frankvitetta commited on
Commit
45a9015
1 Parent(s): ce73322

frankvitetta/frankvitetta-ft

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
7
+ model-index:
8
+ - name: shawgpt-ft
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
+ # shawgpt-ft
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 an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.8250
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
+ | 4.592 | 0.92 | 3 | 3.9556 |
55
+ | 4.0381 | 1.85 | 6 | 3.4300 |
56
+ | 3.4595 | 2.77 | 9 | 2.9801 |
57
+ | 2.2522 | 4.0 | 13 | 2.5503 |
58
+ | 2.6555 | 4.92 | 16 | 2.2883 |
59
+ | 2.3303 | 5.85 | 19 | 2.1013 |
60
+ | 2.099 | 6.77 | 22 | 1.9488 |
61
+ | 1.4765 | 8.0 | 26 | 1.8773 |
62
+ | 1.9247 | 8.92 | 29 | 1.8372 |
63
+ | 1.3414 | 9.23 | 30 | 1.8250 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - PEFT 0.10.0
69
+ - Transformers 4.38.2
70
+ - Pytorch 2.1.0+cu121
71
+ - Datasets 2.18.0
72
+ - Tokenizers 0.15.2
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 sha256:549b86639ed3a72a2d88ac0b93569d393b111b9c7342400e2f3f2ac3bf5ee6a3
3
+ size 8397056
runs/Apr02_08-03-13_bd277842f788/events.out.tfevents.1712045005.bd277842f788.232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dcc056547300de031441d0170fa68a72e8b386094b59162565e6a0a265f07e
3
+ size 10286
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85cfb580009b0fcfab4b77cf5fd0fa821a8ac593feddb702bbeb7f17a8bd2d68
3
+ size 4856