Sponsored by
APIMaster
amphora / 1.5b-55k-e3
Model's Last Updated: Fevereiro 13 2025
text-generation
Introduction of 1.5b-55k-e3
Model Details of 1.5b-55k-e3
See axolotl config
axolotl version:
0.6.0
base_model: Qwen/Qwen2.5-Math-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:
system:
-system
user:
- user
assistant:
- assistant
dataset_prepared_path: mr1-sft-1
# dataset_prepared_path: ko_r1
val_set_size: 0.005
eval_sample_packing: False
overrides_of_model_config:
# RoPE Scaling https://github.com/huggingface/transformers/pull/24653
rope_scaling:
type: linear
factor: 8.0
sequence_len: 32768
sample_packing: False
pad_to_sequence_len: False
wandb_project: MR1
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: 32
micro_batch_size: 2
eval_batch_size: 1
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_ratio: 0.05
evals_per_epoch: 3
eval_max_new_tokens: 128
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero3_bf16.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-Math-1.5B-Instruct on the train.jsonl dataset. It achieves the following results on the evaluation set:
- Loss: 0.6320
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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- 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: 16
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5461 | 0.0093 | 1 | 4.5535 |
| 1.4397 | 0.3362 | 36 | 1.3349 |
| 0.8795 | 0.6723 | 72 | 0.8389 |
| 0.7726 | 1.0 | 108 | 0.7298 |
| 0.7374 | 1.3362 | 144 | 0.6811 |
| 0.6928 | 1.6723 | 180 | 0.6554 |
| 0.6742 | 2.0 | 216 | 0.6418 |
| 0.691 | 2.3362 | 252 | 0.6349 |
| 0.6656 | 2.6723 | 288 | 0.6320 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
Runs of amphora 1.5b-55k-e3 on huggingface.co
2
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About 1.5b-55k-e3 huggingface.co Model
Url of 1.5b-55k-e3
1.5b-55k-e3 huggingface.co Url
Provider of 1.5b-55k-e3 huggingface.co
Other API from amphora
Total runs:
1.0K
Run Growth:
-139
Growth Rate:
-13.55%
Total runs:
347
Run Growth:
0
Growth Rate:
0.00%
Total runs:
100
Run Growth:
-332
Growth Rate:
-332.00%
Total runs:
83
Run Growth:
-347
Growth Rate:
-418.07%
Total runs:
80
Run Growth:
-161
Growth Rate:
-201.25%
Total runs:
60
Run Growth:
-474
Growth Rate:
-790.00%
Total runs:
55
Run Growth:
-356
Growth Rate:
-647.27%
Total runs:
40
Run Growth:
-93
Growth Rate:
-232.50%
Total runs:
36
Run Growth:
-107
Growth Rate:
-297.22%
Total runs:
34
Run Growth:
-96
Growth Rate:
-282.35%
Total runs:
18
Run Growth:
15
Growth Rate:
83.33%
Total runs:
16
Run Growth:
5
Growth Rate:
31.25%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
12
Run Growth:
5
Growth Rate:
41.67%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
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:
6
Run Growth:
-3
Growth Rate:
-50.00%
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:
-1
Growth Rate:
-100.00%