thakkkkkk commited on
Commit
41afe5e
1 Parent(s): 62e858f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/CodeLlama-7b-hf-flash
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: c48b283d-a43b-4042-ace8-737577a1639c
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: NousResearch/CodeLlama-7b-hf-flash
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - e45bf77ec68bf027_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/e45bf77ec68bf027_train_data.json
31
+ type:
32
+ field_instruction: prompt
33
+ field_output: chosen
34
+ format: '{instruction}'
35
+ no_input_format: '{instruction}'
36
+ system_format: '{system}'
37
+ system_prompt: ''
38
+ debug: null
39
+ deepspeed: null
40
+ early_stopping_patience: null
41
+ eval_max_new_tokens: 128
42
+ eval_table_size: null
43
+ evals_per_epoch: 1
44
+ flash_attention: false
45
+ fp16: null
46
+ fsdp: null
47
+ fsdp_config: null
48
+ gradient_accumulation_steps: 4
49
+ gradient_checkpointing: true
50
+ gradient_clipping: 1.0
51
+ group_by_length: false
52
+ hub_model_id: thakkkkkk/c48b283d-a43b-4042-ace8-737577a1639c
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: 0.15
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: 100
69
+ micro_batch_size: 1
70
+ mlflow_experiment_name: /tmp/e45bf77ec68bf027_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
+ special_tokens:
82
+ pad_token: </s>
83
+ strict: false
84
+ tf32: true
85
+ tokenizer_type: AutoTokenizer
86
+ train_on_inputs: false
87
+ trust_remote_code: true
88
+ val_set_size: 0.05
89
+ wandb_entity: null
90
+ wandb_mode: online
91
+ wandb_name: c48b283d-a43b-4042-ace8-737577a1639c
92
+ wandb_project: Gradients-On-Demand
93
+ wandb_run: your_name
94
+ wandb_runid: c48b283d-a43b-4042-ace8-737577a1639c
95
+ warmup_steps: 10
96
+ weight_decay: 0.02
97
+ xformers_attention: true
98
+
99
+ ```
100
+
101
+ </details><br>
102
+
103
+ # c48b283d-a43b-4042-ace8-737577a1639c
104
+
105
+ This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-7b-hf-flash) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: 0.0000
108
+
109
+ ## Model description
110
+
111
+ More information needed
112
+
113
+ ## Intended uses & limitations
114
+
115
+ More information needed
116
+
117
+ ## Training and evaluation data
118
+
119
+ More information needed
120
+
121
+ ## Training procedure
122
+
123
+ ### Training hyperparameters
124
+
125
+ The following hyperparameters were used during training:
126
+ - learning_rate: 0.0001
127
+ - train_batch_size: 1
128
+ - eval_batch_size: 1
129
+ - seed: 42
130
+ - gradient_accumulation_steps: 4
131
+ - total_train_batch_size: 4
132
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
133
+ - lr_scheduler_type: cosine
134
+ - lr_scheduler_warmup_steps: 10
135
+ - training_steps: 100
136
+
137
+ ### Training results
138
+
139
+ | Training Loss | Epoch | Step | Validation Loss |
140
+ |:-------------:|:------:|:----:|:---------------:|
141
+ | 0.0 | 0.0195 | 100 | 0.0000 |
142
+
143
+
144
+ ### Framework versions
145
+
146
+ - PEFT 0.13.2
147
+ - Transformers 4.46.0
148
+ - Pytorch 2.5.0+cu124
149
+ - Datasets 3.0.1
150
+ - 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": "NousResearch/CodeLlama-7b-hf-flash",
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": 0.15,
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
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "o_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "v_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 sha256:3d8f8fc7bdb55530907591e9d4aa3903692c3c7c47b22c42d29e8d1f3a7c90df
3
+ size 160069834
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f4cbcc1e85a3f88aec670e71e227a6b0d1c08789e7d994e177db7e6d4d6c92
3
+ size 159967880
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "NousResearch/CodeLlama-7b-hf-flash",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "NousResearch/CodeLlama-7b-hf-flash--configuration_llama.LlamaConfig",
9
+ "AutoModel": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaModel",
10
+ "AutoModelForCausalLM": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaForCausalLM",
11
+ "AutoModelForSequenceClassification": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaForSequenceClassification"
12
+ },
13
+ "bos_token_id": 1,
14
+ "eos_token_id": 2,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 11008,
19
+ "max_position_embeddings": 16384,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "_load_in_4bit": false,
27
+ "_load_in_8bit": true,
28
+ "bnb_4bit_compute_dtype": "float32",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "fp4",
31
+ "bnb_4bit_use_double_quant": false,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": false,
37
+ "load_in_8bit": true,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "rms_norm_eps": 1e-05,
41
+ "rope_scaling": null,
42
+ "rope_theta": 1000000,
43
+ "tie_word_embeddings": false,
44
+ "torch_dtype": "float16",
45
+ "transformers_version": "4.46.0",
46
+ "use_cache": false,
47
+ "vocab_size": 32016
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": "</s>",
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d7be5683f028bf68521c25c2f923da067abf89a678db25eee64459e403f3df1
3
+ size 6776