Views
No views yet
0.6.01base_model: mistralai/Mistral-Small-Instruct-2409
2
3load_in_8bit: true
4load_in_4bit: false
5
6plugins:
7 - axolotl.integrations.liger.LigerPlugin
8liger_rope: true
9liger_rms_norm: true
10liger_glu_activation: true
11liger_fused_linear_cross_entropy: true
12
13#unsloth_lora_mlp: true
14#unsloth_lora_qkv: true
15#unsloth_lora_o: true
16
17strict: false
18
19adapter: lora
20lora_r: 16
21lora_alpha: 32
22lora_dropout: 0.25
23lora_target_modules:
24 - q_proj
25 - v_proj
26 - k_proj
27 - o_proj
28lora_target_linear: true
29peft_layers_to_transform:
30loraplus_lr_ratio: 16
31
32chat_template: jinja
33chat_template_jinja: "{%- if messages[0][\"role\"] == \"fake\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if message[\"role\"] == \"user\" or message[\"role\"] == \"system\"%}\n {%- if tools is not none and (message == user_messages[-1]) %}\n {{- \"[AVAILABLE_TOOLS][\" }}\n {%- for tool in tools %}\n {%- set tool = tool.function %}\n {{- '{\"type\": \"function\", \"function\": {' }}\n {%- for key, val in tool.items() if key != \"return\" %}\n {%- if val is string %}\n {{- '\"' + key + '\": \"' + val + '\"' }}\n {%- else %}\n {{- '\"' + key + '\": ' + val|tojson }}\n {%- endif %}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \"}}\" }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" }}\n {%- endif %}\n {%- endfor %}\n {{- \"[/AVAILABLE_TOOLS]\" }}\n {%- endif %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST]\" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n {%- else %}\n {{- \"[INST]\" + message[\"content\"] + \"[/INST]\" }}\n {%- endif %}\n {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}\n {{- \"[TOOL_CALLS][\" }}\n {%- for tool_call in message.tool_calls %}\n {%- set out = tool_call.function|tojson %}\n {{- out[:-1] }}\n {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- else %}\n {{- \"]\" + eos_token }}\n {%- endif %}\n {%- endfor %}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- message[\"content\"] + eos_token}}\n {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n {%- if message.content is defined and message.content.content is defined %}\n {%- set content = message.content.content %}\n {%- else %}\n {%- set content = message.content %}\n {%- endif %}\n {{- '[TOOL_RESULTS]{\"content\": ' + content|string + \", \" }}\n {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n {%- endif %}\n {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n {%- endif %}\n{%- endfor %}\n"
34datasets:
35 - path: Fizzarolli/inkmix-v2
36 type: chat_template
37 chat_template: tokenizer_default
38 split: train
39 field_messages: conversations
40 message_field_role: from
41 message_field_content: value
42
43dataset_prepared_path: last_run_prepared
44#val_set_size: 0.02
45output_dir: ./ckpts
46
47sequence_len: 8192
48sample_packing: true
49pad_to_sequence_len: true
50
51#wandb_project: teleut-7b-rp
52#wandb_entity:
53#wandb_watch:
54#wandb_name:
55#wandb_log_model: checkpoint
56
57# mlflow configuration if you're using it
58mlflow_tracking_uri: https://public-tracking.mlflow-e00zzfjq11ky6jcgtv.backbone-e00bgn6e63256prmhq.msp.eu-north1.nebius.cloud
59mlflow_experiment_name: ms-12b-rp-inkmixv2
60mlflow_run_name: v1
61hf_mlflow_log_artifacts: true
62
63gradient_accumulation_steps: 1
64micro_batch_size: 8
65num_epochs: 2
66optimizer: paged_adamw_8bit
67lr_scheduler: cosine
68learning_rate: 6e-5
69
70train_on_inputs: false
71group_by_length: false
72bf16: auto
73fp16:
74tf32: false
75
76gradient_checkpointing: unsloth
77gradient_checkpointing_kwargs:
78 use_reentrant: false
79early_stopping_patience:
80resume_from_checkpoint:
81logging_steps: 1
82xformers_attention:
83flash_attention: true
84
85#deepspeed: deepspeed_configs/zero3_bf16.json
86
87warmup_steps: 25
88#evals_per_epoch: 4
89eval_table_size:
90saves_per_epoch: 10
91debug:
92weight_decay: 0.01
93