Upload 11 files
Browse files- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +13 -0
- llamaboard_config.yaml +63 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +131 -0
- trainer_state.json +379 -0
- training_args.bin +3 -0
- training_args.yaml +33 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"qkv_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"gate_up_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9c54b81b7de53f7d5e8be09b01ddf4778b4f0cf1e55e9f086ccb5e569647b1d
|
| 3 |
+
size 50365768
|
added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
llamaboard_config.yaml
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
top.booster: none
|
| 2 |
+
top.checkpoint_path: null
|
| 3 |
+
top.finetuning_type: lora
|
| 4 |
+
top.model_name: Phi3-4B-4k-Chat
|
| 5 |
+
top.quantization_bit: '4'
|
| 6 |
+
top.rope_scaling: none
|
| 7 |
+
top.template: phi
|
| 8 |
+
top.visual_inputs: false
|
| 9 |
+
train.additional_target: ''
|
| 10 |
+
train.badam_mode: layer
|
| 11 |
+
train.badam_switch_interval: 50
|
| 12 |
+
train.badam_switch_mode: ascending
|
| 13 |
+
train.badam_update_ratio: 0.05
|
| 14 |
+
train.batch_size: 2
|
| 15 |
+
train.compute_type: fp16
|
| 16 |
+
train.create_new_adapter: false
|
| 17 |
+
train.cutoff_len: 4096
|
| 18 |
+
train.dataset:
|
| 19 |
+
- claimver_kgllm
|
| 20 |
+
train.dataset_dir: data
|
| 21 |
+
train.ds_offload: false
|
| 22 |
+
train.ds_stage: none
|
| 23 |
+
train.freeze_extra_modules: ''
|
| 24 |
+
train.freeze_trainable_layers: 2
|
| 25 |
+
train.freeze_trainable_modules: all
|
| 26 |
+
train.galore_rank: 16
|
| 27 |
+
train.galore_scale: 0.25
|
| 28 |
+
train.galore_target: all
|
| 29 |
+
train.galore_update_interval: 200
|
| 30 |
+
train.gradient_accumulation_steps: 8
|
| 31 |
+
train.learning_rate: 5e-5
|
| 32 |
+
train.logging_steps: 5
|
| 33 |
+
train.lora_alpha: 16
|
| 34 |
+
train.lora_dropout: 0
|
| 35 |
+
train.lora_rank: 8
|
| 36 |
+
train.lora_target: ''
|
| 37 |
+
train.loraplus_lr_ratio: 0
|
| 38 |
+
train.lr_scheduler_type: cosine
|
| 39 |
+
train.max_grad_norm: '1.0'
|
| 40 |
+
train.max_samples: '100000'
|
| 41 |
+
train.neftune_alpha: 0
|
| 42 |
+
train.num_train_epochs: '2'
|
| 43 |
+
train.optim: adamw_torch
|
| 44 |
+
train.packing: false
|
| 45 |
+
train.ppo_score_norm: false
|
| 46 |
+
train.ppo_whiten_rewards: false
|
| 47 |
+
train.pref_beta: 0.1
|
| 48 |
+
train.pref_ftx: 0
|
| 49 |
+
train.pref_loss: sigmoid
|
| 50 |
+
train.report_to: false
|
| 51 |
+
train.resize_vocab: false
|
| 52 |
+
train.reward_model: null
|
| 53 |
+
train.save_steps: 100
|
| 54 |
+
train.shift_attn: false
|
| 55 |
+
train.training_stage: Supervised Fine-Tuning
|
| 56 |
+
train.upcast_layernorm: false
|
| 57 |
+
train.use_badam: false
|
| 58 |
+
train.use_dora: false
|
| 59 |
+
train.use_galore: false
|
| 60 |
+
train.use_llama_pro: false
|
| 61 |
+
train.use_rslora: false
|
| 62 |
+
train.val_size: 0
|
| 63 |
+
train.warmup_steps: 0
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": true,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<|assistant|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<|placeholder1|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": true,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<|placeholder2|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": true,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<|placeholder3|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": true,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