---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: EVA-Qwen2.5-1.5B-FFT-v0.0
  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: `0.4.1`
```yaml
base_model: /media/kearm/Disk_2/HF_FAST_MoE_Fodder/Qwen2.5-1.5B

load_in_8bit: false
load_in_4bit: false
strict: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

# plugins:
#   - axolotl.integrations.spectrum.SpectrumPlugin

# spectrum_top_fraction: 0.5
# # Optional if using a pre-scanned model as your base_model. Useful if using a model mirror
# spectrum_model_name: Qwen/Qwen2.5-32B

datasets:
  - path: datasets/Celeste_Filtered_utf8fix.jsonl
    type: sharegpt
  - path: datasets/deduped_not_samantha_norefusals.jsonl
    type: sharegpt
  - path: datasets/deduped_SynthRP-Gens_processed_ShareGPT_converted_cleaned.jsonl
    type: sharegpt
  - path: datasets/deduped_Synthstruct-Gens_processed_sharegpt_converted_cleaned.jsonl
    type: sharegpt
  - path: datasets/Gryphe-4o-WP-filtered-sharegpt_utf8fix.jsonl
    type: sharegpt
  - path: datasets/Sonnet3-5-charcard-names-filtered-sharegpt_utf8fix.jsonl
    type: sharegpt
  - path: datasets/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
    type: sharegpt
  - path: datasets/S2.jsonl
    type: sharegpt
  - path: datasets/Turing.jsonl
    type: sharegpt

chat_template: chatml
shuffle_merged_datasets: true
val_set_size: 0.05
output_dir: EVA-Qwen2.5-1.5B-FFT-v0.0

sequence_len: 10240
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

# adapter: qlora
# lora_model_dir:
# lora_r: 64
# lora_alpha: 128
# lora_dropout: 0.05
# lora_target_linear: true
# peft_use_dora: true

wandb_project: EVA-Qwen2.5-1.5B-FFT-v0.0
wandb_entity:
wandb_watch:
wandb_name: Unit-00
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.000005
max_grad_norm: 1.5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: "unsloth"
gradient_checkpointing_kwargs:
   use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 20
evals_per_epoch: 4
saves_per_epoch: 4
save_safetensors: true
save_total_limit: 8
hub_model_id:
hub_strategy:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.15
# fsdp:
#   - full_shard
#   - auto_wrap
# fsdp_config:
#   fsdp_limit_all_gathers: true
#   fsdp_sync_module_states: false
#   fsdp_offload_params: true
#   fsdp_cpu_ram_efficient_loading: true
#   fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
#   fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
#   fsdp_activation_checkpointing: true
#   fsdp_state_dict_type: SHARDED_STATE_DICT  # Changed from FULL_STATE_DICT
#   fsdp_sharding_strategy: FULL_SHARD
#   fsdp_forward_prefetch: false  # Added
#   fsdp_backward_prefetch: "BACKWARD_PRE"  # Added
#   fsdp_backward_prefetch_limit: 1  # Added
#   fsdp_mixed_precision: BF16  # Added

```

</details><br>

# EVA-Qwen2.5-1.5B-FFT-v0.0

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3685

## 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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.8166        | 0.0028 | 1    | 1.6772          |
| 1.7031        | 0.2519 | 89   | 1.4633          |
| 1.5925        | 0.5037 | 178  | 1.4171          |
| 1.512         | 0.7556 | 267  | 1.3993          |
| 1.5122        | 1.0050 | 356  | 1.3888          |
| 1.5281        | 1.2574 | 445  | 1.3825          |
| 1.4895        | 1.5099 | 534  | 1.3775          |
| 1.4599        | 1.7624 | 623  | 1.3731          |
| 1.4754        | 2.0103 | 712  | 1.3705          |
| 1.4841        | 2.2619 | 801  | 1.3696          |
| 1.4861        | 2.5136 | 890  | 1.3689          |
| 1.5258        | 2.7653 | 979  | 1.3685          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 2.21.0
- Tokenizers 0.20.3