Tippawan commited on
Commit
88a74e7
1 Parent(s): 5b5e33b

Training in progress, epoch 0

Browse files
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: SeaLLMs/SeaLLM3-7B-Chat
3
+ library_name: peft
4
+ license: other
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: proof-reading-SeaLLM3-7B-Chat-3090-v2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<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)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ base_model: SeaLLMs/SeaLLM3-7B-Chat
22
+ trust_remote_code: true
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: true
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v2
30
+ type: sharegpt
31
+ conversation: chatml
32
+ field_messages: messages
33
+ chat_template: chatml
34
+ dataset_prepared_path:
35
+ val_set_size: 0.00 #editted 2
36
+ output_dir: ./outputs/outputs_name
37
+
38
+ sequence_len: 2048
39
+ sample_packing: false
40
+ eval_sample_packing: false
41
+ pad_to_sequence_len: false
42
+
43
+ push_to_hub: true
44
+ hub_model_id: Tippawan/proof-reading-SeaLLM3-7B-Chat-3090-v2 # Replace with your Hugging Face repo ID
45
+ use_auth_token: true # Ensure you have set your Hugging Face API token in the environment
46
+ hub_private_repo: true # Set to true if you want the repository to be private
47
+ hub_strategy: all_checkpoints
48
+ save_total_limit: 3
49
+ load_best_model_at_end: true
50
+
51
+ adapter: qlora
52
+ lora_model_dir:
53
+ lora_r: 16
54
+ lora_alpha: 32
55
+ lora_dropout: 0.05
56
+ lora_target_linear: true
57
+ lora_fan_in_fan_out:
58
+
59
+ wandb_project: proof-reading-SeaLLM3-7B-Chat-3090-v2
60
+ wandb_entity:
61
+ wandb_watch:
62
+ wandb_name:
63
+ wandb_log_model:
64
+
65
+ gradient_accumulation_steps: 4
66
+ micro_batch_size: 4
67
+ num_epochs: 1 #editted 3
68
+ optimizer: adamw_torch
69
+ lr_scheduler: cosine
70
+ learning_rate: 0.0002
71
+
72
+ train_on_inputs: false
73
+ group_by_length: false
74
+ bf16: auto
75
+ fp16:
76
+ tf32: true
77
+
78
+ gradient_checkpointing: true
79
+ early_stopping_patience:
80
+ resume_from_checkpoint:
81
+ local_rank:
82
+ logging_steps: 1
83
+ xformers_attention:
84
+ flash_attention: true
85
+ seed: 42
86
+ warmup_steps: 10
87
+ evals_per_epoch: 1
88
+ saves_per_epoch: 1
89
+ debug:
90
+ deepspeed:
91
+ weight_decay: 0.0
92
+ fsdp:
93
+ fsdp_config:
94
+ special_tokens:
95
+ ```
96
+
97
+ </details><br>
98
+
99
+ # proof-reading-SeaLLM3-7B-Chat-3090-v2
100
+
101
+ This model is a fine-tuned version of [SeaLLMs/SeaLLM3-7B-Chat](https://huggingface.co/SeaLLMs/SeaLLM3-7B-Chat) on the None dataset.
102
+
103
+ ## Model description
104
+
105
+ More information needed
106
+
107
+ ## Intended uses & limitations
108
+
109
+ More information needed
110
+
111
+ ## Training and evaluation data
112
+
113
+ More information needed
114
+
115
+ ## Training procedure
116
+
117
+ ### Training hyperparameters
118
+
119
+ The following hyperparameters were used during training:
120
+ - learning_rate: 0.0002
121
+ - train_batch_size: 4
122
+ - eval_batch_size: 4
123
+ - seed: 42
124
+ - gradient_accumulation_steps: 4
125
+ - total_train_batch_size: 16
126
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
127
+ - lr_scheduler_type: cosine
128
+ - lr_scheduler_warmup_steps: 10
129
+ - num_epochs: 1
130
+
131
+ ### Training results
132
+
133
+
134
+
135
+ ### Framework versions
136
+
137
+ - PEFT 0.12.0
138
+ - Transformers 4.45.0.dev0
139
+ - Pytorch 2.3.1+cu121
140
+ - Datasets 2.21.0
141
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "SeaLLMs/SeaLLM3-7B-Chat",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "gate_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3e8ac4f51f2835203d41cba71d7bed76a4561b123311a9761500dc0507ea23
3
+ size 161621802
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d5f79de95597c6bac3283b8d8574170774f8b603a0b73edd710339874c936f
3
+ size 161533192
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SeaLLMs/SeaLLM3-7B-Chat",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "quantization_config": {
19
+ "_load_in_4bit": true,
20
+ "_load_in_8bit": false,
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_storage": "bfloat16",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": null,
35
+ "rope_theta": 1000000.0,
36
+ "sliding_window": null,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.45.0.dev0",
40
+ "use_cache": false,
41
+ "use_sliding_window": false,
42
+ "vocab_size": 152064
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a4b3e887d7607cb694108f5be11ac34e74e6c1b4afbe33161bd0c22b8c5f11
3
+ size 6200
vocab.json ADDED
The diff for this file is too large to render. See raw diff