nbninh commited on
Commit
5055463
1 Parent(s): 43e6f8a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/llama-2-7b
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 6ff46efe-27f7-4fe7-a728-65f38828e0e6
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
+ adapter: lora
22
+ base_model: unsloth/llama-2-7b
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 40d5c2cb9c53aaac_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/40d5c2cb9c53aaac_train_data.json
32
+ type:
33
+ field_instruction: title
34
+ field_output: abstract
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: null
42
+ eval_max_new_tokens: 128
43
+ eval_table_size: null
44
+ evals_per_epoch: 1
45
+ flash_attention: true
46
+ fp16: null
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 1
50
+ gradient_checkpointing: true
51
+ group_by_length: false
52
+ hub_model_id: nbninh/6ff46efe-27f7-4fe7-a728-65f38828e0e6
53
+ hub_repo: null
54
+ hub_strategy: end
55
+ hub_token: null
56
+ learning_rate: 0.0001
57
+ load_in_4bit: true
58
+ load_in_8bit: true
59
+ local_rank: null
60
+ logging_steps: 1
61
+ lora_alpha: 32
62
+ lora_dropout: 0.05
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 16
66
+ lora_target_linear: true
67
+ lr_scheduler: cosine
68
+ max_steps: 50
69
+ micro_batch_size: 1
70
+ mlflow_experiment_name: /tmp/40d5c2cb9c53aaac_train_data.json
71
+ model_type: AutoModelForCausalLM
72
+ num_epochs: 1
73
+ optimizer: adamw_bnb_8bit
74
+ output_dir: miner_id_24
75
+ pad_to_sequence_len: true
76
+ resume_from_checkpoint: null
77
+ s2_attention: null
78
+ sample_packing: false
79
+ saves_per_epoch: 1
80
+ sequence_len: 2048
81
+ strict: false
82
+ tf32: false
83
+ tokenizer_type: AutoTokenizer
84
+ train_on_inputs: false
85
+ trust_remote_code: true
86
+ val_set_size: 0.05
87
+ wandb_entity: null
88
+ wandb_mode: online
89
+ wandb_name: 6ff46efe-27f7-4fe7-a728-65f38828e0e6
90
+ wandb_project: Gradients-On-Demand
91
+ wandb_run: your_name
92
+ wandb_runid: 6ff46efe-27f7-4fe7-a728-65f38828e0e6
93
+ warmup_steps: 10
94
+ weight_decay: 0.0
95
+ xformers_attention: true
96
+
97
+ ```
98
+
99
+ </details><br>
100
+
101
+ # 6ff46efe-27f7-4fe7-a728-65f38828e0e6
102
+
103
+ This model is a fine-tuned version of [unsloth/llama-2-7b](https://huggingface.co/unsloth/llama-2-7b) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 2.3057
106
+
107
+ ## Model description
108
+
109
+ More information needed
110
+
111
+ ## Intended uses & limitations
112
+
113
+ More information needed
114
+
115
+ ## Training and evaluation data
116
+
117
+ More information needed
118
+
119
+ ## Training procedure
120
+
121
+ ### Training hyperparameters
122
+
123
+ The following hyperparameters were used during training:
124
+ - learning_rate: 0.0001
125
+ - train_batch_size: 1
126
+ - eval_batch_size: 1
127
+ - seed: 42
128
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
129
+ - lr_scheduler_type: cosine
130
+ - lr_scheduler_warmup_steps: 10
131
+ - training_steps: 50
132
+
133
+ ### Training results
134
+
135
+ | Training Loss | Epoch | Step | Validation Loss |
136
+ |:-------------:|:------:|:----:|:---------------:|
137
+ | 2.4915 | 0.0351 | 50 | 2.3057 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - PEFT 0.13.2
143
+ - Transformers 4.46.0
144
+ - Pytorch 2.5.0+cu124
145
+ - Datasets 3.0.1
146
+ - 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": "unsloth/llama-2-7b",
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
+ "q_proj",
24
+ "gate_proj",
25
+ "down_proj",
26
+ "up_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "o_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:e339805612e4a5e49c0b6beb359578e7865e6e29d431a3636e90a3263e80ce97
3
+ size 160069834
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c7ff40aea6269850b8a4b369812349c52f65fb07fead03226a2d0ceeebd681
3
+ size 159967880
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "unsloth/llama-2-7b",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 11008,
16
+ "max_position_embeddings": 4096,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "_load_in_4bit": false,
26
+ "_load_in_8bit": true,
27
+ "bnb_4bit_compute_dtype": "float32",
28
+ "bnb_4bit_quant_storage": "uint8",
29
+ "bnb_4bit_quant_type": "fp4",
30
+ "bnb_4bit_use_double_quant": false,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": false,
36
+ "load_in_8bit": true,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": null,
41
+ "rope_theta": 10000.0,
42
+ "tie_word_embeddings": false,
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.46.0",
45
+ "unsloth_version": "2024.9",
46
+ "use_cache": false,
47
+ "vocab_size": 32000
48
+ }
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
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
+ },
31
+ "bos_token": "<s>",
32
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "left",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df65babe431d89957899bafe5e647b8a0c9ed5adc0e9dfe7ae845a5b3a87fca
3
+ size 6776