<|placeholder4|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": true,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<|system|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": true,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<|end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<|placeholder5|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": true,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<|placeholder6|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": true,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<|user|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": true,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
}
|
| 117 |
+
},
|
| 118 |
+
"bos_token": "<s>",
|
| 119 |
+
"chat_template": "{% set system_message = 'You are a helpful AI assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<s>' + '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
| 120 |
+
"clean_up_tokenization_spaces": false,
|
| 121 |
+
"eos_token": "<|end|>",
|
| 122 |
+
"legacy": false,
|
| 123 |
+
"model_max_length": 4096,
|
| 124 |
+
"pad_token": "<|endoftext|>",
|
| 125 |
+
"padding_side": "right",
|
| 126 |
+
"sp_model_kwargs": {},
|
| 127 |
+
"split_special_tokens": false,
|
| 128 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 129 |
+
"unk_token": "<unk>",
|
| 130 |
+
"use_default_system_prompt": false
|
| 131 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9952941176470587,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 212,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.047058823529411764,
|
| 13 |
+
"grad_norm": 0.5000221729278564,
|
| 14 |
+
"learning_rate": 4.9931407070965254e-05,
|
| 15 |
+
"loss": 0.841,
|
| 16 |
+
"num_input_tokens_seen": 114256,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09411764705882353,
|
| 21 |
+
"grad_norm": 0.38539719581604004,
|
| 22 |
+
"learning_rate": 4.97260046830541e-05,
|
| 23 |
+
"loss": 0.692,
|
| 24 |
+
"num_input_tokens_seen": 225200,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.1411764705882353,
|
| 29 |
+
"grad_norm": 0.275894433259964,
|
| 30 |
+
"learning_rate": 4.9384919968379945e-05,
|
| 31 |
+
"loss": 0.5684,
|
| 32 |
+
"num_input_tokens_seen": 338592,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.18823529411764706,
|
| 37 |
+
"grad_norm": 0.22247478365898132,
|
| 38 |
+
"learning_rate": 4.891002460691306e-05,
|
| 39 |
+
"loss": 0.5256,
|
| 40 |
+
"num_input_tokens_seen": 455856,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.23529411764705882,
|
| 45 |
+
"grad_norm": 0.20748302340507507,
|
| 46 |
+
"learning_rate": 4.83039245557597e-05,
|
| 47 |
+
"loss": 0.483,
|
| 48 |
+
"num_input_tokens_seen": 569056,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.2823529411764706,
|
| 53 |
+
"grad_norm": 0.207512766122818,
|
| 54 |
+
"learning_rate": 4.756994574914359e-05,
|
| 55 |
+
"loss": 0.4401,
|
| 56 |
+
"num_input_tokens_seen": 683408,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32941176470588235,
|
| 61 |
+
"grad_norm": 0.18322080373764038,
|
| 62 |
+
"learning_rate": 4.6712115847560355e-05,
|
| 63 |
+
"loss": 0.4162,
|
| 64 |
+
"num_input_tokens_seen": 802032,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3764705882352941,
|
| 69 |
+
"grad_norm": 0.16893012821674347,
|
| 70 |
+
"learning_rate": 4.573514213625505e-05,
|
| 71 |
+
"loss": 0.3951,
|
| 72 |
+
"num_input_tokens_seen": 917808,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.4235294117647059,
|
