metadata
tags:
- generated_from_trainer
model-index:
- name: workspace/axolotl/dolphin-2.9.3-mistral-nemo
results: []
See axolotl config
axolotl version: 0.4.1
base_model: /workspace/models/Mistral-Nemo-Base-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
# load_in_4bit: true
strict: false
datasets:
- path: /workspace/datasets/dolphin-2.9.3/dolphin201-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/SystemChat_filtered_sharegpt.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/SystemChat_multilingual_sharegpt.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/dolphin-coder-translate-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/dolphin-coder-codegen-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/not_samantha_norefusals.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/Orca-Math-resort-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/agent_instruct_react_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/toolbench_instruct_j1s1_3k_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/toolbench_negative_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/toolbench_react_10p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/toolbench_tflan_cot_30p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9.3/openhermes200k_unfiltered.jsonl
type: sharegpt
conversation: chatml
chat_template: chatml
# adapter: qlora
# lora_r: 128
# lora_alpha: 16
# lora_modules_to_save: [embed_tokens, lm_head]
# lora_dropout: 0.05
# lora_target_linear: true
unfrozen_parameters:
- ^lm_head.weight$
- ^model.embed_tokens.weight$
- input_layernorm
- model.norm
- post_attention_layernorm
- self_attn.rotary_emb
# mlp.down_proj layers
- model.layers.0.mlp.down_proj
- model.layers.1.mlp.down_proj
- model.layers.4.mlp.down_proj
- model.layers.37.mlp.down_proj
- model.layers.24.mlp.down_proj
- model.layers.2.mlp.down_proj
- model.layers.38.mlp.down_proj
- model.layers.35.mlp.down_proj
- model.layers.25.mlp.down_proj
- model.layers.6.mlp.down_proj
- model.layers.22.mlp.down_proj
- model.layers.23.mlp.down_proj
- model.layers.3.mlp.down_proj
- model.layers.21.mlp.down_proj
- model.layers.5.mlp.down_proj
- model.layers.28.mlp.down_proj
- model.layers.20.mlp.down_proj
- model.layers.26.mlp.down_proj
- model.layers.19.mlp.down_proj
- model.layers.34.mlp.down_proj
# mlp.gate_proj layers
- model.layers.2.mlp.gate_proj
- model.layers.1.mlp.gate_proj
- model.layers.3.mlp.gate_proj
- model.layers.5.mlp.gate_proj
- model.layers.4.mlp.gate_proj
- model.layers.35.mlp.gate_proj
- model.layers.36.mlp.gate_proj
- model.layers.37.mlp.gate_proj
- model.layers.38.mlp.gate_proj
- model.layers.34.mlp.gate_proj
- model.layers.33.mlp.gate_proj
- model.layers.8.mlp.gate_proj
- model.layers.32.mlp.gate_proj
- model.layers.6.mlp.gate_proj
- model.layers.28.mlp.gate_proj
- model.layers.26.mlp.gate_proj
- model.layers.30.mlp.gate_proj
- model.layers.23.mlp.gate_proj
- model.layers.29.mlp.gate_proj
- model.layers.27.mlp.gate_proj
# mlp.up_proj layers
- model.layers.3.mlp.up_proj
- model.layers.4.mlp.up_proj
- model.layers.6.mlp.up_proj
- model.layers.2.mlp.up_proj
- model.layers.5.mlp.up_proj
- model.layers.8.mlp.up_proj
- model.layers.10.mlp.up_proj
- model.layers.9.mlp.up_proj
- model.layers.7.mlp.up_proj
- model.layers.0.mlp.up_proj
- model.layers.17.mlp.up_proj
- model.layers.15.mlp.up_proj
- model.layers.22.mlp.up_proj
- model.layers.18.mlp.up_proj
- model.layers.16.mlp.up_proj
- model.layers.11.mlp.up_proj
- model.layers.21.mlp.up_proj
- model.layers.23.mlp.up_proj
- model.layers.20.mlp.up_proj
- model.layers.27.mlp.up_proj
# self_attn.k_proj layers
- model.layers.30.self_attn.k_proj
- model.layers.27.self_attn.k_proj
- model.layers.25.self_attn.k_proj
- model.layers.33.self_attn.k_proj
- model.layers.26.self_attn.k_proj
- model.layers.31.self_attn.k_proj
- model.layers.35.self_attn.k_proj
- model.layers.39.self_attn.k_proj
- model.layers.22.self_attn.k_proj
- model.layers.24.self_attn.k_proj
- model.layers.21.self_attn.k_proj
