fangzhaoz commited on
Commit
d89d764
1 Parent(s): f54c201

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: mistralai/Mistral-7B-v0.1
6
+ model-index:
7
+ - name: mistralv1_spectral_r4_6e-5_e5_bf16
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # mistralv1_spectral_r4_6e-5_e5_bf16
15
+
16
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 6e-05
36
+ - train_batch_size: 4
37
+ - eval_batch_size: 8
38
+ - seed: 0
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 5
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - PEFT 0.9.0
50
+ - Transformers 4.39.3
51
+ - Pytorch 2.2.2
52
+ - Datasets 2.18.0
53
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 8,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 4,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "spectral_bottom": false,
22
+ "spectral_top": true,
23
+ "target_modules": [
24
+ "o_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "v_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c196634c6eb22ae1e4dca85a48f16deff41322c6d77c671cecc17a19fbfb9c4
3
+ size 11576704
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff3b06b5ee840f264beb4b5af1161c6eaa5a5edb21d64f72e660f5716a60b1c
3
+ size 4984