| 77 |
+
"grad_norm": 0.17897149920463562,
|
| 78 |
+
"learning_rate": 4.464438569430354e-05,
|
| 79 |
+
"loss": 0.4007,
|
| 80 |
+
"num_input_tokens_seen": 1037840,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.47058823529411764,
|
| 85 |
+
"grad_norm": 0.14339417219161987,
|
| 86 |
+
"learning_rate": 4.344583197604318e-05,
|
| 87 |
+
"loss": 0.3672,
|
| 88 |
+
"num_input_tokens_seen": 1154864,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.5176470588235295,
|
| 93 |
+
"grad_norm": 0.1722479611635208,
|
| 94 |
+
"learning_rate": 4.214605796628527e-05,
|
| 95 |
+
"loss": 0.3764,
|
| 96 |
+
"num_input_tokens_seen": 1273984,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.5647058823529412,
|
| 101 |
+
"grad_norm": 0.15474933385849,
|
| 102 |
+
"learning_rate": 4.075219608954278e-05,
|
| 103 |
+
"loss": 0.361,
|
| 104 |
+
"num_input_tokens_seen": 1391904,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.611764705882353,
|
| 109 |
+
"grad_norm": 0.14795532822608948,
|
| 110 |
+
"learning_rate": 3.927189507131938e-05,
|
| 111 |
+
"loss": 0.3472,
|
| 112 |
+
"num_input_tokens_seen": 1506640,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.6588235294117647,
|
| 117 |
+
"grad_norm": 0.1496661901473999,
|
| 118 |
+
"learning_rate": 3.7713277966230514e-05,
|
| 119 |
+
"loss": 0.3497,
|
| 120 |
+
"num_input_tokens_seen": 1619120,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7058823529411765,
|
| 125 |
+
"grad_norm": 0.15912510454654694,
|
| 126 |
+
"learning_rate": 3.608489758327472e-05,
|
| 127 |
+
"loss": 0.3552,
|
| 128 |
+
"num_input_tokens_seen": 1739248,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7529411764705882,
|
| 133 |
+
"grad_norm": 0.17292849719524384,
|
| 134 |
+
"learning_rate": 3.4395689552855955e-05,
|
| 135 |
+
"loss": 0.3369,
|
| 136 |
+
"num_input_tokens_seen": 1854336,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.8,
|
| 141 |
+
"grad_norm": 0.1803598403930664,
|
| 142 |
+
"learning_rate": 3.265492329309867e-05,
|
| 143 |
+
"loss": 0.3302,
|
| 144 |
+
"num_input_tokens_seen": 1971904,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.8470588235294118,
|
| 149 |
+
"grad_norm": 0.171905979514122,
|
| 150 |
+
"learning_rate": 3.0872151144524595e-05,
|
| 151 |
+
"loss": 0.3305,
|
| 152 |
+
"num_input_tokens_seen": 2080496,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8941176470588236,
|
| 157 |
+
"grad_norm": 0.17595848441123962,
|
| 158 |
+
"learning_rate": 2.9057155952211502e-05,
|
| 159 |
+
"loss": 0.3239,
|
| 160 |
+
"num_input_tokens_seen": 2191968,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.9411764705882353,
|
| 165 |
+
"grad_norm": 0.16902042925357819,
|
| 166 |
+
"learning_rate": 2.7219897383073373e-05,
|
| 167 |
+
"loss": 0.3111,
|
| 168 |
+
"num_input_tokens_seen": 2306544,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.9882352941176471,
|
| 173 |
+
"grad_norm": 0.17742857336997986,
|
| 174 |
+
"learning_rate": 2.537045727284232e-05,
|
| 175 |
+
"loss": 0.2959,
|
| 176 |
+
"num_input_tokens_seen": 2418400,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.035294117647059,
|
| 181 |
+
"grad_norm": 0.16856059432029724,
|
| 182 |
+
"learning_rate": 2.3518984302657146e-05,
|
| 183 |
+
"loss": 0.306,
|
| 184 |
+
"num_input_tokens_seen": 2537984,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.0823529411764705,
|
| 189 |
+
"grad_norm": 0.19464781880378723,
|
| 190 |
+
"learning_rate": 2.1675638308842145e-05,
|
| 191 |
+
"loss": 0.3206,
|
| 192 |
+
