DeepDream2045 commited on
Commit
f0a1d34
·
verified ·
1 Parent(s): 1aa649f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: jingyeom/seal3.1.6n_7b
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: de839ffd-88b2-4ff5-85ca-684fa9c836d3
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: jingyeom/seal3.1.6n_7b
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - 11c78080fd4bcc0d_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/11c78080fd4bcc0d_train_data.json
31
+ type:
32
+ field_input: id
33
+ field_instruction: context
34
+ field_output: dataset
35
+ format: '{instruction} {input}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: 1
42
+ eval_max_new_tokens: 128
43
+ eval_steps: 25
44
+ eval_table_size: null
45
+ flash_attention: false
46
+ fp16: false
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 16
50
+ gradient_checkpointing: true
51
+ group_by_length: true
52
+ hub_model_id: DeepDream2045/de839ffd-88b2-4ff5-85ca-684fa9c836d3
53
+ hub_repo: null
54
+ hub_strategy: checkpoint
55
+ hub_token: null
56
+ learning_rate: 0.0001
57
+ load_in_4bit: false
58
+ load_in_8bit: false
59
+ local_rank: null
60
+ logging_steps: 1
61
+ lora_alpha: 64
62
+ lora_dropout: 0.05
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 32
66
+ lora_target_linear: true
67
+ lr_scheduler: cosine
68
+ max_steps: 50
69
+ micro_batch_size: 2
70
+ mlflow_experiment_name: /tmp/11c78080fd4bcc0d_train_data.json
71
+ model_type: AutoModelForCausalLM
72
+ num_epochs: 3
73
+ optimizer: adamw_torch
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
+ save_steps: 25
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: de839ffd-88b2-4ff5-85ca-684fa9c836d3
90
+ wandb_project: Gradients-On-Demand
91
+ wandb_run: your_name
92
+ wandb_runid: de839ffd-88b2-4ff5-85ca-684fa9c836d3
93
+ warmup_ratio: 0.05
94
+ weight_decay: 0.01
95
+ xformers_attention: true
96
+
97
+ ```
98
+
99
+ </details><br>
100
+
101
+ # de839ffd-88b2-4ff5-85ca-684fa9c836d3
102
+
103
+ This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 0.0028
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: 2
126
+ - eval_batch_size: 2
127
+ - seed: 42
128
+ - distributed_type: multi-GPU
129
+ - num_devices: 4
130
+ - gradient_accumulation_steps: 16
131
+ - total_train_batch_size: 128
132
+ - total_eval_batch_size: 8
133
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
134
+ - lr_scheduler_type: cosine
135
+ - lr_scheduler_warmup_steps: 2
136
+ - training_steps: 34
137
+
138
+ ### Training results
139
+
140
+ | Training Loss | Epoch | Step | Validation Loss |
141
+ |:-------------:|:------:|:----:|:---------------:|
142
+ | 5.0286 | 0.0894 | 1 | 4.4021 |
143
+ | 0.1096 | 2.2570 | 25 | 0.0028 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - PEFT 0.13.2
149
+ - Transformers 4.46.0
150
+ - Pytorch 2.4.1+cu124
151
+ - Datasets 3.0.1
152
+ - Tokenizers 0.20.1
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
  "up_proj",
25
- "k_proj",
26
- "down_proj",
27
  "gate_proj",
 
 
28
  "o_proj",
 
29
  "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
 
 
24
  "gate_proj",
25
+ "down_proj",
26
+ "k_proj",
27
  "o_proj",
28
+ "v_proj",
29
  "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4afc47dbc501b822e25c0cdc000280de74095b83eeb25555ac12858797c3b73
3
+ size 319977674
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7557a56d5c807366776e4fbd8080f5b5293562699529fae6526f3f957deb06
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be8897042dd870908e2b95e92353fbf5ecafc46d10f1068c1bf13a0323783cd
3
  size 319876032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b42f1ce68c7b4db4cb68bcee97e43a6c1d797d25c673c723efcb20fa6d8d4fb5
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36764b90adc2cda234cb27fbe5577f8dd90ec791c0bc4559b1a90ac18fa5b20d
3
  size 6776