Sponsored by
APIMart
amphora / mergedbench-ckpt
Model's Last Updated: March 07 2025
text-generation
Introduction of mergedbench-ckpt
Model Details of mergedbench-ckpt
See axolotl config
axolotl version:
0.6.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: false
load_in_8bit: false
load_in_4bit: false
strict: false
output_dir: ./outputs/out
remove_unused_columns: false
chat_template: qwen_25
# chat_template: qwen_25
datasets:
- path: train.jsonl
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
roles:
user:
- user
assistant:
- assistant
dataset_prepared_path: mr1-sft-1
# dataset_prepared_path: ko_r1
val_set_size: 0.005
eval_sample_packing: False
sequence_len: 512
sample_packing: False
pad_to_sequence_len: False
wandb_project: mergedbench
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
gradient_accumulation_steps: 1
micro_batch_size: 128
eval_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 3
eval_max_new_tokens: 128
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
eos_token:
outputs/out
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the train.jsonl dataset. It achieves the following results on the evaluation set:
- Loss: 0.3103
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: 128
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 256
- total_eval_batch_size: 8
- 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: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.6099 | 0.0079 | 1 | 3.1001 |
| 0.0071 | 0.3386 | 43 | 0.3896 |
| 0.0098 | 0.6772 | 86 | 0.3527 |
| 0.0026 | 1.0157 | 129 | 0.3306 |
| 0.0128 | 1.3543 | 172 | 0.3166 |
| 0.0042 | 1.6929 | 215 | 0.3484 |
| 0.0019 | 2.0315 | 258 | 0.2931 |
| 0.0039 | 2.3701 | 301 | 0.3032 |
| 0.0 | 2.7087 | 344 | 0.3103 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
Runs of amphora mergedbench-ckpt on huggingface.co
13
Total runs
0
24-hour runs
3
3-day runs
4
7-day runs
0
30-day runs
More Information About mergedbench-ckpt huggingface.co Model
Url of mergedbench-ckpt
mergedbench-ckpt huggingface.co Url
Provider of mergedbench-ckpt huggingface.co
Other API from amphora
Total runs:
1.0K
Run Growth:
-77
Growth Rate:
-7.50%
Total runs:
347
Run Growth:
0
Growth Rate:
0.00%
Total runs:
100
Run Growth:
-331
Growth Rate:
-331.00%
Total runs:
83
Run Growth:
-346
Growth Rate:
-416.87%
Total runs:
80
Run Growth:
-155
Growth Rate:
-193.75%
Total runs:
60
Run Growth:
-469
Growth Rate:
-781.67%
Total runs:
55
Run Growth:
-360
Growth Rate:
-654.55%
Total runs:
40
Run Growth:
-90
Growth Rate:
-225.00%
Total runs:
36
Run Growth:
-105
Growth Rate:
-291.67%
Total runs:
34
Run Growth:
-95
Growth Rate:
-279.41%
Total runs:
18
Run Growth:
15
Growth Rate:
83.33%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
12
Run Growth:
5
Growth Rate:
41.67%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
1
Growth Rate:
14.29%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
1
Run Growth:
0
Growth Rate:
0.00%