jysssacc commited on
Commit
9a6d053
1 Parent(s): 9b35578

End of training

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: facebook/opt-1.3b
7
+ model-index:
8
+ - name: opt-1.3b_adalora_627_lr5e-05_bs4_epoch5_wd0.01
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
+ # opt-1.3b_adalora_627_lr5e-05_bs4_epoch5_wd0.01
16
+
17
+ This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.0160
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: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 500
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 4.5943 | 1.0 | 157 | 4.2292 |
52
+ | 4.1943 | 2.0 | 314 | 3.8077 |
53
+ | 3.8866 | 3.0 | 471 | 3.2970 |
54
+ | 3.2933 | 4.0 | 628 | 3.0521 |
55
+ | 3.1627 | 5.0 | 785 | 3.0160 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - PEFT 0.7.1
61
+ - Transformers 4.36.2
62
+ - Pytorch 2.0.1
63
+ - Datasets 2.16.1
64
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/opt-1.3b",
5
+ "beta1": 0.85,
6
+ "beta2": 0.85,
7
+ "bias": "none",
8
+ "deltaT": 1,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "init_r": 12,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "orth_reg_weight": 0.5,
22
+ "peft_type": "ADALORA",
23
+ "r": 8,
24
+ "rank_pattern": null,
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj",
30
+ "out_proj",
31
+ "fc1",
32
+ "fc2"
33
+ ],
34
+ "target_r": 8,
35
+ "task_type": "CAUSAL_LM",
36
+ "tfinal": 0,
37
+ "tinit": 0,
38
+ "total_step": null
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d590f43b396e77a9ef27f0927c8e5781104946f40dd2f3560c67a36132912c
3
+ size 42530480
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "<pad>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26b7679a26444f46e753144a4e4db255b8f90aab2a122336f28be344e7199ef
3
+ size 4219
vocab.json ADDED
The diff for this file is too large to render. See raw diff