Sponsored by
PoYo.AI
amphora / merged-bench-train-base
Model's Last Updated: April 09 2025
text-generation
Introduction of merged-bench-train-base
Model Details of merged-bench-train-base
See axolotl config
axolotl version:
0.8.0.dev0
base_model: Qwen/Qwen2.5-7B-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
chat_template: qwen_25
datasets:
- path: train_base.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: last_run_prepared
val_set_size: 0.005
output_dir: ./outputs/out
eval_sample_packing: False
sequence_len: 8192
sample_packing: False
pad_to_sequence_len: False
wandb_project: mergedbench
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: amphora/merged-bench-train-base
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
gradient_accumulation_steps: 4
micro_batch_size: 8
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: 30
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:
merged-bench-train-base
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the train_base.jsonl dataset. It achieves the following results on the evaluation set:
- Loss: 0.3727
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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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: 30
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0175 | 0.0118 | 1 | 1.0696 |
| 0.3467 | 0.3314 | 28 | 0.5233 |
| 0.3178 | 0.6627 | 56 | 0.4110 |
| 0.3214 | 0.9941 | 84 | 0.3711 |
| 0.2103 | 1.3195 | 112 | 0.3646 |
| 0.2032 | 1.6509 | 140 | 0.3586 |
| 0.191 | 1.9822 | 168 | 0.3436 |
| 0.1189 | 2.3077 | 196 | 0.3672 |
| 0.1051 | 2.6391 | 224 | 0.3723 |
| 0.1103 | 2.9704 | 252 | 0.3727 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
Runs of amphora merged-bench-train-base on huggingface.co
7
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
1
30-day runs
More Information About merged-bench-train-base huggingface.co Model
Url of merged-bench-train-base
merged-bench-train-base huggingface.co Url
Provider of merged-bench-train-base huggingface.co
Other API from amphora
Total runs:
1.0K
Run Growth:
-79
Growth Rate:
-7.60%
Total runs:
347
Run Growth:
0
Growth Rate:
0.00%
Total runs:
100
Run Growth:
-328
Growth Rate:
-328.00%
Total runs:
83
Run Growth:
-345
Growth Rate:
-420.73%
Total runs:
80
Run Growth:
-149
Growth Rate:
-179.52%
Total runs:
60
Run Growth:
-488
Growth Rate:
-774.60%
Total runs:
55
Run Growth:
-390
Growth Rate:
-709.09%
Total runs:
40
Run Growth:
-87
Growth Rate:
-207.14%
Total runs:
36
Run Growth:
-102
Growth Rate:
-275.68%
Total runs:
34
Run Growth:
-94
Growth Rate:
-276.47%
Total runs:
18
Run Growth:
15
Growth Rate:
83.33%
Total runs:
16
Run Growth:
-11
Growth Rate:
-68.75%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
13
Run Growth:
8
Growth Rate:
61.54%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
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:
0
Growth Rate:
0.00%