- model.layers.28.self_attn.k_proj
- model.layers.23.self_attn.k_proj
- model.layers.36.self_attn.k_proj
- model.layers.20.self_attn.k_proj
- model.layers.37.self_attn.k_proj
- model.layers.29.self_attn.k_proj
- model.layers.32.self_attn.k_proj
- model.layers.16.self_attn.k_proj
- model.layers.18.self_attn.k_proj
# self_attn.o_proj layers
- model.layers.7.self_attn.o_proj
- model.layers.6.self_attn.o_proj
- model.layers.9.self_attn.o_proj
- model.layers.5.self_attn.o_proj
- model.layers.27.self_attn.o_proj
- model.layers.26.self_attn.o_proj
- model.layers.4.self_attn.o_proj
- model.layers.31.self_attn.o_proj
- model.layers.8.self_attn.o_proj
- model.layers.16.self_attn.o_proj
- model.layers.3.self_attn.o_proj
- model.layers.10.self_attn.o_proj
- model.layers.18.self_attn.o_proj
- model.layers.33.self_attn.o_proj
- model.layers.17.self_attn.o_proj
- model.layers.32.self_attn.o_proj
- model.layers.30.self_attn.o_proj
- model.layers.2.self_attn.o_proj
- model.layers.15.self_attn.o_proj
- model.layers.11.self_attn.o_proj
# self_attn.q_proj layers
- model.layers.14.self_attn.q_proj
- model.layers.11.self_attn.q_proj
- model.layers.15.self_attn.q_proj
- model.layers.9.self_attn.q_proj
- model.layers.8.self_attn.q_proj
- model.layers.18.self_attn.q_proj
- model.layers.12.self_attn.q_proj
- model.layers.13.self_attn.q_proj
- model.layers.19.self_attn.q_proj
- model.layers.16.self_attn.q_proj
- model.layers.10.self_attn.q_proj
- model.layers.17.self_attn.q_proj
- model.layers.7.self_attn.q_proj
- model.layers.5.self_attn.q_proj
- model.layers.20.self_attn.q_proj
- model.layers.3.self_attn.q_proj
- model.layers.26.self_attn.q_proj
- model.layers.27.self_attn.q_proj
- model.layers.28.self_attn.q_proj
- model.layers.33.self_attn.q_proj
# self_attn.v_proj layers
- model.layers.27.self_attn.v_proj
- model.layers.20.self_attn.v_proj
- model.layers.24.self_attn.v_proj
- model.layers.25.self_attn.v_proj
- model.layers.30.self_attn.v_proj
- model.layers.2.self_attn.v_proj
- model.layers.23.self_attn.v_proj
- model.layers.22.self_attn.v_proj
- model.layers.26.self_attn.v_proj
- model.layers.33.self_attn.v_proj
- model.layers.37.self_attn.v_proj
- model.layers.7.self_attn.v_proj
- model.layers.4.self_attn.v_proj
- model.layers.18.self_attn.v_proj
- model.layers.31.self_attn.v_proj
- model.layers.17.self_attn.v_proj
- model.layers.35.self_attn.v_proj
- model.layers.32.self_attn.v_proj
- model.layers.21.self_attn.v_proj
- model.layers.3.self_attn.v_proj
dataset_prepared_path: /workspace/axolotl/dolph-2.9.3-nemo-prepared
val_set_size: 0.01
output_dir: /workspace/axolotl/dolphin-2.9.3-mistral-nemo
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project: dolphin-2.9.3-Mistral-nemo
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 5e-6
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32:
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: 100
# evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
save_total_limit: 2
save_steps:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
special_tokens:
eos_token: "<|im_end|>"
pad_token: "<pad>"
bos_token: "<s>"
unk_token: "<unk>"
tokens:
- "<|im_start|>"
# fsdp:
# - full_shard
# - auto_wrap
# fsdp_config:
# fsdp_limit_all_gathers: true
# fsdp_sync_module_states: true
# fsdp_offload_params: true
# fsdp_use_orig_params: false
# fsdp_cpu_ram_efficient_loading: true
# fsdp_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock
# fsdp_state_dict_type: FULL_STATE_DICT
# fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
# fsdp_sharding_strategy: FULL_SHARD
# fsdp_forward_prefetch: false
# fsdp_backward_prefetch: BACKWARD_PRE
workspace/axolotl/dolphin-2.9.3-mistral-nemo
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5605
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: 8
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5691 | 1.0162 | 983 | 0.5734 |
0.5335 | 2.0174 | 1968 | 0.5609 |
0.5297 | 2.9639 | 2901 | 0.5605 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1