nbninh commited on
Commit
a3024ab
1 Parent(s): 85b98cb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: jhflow/mistral7b-lora-multi-turn-v2
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 405d6641-60e6-4846-906f-6d2d62a581e4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ adapter: lora
21
+ base_model: jhflow/mistral7b-lora-multi-turn-v2
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - f88469f23669e6cb_train_data.json
28
+ ds_type: json
29
+ field: text_normalized
30
+ path: /workspace/input_data/f88469f23669e6cb_train_data.json
31
+ type: completion
32
+ debug: null
33
+ deepspeed: null
34
+ early_stopping_patience: null
35
+ eval_max_new_tokens: 128
36
+ eval_table_size: null
37
+ evals_per_epoch: 1
38
+ flash_attention: true
39
+ fp16: null
40
+ fsdp: null
41
+ fsdp_config: null
42
+ gradient_accumulation_steps: 1
43
+ gradient_checkpointing: true
44
+ gradient_clipping: 1.0
45
+ group_by_length: false
46
+ hub_model_id: nbninh/405d6641-60e6-4846-906f-6d2d62a581e4
47
+ hub_repo: null
48
+ hub_strategy: end
49
+ hub_token: null
50
+ learning_rate: 0.0001
51
+ load_in_4bit: true
52
+ load_in_8bit: true
53
+ local_rank: null
54
+ logging_steps: 1
55
+ lora_alpha: 32
56
+ lora_dropout: 0.1
57
+ lora_fan_in_fan_out: null
58
+ lora_model_dir: null
59
+ lora_r: 16
60
+ lora_target_linear: true
61
+ lr_scheduler: cosine
62
+ max_steps: 50
63
+ micro_batch_size: 1
64
+ mlflow_experiment_name: /tmp/f88469f23669e6cb_train_data.json
65
+ model_type: AutoModelForCausalLM
66
+ num_epochs: 1
67
+ optimizer: adamw_bnb_8bit
68
+ output_dir: miner_id_24
69
+ pad_to_sequence_len: true
70
+ resume_from_checkpoint: null
71
+ s2_attention: null
72
+ sample_packing: false
73
+ saves_per_epoch: 1
74
+ sequence_len: 2048
75
+ strict: false
76
+ tf32: false
77
+ tokenizer_type: AutoTokenizer
78
+ train_on_inputs: false
79
+ trust_remote_code: true
80
+ val_set_size: 0.05
81
+ wandb_entity: null
82
+ wandb_mode: online
83
+ wandb_name: 405d6641-60e6-4846-906f-6d2d62a581e4
84
+ wandb_project: Gradients-On-Demand
85
+ wandb_run: your_name
86
+ wandb_runid: 405d6641-60e6-4846-906f-6d2d62a581e4
87
+ warmup_steps: 10
88
+ weight_decay: 0.01
89
+ xformers_attention: true
90
+
91
+ ```
92
+
93
+ </details><br>
94
+
95
+ # 405d6641-60e6-4846-906f-6d2d62a581e4
96
+
97
+ This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2) on the None dataset.
98
+ It achieves the following results on the evaluation set:
99
+ - Loss: 3.1951
100
+
101
+ ## Model description
102
+
103
+ More information needed
104
+
105
+ ## Intended uses & limitations
106
+
107
+ More information needed
108
+
109
+ ## Training and evaluation data
110
+
111
+ More information needed
112
+
113
+ ## Training procedure
114
+
115
+ ### Training hyperparameters
116
+
117
+ The following hyperparameters were used during training:
118
+ - learning_rate: 0.0001
119
+ - train_batch_size: 1
120
+ - eval_batch_size: 1
121
+ - seed: 42
122
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
123
+ - lr_scheduler_type: cosine
124
+ - lr_scheduler_warmup_steps: 10
125
+ - training_steps: 50
126
+
127
+ ### Training results
128
+
129
+ | Training Loss | Epoch | Step | Validation Loss |
130
+ |:-------------:|:------:|:----:|:---------------:|
131
+ | 3.1894 | 0.0001 | 50 | 3.1951 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - PEFT 0.13.2
137
+ - Transformers 4.46.0
138
+ - Pytorch 2.5.0+cu124
139
+ - Datasets 3.0.1
140
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "jhflow/mistral7b-lora-multi-turn-v2",
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": 0.1,
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
+ "k_proj",
25
+ "gate_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "o_proj",
29
+ "q_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 sha256:0a5842fc3fdb9faa1db7e45555b528342318c84044b1780bbfc160712a74900c
3
+ size 167934026
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfb477a765f7fa2cd33578f4bf48bd5fd25abdac92418f0ef0f4a468a771129
3
+ size 167832240
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "jhflow/mistral7b-lora-multi-turn-v2",
4
+ "architectures": [
5
+ "MistralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 32768,
16
+ "model_type": "mistral",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": false,
32
+ "load_in_8bit": true,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_theta": 10000.0,
37
+ "sliding_window": 4096,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.46.0",
41
+ "use_cache": false,
42
+ "vocab_size": 32002
43
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": true,
9
+ "normalized": false,
10
+ "rstrip": true,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": true,
17
+ "normalized": false,
18
+ "rstrip": true,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": true,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "max_length": 4096,
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_token": "<unk>",
56
+ "sp_model_kwargs": {},
57
+ "spaces_between_special_tokens": false,
58
+ "stride": 0,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "trust_remote_code": false,
63
+ "unk_token": "<unk>",
64
+ "use_default_system_prompt": false,
65
+ "use_fast": true
66
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3538d54fbc0448ec1895232762c55e39f9f6cfad5aa598f21fe68fc230fcb1d
3
+ size 6776