"num_input_tokens_seen": 2656416,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.1294117647058823,
|
| 197 |
+
"grad_norm": 0.17075157165527344,
|
| 198 |
+
"learning_rate": 1.9850534531472546e-05,
|
| 199 |
+
"loss": 0.3053,
|
| 200 |
+
"num_input_tokens_seen": 2773280,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.1764705882352942,
|
| 205 |
+
"grad_norm": 0.173744335770607,
|
| 206 |
+
"learning_rate": 1.8053688107658908e-05,
|
| 207 |
+
"loss": 0.3176,
|
| 208 |
+
"num_input_tokens_seen": 2889024,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.223529411764706,
|
| 213 |
+
"grad_norm": 0.18248489499092102,
|
| 214 |
+
"learning_rate": 1.6294959114140034e-05,
|
| 215 |
+
"loss": 0.2997,
|
| 216 |
+
"num_input_tokens_seen": 3004880,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.2705882352941176,
|
| 221 |
+
"grad_norm": 0.1806834191083908,
|
| 222 |
+
"learning_rate": 1.4583998460759424e-05,
|
| 223 |
+
"loss": 0.2954,
|
| 224 |
+
"num_input_tokens_seen": 3117936,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.3176470588235294,
|
| 229 |
+
"grad_norm": 0.1907871961593628,
|
| 230 |
+
"learning_rate": 1.2930194931731382e-05,
|
| 231 |
+
"loss": 0.3048,
|
| 232 |
+
"num_input_tokens_seen": 3231712,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.3647058823529412,
|
| 237 |
+
"grad_norm": 0.20322641730308533,
|
| 238 |
+
"learning_rate": 1.1342623665304209e-05,
|
| 239 |
+
"loss": 0.3208,
|
| 240 |
+
"num_input_tokens_seen": 3350528,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.4117647058823528,
|
| 245 |
+
"grad_norm": 0.16647660732269287,
|
| 246 |
+
"learning_rate": 9.829996354535172e-06,
|
| 247 |
+
"loss": 0.3015,
|
| 248 |
+
"num_input_tokens_seen": 3464144,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.4588235294117646,
|
| 253 |
+
"grad_norm": 0.18004418909549713,
|
| 254 |
+
"learning_rate": 8.400613442446948e-06,
|
| 255 |
+
"loss": 0.3106,
|
| 256 |
+
"num_input_tokens_seen": 3580464,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.5058823529411764,
|
| 261 |
+
"grad_norm": 0.1924523115158081,
|
| 262 |
+
"learning_rate": 7.062318573891716e-06,
|
| 263 |
+
"loss": 0.3055,
|
| 264 |
+
"num_input_tokens_seen": 3695040,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.5529411764705883,
|
| 269 |
+
"grad_norm": 0.19149142503738403,
|
| 270 |
+
"learning_rate": 5.822455554065217e-06,
|
| 271 |
+
"loss": 0.3069,
|
| 272 |
+
"num_input_tokens_seen": 3812512,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.6,
|
| 277 |
+
"grad_norm": 0.19474638998508453,
|
| 278 |
+
"learning_rate": 4.687828049857967e-06,
|
| 279 |
+
"loss": 0.2806,
|
| 280 |
+
"num_input_tokens_seen": 3922976,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.6470588235294117,
|
| 285 |
+
"grad_norm": 0.19301049411296844,
|
| 286 |
+
"learning_rate": 3.6646622551801345e-06,
|
| 287 |
+
"loss": 0.2782,
|
| 288 |
+
"num_input_tokens_seen": 4038656,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6941176470588235,
|
| 293 |
+
"grad_norm": 0.20220619440078735,
|
| 294 |
+
"learning_rate": 2.75857272513132e-06,
|
| 295 |
+
"loss": 0.3066,
|
| 296 |
+
"num_input_tokens_seen": 4154032,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.7411764705882353,
|
| 301 |
+
"grad_norm": 0.19466643035411835,
|
| 302 |
+
"learning_rate": 1.9745315664982276e-06,
|
| 303 |
+
"loss": 0.2908,
|
| 304 |
+
"num_input_tokens_seen": 4267600,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.788235294117647,
|
| 309 |
