vjvk commited on
Commit
ba2a267
1 Parent(s): d418353

vjvk/shoptalk_assist_mistral_7b_qlora_finetuned_small_chunks

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Mistral-7B-Instruct-v0.2-GPTQ_finetune_s1000
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
+ # Mistral-7B-Instruct-v0.2-GPTQ_finetune_s1000
16
+
17
+ This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6456
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 10
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.2303 | 0.9829 | 43 | 0.8563 |
55
+ | 0.6964 | 1.9886 | 87 | 0.7045 |
56
+ | 0.6032 | 2.9943 | 131 | 0.6661 |
57
+ | 0.558 | 4.0 | 175 | 0.6472 |
58
+ | 0.5376 | 4.9829 | 218 | 0.6400 |
59
+ | 0.4962 | 5.9886 | 262 | 0.6360 |
60
+ | 0.4754 | 6.9943 | 306 | 0.6359 |
61
+ | 0.4593 | 8.0 | 350 | 0.6393 |
62
+ | 0.456 | 8.9829 | 393 | 0.6430 |
63
+ | 0.4305 | 9.8286 | 430 | 0.6456 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - PEFT 0.11.1
69
+ - Transformers 4.41.2
70
+ - Pytorch 2.3.0+cu121
71
+ - Datasets 2.20.0
72
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
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": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_dora": false,
27
+ "use_rslora": false
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37d1db1466a6a062c7de9c6172e2fa1f57fced0e87fd6982c667b3ba5e4ee62
3
+ size 8397056
runs/Jul03_03-32-45_8f517729a969/events.out.tfevents.1719977568.8f517729a969.395.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7861019e9530428524bf23051a29297528094499c933c87719290cd9f44fd802
3
+ size 10853
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95de755d5d4509b83a28d28cb7bdde5f0e02c6bdde425580847444a89132834
3
+ size 5240