Luongdzung commited on
Commit
e6b507b
1 Parent(s): dca3c76

End of training

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: vlsp-2023-vllm/hoa-1b4
3
+ library_name: peft
4
+ license: bigscience-bloom-rail-1.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: rsLora_500_last_question_wikiqa_seed_46
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
+ # rsLora_500_last_question_wikiqa_seed_46
16
+
17
+ This model is a fine-tuned version of [vlsp-2023-vllm/hoa-1b4](https://huggingface.co/vlsp-2023-vllm/hoa-1b4) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4834
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: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 3.0
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.513 | 1.0 | 50 | 0.5529 |
51
+ | 0.4674 | 2.0 | 100 | 0.4900 |
52
+ | 0.4291 | 3.0 | 150 | 0.4834 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.13.0
58
+ - Transformers 4.44.0
59
+ - Pytorch 2.4.0
60
+ - Datasets 2.21.0
61
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "vlsp-2023-vllm/hoa-1b4",
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": 8,
14
+ "lora_dropout": 0.0,
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
+ "query_key_value",
24
+ "dense_4h_to_h",
25
+ "dense",
26
+ "dense_h_to_4h"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": true
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c003ead0ab7c2614f47b7b0b48532628c4253a61a33bdbc2fe78b66d0ad91
3
+ size 25192496
runs/Oct07_16-07-16_f3f004385dbf/events.out.tfevents.1728317245.f3f004385dbf.36.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7717cb3678bc9d5ad3f2b007459e6093bc6975421bd55c7511990d2c9a96dca9
3
+ size 37436
runs/Oct07_16-07-16_f3f004385dbf/events.out.tfevents.1728317514.f3f004385dbf.36.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d3de1eb2caf4fa7e55cbbae1f689905b56a1dfadc021ec74a01159cdaece23
3
+ size 359
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c921f1529684e24f0f29b90809609bf425d21e6d0d66a437d8ac0e6ec795b4a
3
+ size 5240