+
"grad_norm": 0.17281493544578552,
|
| 310 |
+
"learning_rate": 1.3168411536452152e-06,
|
| 311 |
+
"loss": 0.2829,
|
| 312 |
+
"num_input_tokens_seen": 4382640,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.835294117647059,
|
| 317 |
+
"grad_norm": 0.19972845911979675,
|
| 318 |
+
"learning_rate": 7.891105195175358e-07,
|
| 319 |
+
"loss": 0.2968,
|
| 320 |
+
"num_input_tokens_seen": 4503040,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.8823529411764706,
|
| 325 |
+
"grad_norm": 0.17375272512435913,
|
| 326 |
+
"learning_rate": 3.9423555131007925e-07,
|
| 327 |
+
"loss": 0.2968,
|
| 328 |
+
"num_input_tokens_seen": 4618144,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.9294117647058824,
|
| 333 |
+
"grad_norm": 0.17855483293533325,
|
| 334 |
+
"learning_rate": 1.343830994765982e-07,
|
| 335 |
+
"loss": 0.2879,
|
| 336 |
+
"num_input_tokens_seen": 4731744,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.9764705882352942,
|
| 341 |
+
"grad_norm": 0.20227883756160736,
|
| 342 |
+
"learning_rate": 1.0979087280141298e-08,
|
| 343 |
+
"loss": 0.3026,
|
| 344 |
+
"num_input_tokens_seen": 4844416,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.9952941176470587,
|
| 349 |
+
"num_input_tokens_seen": 4890624,
|
| 350 |
+
"step": 212,
|
| 351 |
+
"total_flos": 1.0960363294870733e+17,
|
| 352 |
+
"train_loss": 0.36075482390961555,
|
| 353 |
+
"train_runtime": 1824.8202,
|
| 354 |
+
"train_samples_per_second": 3.726,
|
| 355 |
+
"train_steps_per_second": 0.116
|
| 356 |
+
}
|
| 357 |
+
],
|
| 358 |
+
"logging_steps": 5,
|
| 359 |
+
"max_steps": 212,
|
| 360 |
+
"num_input_tokens_seen": 4890624,
|
| 361 |
+
"num_train_epochs": 2,
|
| 362 |
+
"save_steps": 100,
|
| 363 |
+
"stateful_callbacks": {
|
| 364 |
+
"TrainerControl": {
|
| 365 |
+
"args": {
|
| 366 |
+
"should_epoch_stop": false,
|
| 367 |
+
"should_evaluate": false,
|
| 368 |
+
"should_log": false,
|
| 369 |
+
"should_save": true,
|
| 370 |
+
"should_training_stop": false
|
| 371 |
+
},
|
| 372 |
+
"attributes": {}
|
| 373 |
+
}
|
| 374 |
+
},
|
| 375 |
+
"total_flos": 1.0960363294870733e+17,
|
| 376 |
+
"train_batch_size": 2,
|
| 377 |
+
"trial_name": null,
|
| 378 |
+
"trial_params": null
|
| 379 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6044ecd5cce8a7c0f82ecb44a89fed522dd530bc42bf831f6f045c1fbb64ccaa
|
| 3 |
+
size 5304
|
training_args.yaml
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
cutoff_len: 4096
|
| 2 |
+
dataset: claimver_kgllm
|
| 3 |
+
dataset_dir: data
|
| 4 |
+
ddp_timeout: 180000000
|
| 5 |
+
do_train: true
|
| 6 |
+
finetuning_type: lora
|
| 7 |
+
flash_attn: auto
|
| 8 |
+
fp16: true
|
| 9 |
+
gradient_accumulation_steps: 8
|
| 10 |
+
include_num_input_tokens_seen: true
|
| 11 |
+
learning_rate: 5.0e-05
|
| 12 |
+
logging_steps: 5
|
| 13 |
+
lora_alpha: 16
|
| 14 |
+
lora_dropout: 0
|
| 15 |
+
lora_rank: 8
|
| 16 |
+
lora_target: all
|
| 17 |
+
lr_scheduler_type: cosine
|
| 18 |
+
max_grad_norm: 1.0
|
| 19 |
+
max_samples: 100000
|
| 20 |
+
model_name_or_path: microsoft/Phi-3-mini-4k-instruct
|
| 21 |
+
num_train_epochs: 2.0
|
| 22 |
+
optim: adamw_torch
|
| 23 |
+
output_dir: saves/Phi3-4B-4k-Chat/lora/phi3-4B4K-chat_claimver_run2
|
| 24 |
+
packing: false
|
| 25 |
+
per_device_train_batch_size: 2
|
| 26 |
+
plot_loss: true
|
| 27 |
+
preprocessing_num_workers: 16
|
| 28 |
+
quantization_bit: 4
|
| 29 |
+
report_to: none
|
| 30 |
+
save_steps: 100
|
| 31 |
+
stage: sft
|
| 32 |
+
template: phi
|
| 33 |
+
warmup_steps: 0
|