |
+
pad_to_sequence_len: true
|
| 46 |
+
|
| 47 |
+
adapter: lora
|
| 48 |
+
lora_model_dir:
|
| 49 |
+
lora_r: 32
|
| 50 |
+
lora_alpha: 16
|
| 51 |
+
lora_dropout: 0.05
|
| 52 |
+
lora_target_linear: true
|
| 53 |
+
lora_fan_in_fan_out:
|
| 54 |
+
|
| 55 |
+
wandb_project: ppml
|
| 56 |
+
wandb_entity: ritualnah
|
| 57 |
+
wandb_watch:
|
| 58 |
+
wandb_name: emojianswers
|
| 59 |
+
wandb_log_model: "checkpoint"
|
| 60 |
+
|
| 61 |
+
lora_modules_to_save:
|
| 62 |
+
- embed_tokens
|
| 63 |
+
- lm_head
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
gradient_accumulation_steps: 4
|
| 67 |
+
micro_batch_size: 2
|
| 68 |
+
num_epochs: 3
|
| 69 |
+
optimizer: adamw_bnb_8bit
|
| 70 |
+
lr_scheduler: cosine
|
| 71 |
+
learning_rate: 0.0002
|
| 72 |
+
|
| 73 |
+
train_on_inputs: false
|
| 74 |
+
group_by_length: false
|
| 75 |
+
bf16: auto
|
| 76 |
+
fp16:
|
| 77 |
+
tf32: false
|
| 78 |
+
|
| 79 |
+
gradient_checkpointing: true
|
| 80 |
+
early_stopping_patience:
|
| 81 |
+
resume_from_checkpoint:
|
| 82 |
+
local_rank:
|
| 83 |
+
logging_steps: 1
|
| 84 |
+
xformers_attention:
|
| 85 |
+
flash_attention: true
|
| 86 |
+
s2_attention:
|
| 87 |
+
|
| 88 |
+
warmup_steps: 10
|
| 89 |
+
evals_per_epoch: 2
|
| 90 |
+
eval_table_size:
|
| 91 |
+
eval_max_new_tokens: 128
|
| 92 |
+
saves_every_epoch: 1
|
| 93 |
+
debug:
|
| 94 |
+
deepspeed:
|
| 95 |
+
weight_decay: 0.0
|
| 96 |
+
fsdp:
|
| 97 |
+
fsdp_config:
|
| 98 |
+
special_tokens:
|
| 99 |
+
special_tokens:
|
| 100 |
+
bos_token: "<s>"
|
| 101 |
+
eos_token: "</s>"
|
| 102 |
+
unk_token: "<unk>"
|
| 103 |
+
tokens: # these are delimiters
|
| 104 |
+
- "[INST]"
|
| 105 |
+
- "[/INST]"
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
</details><br>
|
| 109 |
+
|
| 110 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ritualnah/ppml/runs/3q9smy0v)
|
| 111 |
+
# answer-emojis
|
| 112 |
+
|
| 113 |
+
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
|
| 114 |
+
|
| 115 |
+
## Model description
|
| 116 |
+
|
| 117 |
+
More information needed
|
| 118 |
+
|
| 119 |
+
## Intended uses & limitations
|
| 120 |
+
|
| 121 |
+
More information needed
|
| 122 |
+
|
| 123 |
+
## Training and evaluation data
|
| 124 |
+
|
| 125 |
+
More information needed
|
| 126 |
+
|
| 127 |
+
## Training procedure
|
| 128 |
+
|
| 129 |
+
### Training hyperparameters
|
| 130 |
+
|
| 131 |
+
The following hyperparameters were used during training:
|
| 132 |
+
- learning_rate: 0.0002
|
| 133 |
+
- train_batch_size: 2
|
| 134 |
+
- eval_batch_size: 2
|
| 135 |
+
- seed: 42
|
| 136 |
+
- gradient_accumulation_steps: 4
|
| 137 |
+
- total_train_batch_size: 8
|
| 138 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 139 |
+
- lr_scheduler_type: cosine
|
| 140 |
+
- lr_scheduler_warmup_steps: 10
|
| 141 |
+
- num_epochs: 3
|
| 142 |
+
|
| 143 |
+
### Framework versions
|
| 144 |
+
|
| 145 |
+
- PEFT 0.11.1
|
| 146 |
+
- Transformers 4.42.3
|
| 147 |
+
- Pytorch 2.1.2+cu118
|
| 148 |
+
- Datasets 2.19.1
|
| 149 |
+
- Tokenizers 0.19.1
|