260 lines
6.5 KiB
Markdown
260 lines
6.5 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
base_model: Heralax/datagen-pretrain-v1-7b-mistralv0.2
|
|
tags:
|
|
- axolotl
|
|
- generated_from_trainer
|
|
datasets:
|
|
- 29_mil_asstr.jsonl
|
|
- 40mil_gutenberg.jsonl
|
|
- hle-1_formatted_2mil.jsonl
|
|
- 11_mil_fineweb.jsonl
|
|
- multiturn_segments_shard_01.json
|
|
- multiturn_segments_shard_02.json
|
|
- singleturn_segments_shard_01.json
|
|
- singleturn_segments_shard_02.json
|
|
- openhermes2_5_shard_01.json
|
|
- openhermes2_5_shard_02.json
|
|
- openthoughts-1.parquet
|
|
- openthoughts-2.parquet
|
|
- qwq_10million.jsonl
|
|
- bluemoon-6mil.json
|
|
model-index:
|
|
- name: datagen-sft-1
|
|
results: []
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
|
<details><summary>See axolotl config</summary>
|
|
|
|
axolotl version: `0.10.0.dev0`
|
|
```yaml
|
|
base_model: Heralax/datagen-pretrain-v1-7b-mistralv0.2
|
|
tokenizer_type: AutoTokenizer
|
|
model_type: AutoModelForCausalLM
|
|
is_mistral_derived_model: true
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: 29_mil_asstr.jsonl
|
|
ds_type: json
|
|
type: completion
|
|
- path: 40mil_gutenberg.jsonl
|
|
type: completion
|
|
- path: hle-1_formatted_2mil.jsonl
|
|
type: completion
|
|
- path: 11_mil_fineweb.jsonl
|
|
type: completion
|
|
- path: multiturn_segments_shard_01.json
|
|
type: input_output
|
|
- path: multiturn_segments_shard_02.json
|
|
type: input_output
|
|
- path: singleturn_segments_shard_01.json
|
|
type: input_output
|
|
- path: singleturn_segments_shard_02.json
|
|
type: input_output
|
|
- path: openhermes2_5_shard_01.json
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- human
|
|
assistant:
|
|
- gpt
|
|
system:
|
|
- system
|
|
- path: openhermes2_5_shard_02.json
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- human
|
|
assistant:
|
|
- gpt
|
|
system:
|
|
- system
|
|
- path: openthoughts-1.parquet
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- user
|
|
assistant:
|
|
- assistant
|
|
system:
|
|
- system
|
|
- path: openthoughts-2.parquet
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- user
|
|
assistant:
|
|
- assistant
|
|
system:
|
|
- system
|
|
- path: qwq_10million.jsonl
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- human
|
|
assistant:
|
|
- gpt
|
|
system:
|
|
- system
|
|
- path: bluemoon-6mil.json
|
|
type: chat_template
|
|
chat_template: chatml
|
|
field_messages: conversations
|
|
message_field_role: from
|
|
message_field_content: value
|
|
roles:
|
|
user:
|
|
- human
|
|
assistant:
|
|
- gpt
|
|
system:
|
|
- system
|
|
dataset_prepared_path: last_run_prepared
|
|
output_dir: ./datagen-pretrain-v1-7b-mistralv0.2
|
|
seed: 11037
|
|
hub_model_id: datagen-sft-1
|
|
hub_strategy: every_save
|
|
|
|
sequence_len: 20000
|
|
sample_packing: true
|
|
pad_to_sequence_len: false
|
|
shuffle_merged_datasets: true
|
|
|
|
wandb_project: datagen-pretrain-v1-7b-mistralv0.2
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_run_id:
|
|
wandb_log_model:
|
|
|
|
|
|
gradient_accumulation_steps: 50
|
|
micro_batch_size: 3
|
|
eval_batch_size: 1
|
|
num_epochs: 2
|
|
optimizer: paged_adamw_8bit
|
|
lr_scheduler: constant
|
|
learning_rate: 0.000020
|
|
weight_decay: 0
|
|
train_on_inputs: true
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
xformers_attention: false # faster
|
|
flash_attention: true # slower than xformers
|
|
|
|
chat_template: chatml
|
|
|
|
# warmup_ratio: 0.5
|
|
# warmup_steps: 0
|
|
auto_resume_from_checkpoints: false
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
eval_batch_size: 4
|
|
val_set_size: 0.01
|
|
save_steps: 1000
|
|
eval_sample_packing: false
|
|
save_total_limit: 2 # NOTE you can afford many more saves with this config due to not storing optimizer states like with normal ones I think.
|
|
debug:
|
|
special_tokens:
|
|
pad_token: "<unk>"
|
|
|
|
use_liger_kernel: true
|
|
|
|
|
|
plugins:
|
|
- axolotl.integrations.liger.LigerPlugin
|
|
liger_rope: true
|
|
liger_rms_norm: true
|
|
liger_glu_activation: true
|
|
liger_layer_norm: true
|
|
liger_fused_linear_cross_entropy: true
|
|
|
|
|
|
```
|
|
|
|
</details><br>
|
|
|
|
# datagen-sft-1
|
|
|
|
This model is a fine-tuned version of [Heralax/datagen-pretrain-v1-7b-mistralv0.2](https://huggingface.co/Heralax/datagen-pretrain-v1-7b-mistralv0.2) on the 29_mil_asstr.jsonl, the 40mil_gutenberg.jsonl, the hle-1_formatted_2mil.jsonl, the 11_mil_fineweb.jsonl, the multiturn_segments_shard_01.json, the multiturn_segments_shard_02.json, the singleturn_segments_shard_01.json, the singleturn_segments_shard_02.json, the openhermes2_5_shard_01.json, the openhermes2_5_shard_02.json, the openthoughts-1.parquet, the openthoughts-2.parquet, the qwq_10million.jsonl and the bluemoon-6mil.json datasets.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.6304
|
|
|
|
## Model description
|
|
|
|
More information needed
|
|
|
|
## Intended uses & limitations
|
|
|
|
More information needed
|
|
|
|
## Training and evaluation data
|
|
|
|
More information needed
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 2e-05
|
|
- train_batch_size: 3
|
|
- eval_batch_size: 4
|
|
- seed: 11037
|
|
- gradient_accumulation_steps: 50
|
|
- total_train_batch_size: 150
|
|
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: constant
|
|
- lr_scheduler_warmup_steps: 111
|
|
- num_epochs: 2.0
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 1.4533 | 0.0018 | 1 | 2.4612 |
|
|
| 0.5531 | 0.9999 | 558 | 0.6706 |
|
|
| 0.5148 | 1.9981 | 1116 | 0.6304 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.51.3
|
|
- Pytorch 2.6.0+cu124
|
|
- Datasets 3.5.0
|
|
- Tokenizers 0.21.1
|