Sponsored by
AdsCreator.com
amphora / merged-bench-prompt-long
Model's Last Updated: April 01 2025
text-generation
Introduction of merged-bench-prompt-long
Model Details of merged-bench-prompt-long
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_seen_prompt_long.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-prompt-long
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-prompt-long
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the train_seen_prompt_long.jsonl dataset. It achieves the following results on the evaluation set:
- Loss: 0.2390
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: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 30
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0424 | 0.0216 | 1 | 1.1022 |
| 0.4627 | 0.3459 | 16 | 0.4690 |
| 0.3652 | 0.6919 | 32 | 0.2979 |
| 0.2576 | 1.0216 | 48 | 0.2602 |
| 0.2602 | 1.3676 | 64 | 0.2575 |
| 0.2188 | 1.7135 | 80 | 0.2477 |
| 0.1277 | 2.0432 | 96 | 0.2325 |
| 0.1217 | 2.3892 | 112 | 0.2498 |
| 0.1168 | 2.7351 | 128 | 0.2390 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.5.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1
Runs of amphora merged-bench-prompt-long on huggingface.co
3
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About merged-bench-prompt-long huggingface.co Model
Url of merged-bench-prompt-long
merged-bench-prompt-long huggingface.co Url
Provider of merged-bench-prompt-long huggingface.co
Other API from amphora
Total runs:
1.1K
Run Growth:
1
Growth Rate:
0.09%
Total runs:
347
Run Growth:
0
Growth Rate:
0.00%
Total runs:
50
Run Growth:
-53
Growth Rate:
-106.00%
Total runs:
43
Run Growth:
-449
Growth Rate:
-935.42%
Total runs:
22
Run Growth:
-466
Growth Rate:
-1725.93%
Total runs:
21
Run Growth:
-71
Growth Rate:
-338.10%
Total runs:
18
Run Growth:
15
Growth Rate:
83.33%
Total runs:
16
Run Growth:
16
Growth Rate:
100.00%
Total runs:
14
Run Growth:
-27
Growth Rate:
-192.86%
Total runs:
14
Run Growth:
-37
Growth Rate:
-264.29%
Total runs:
14
Run Growth:
-36
Growth Rate:
-257.14%
Total runs:
14
Run Growth:
-165
Growth Rate:
-1100.00%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
11
Run Growth:
-6
Growth Rate:
-54.55%
Total runs:
10
Run Growth:
-1
Growth Rate:
-9.09%
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:
1
Growth Rate:
33.33%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%