argilla/gemma-2b-lora-distilabel-intel-orca-dpo-pairs
Browse files- .gitattributes +1 -0
- README.md +97 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: google/gemma-2b
|
9 |
+
model-index:
|
10 |
+
- name: gemma-2b-lora-distilabel-intel-orca-dpo-pairs
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# gemma-2b-lora-distilabel-intel-orca-dpo-pairs
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4752
|
22 |
+
- Rewards/chosen: -0.2074
|
23 |
+
- Rewards/rejected: -2.7558
|
24 |
+
- Rewards/accuracies: 0.8491
|
25 |
+
- Rewards/margins: 2.5483
|
26 |
+
- Logps/rejected: -309.6141
|
27 |
+
- Logps/chosen: -258.4032
|
28 |
+
- Logits/rejected: -29.9596
|
29 |
+
- Logits/chosen: -27.7808
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 1e-05
|
49 |
+
- train_batch_size: 2
|
50 |
+
- eval_batch_size: 2
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 4
|
53 |
+
- total_train_batch_size: 8
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- lr_scheduler_warmup_steps: 250
|
57 |
+
- num_epochs: 5
|
58 |
+
- mixed_precision_training: Native AMP
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
+
| 0.6326 | 0.19 | 250 | 0.5095 | -0.4198 | -1.0814 | 0.8348 | 0.6616 | -292.8703 | -260.5270 | -29.7690 | -27.6954 |
|
65 |
+
| 0.4753 | 0.39 | 500 | 0.4478 | -0.4809 | -1.9324 | 0.8507 | 1.4515 | -301.3807 | -261.1383 | -29.6874 | -27.5844 |
|
66 |
+
| 0.4466 | 0.58 | 750 | 0.4318 | -0.1824 | -1.8487 | 0.8503 | 1.6663 | -300.5433 | -258.1532 | -29.6629 | -27.5793 |
|
67 |
+
| 0.4287 | 0.78 | 1000 | 0.4400 | -0.1281 | -2.0702 | 0.8507 | 1.9420 | -302.7580 | -257.6101 | -30.0317 | -27.8922 |
|
68 |
+
| 0.4417 | 0.97 | 1250 | 0.4321 | 0.1125 | -1.7668 | 0.8495 | 1.8792 | -299.7242 | -255.2044 | -30.0155 | -27.875 |
|
69 |
+
| 0.4085 | 1.17 | 1500 | 0.4355 | -0.1108 | -2.1492 | 0.8511 | 2.0384 | -303.5482 | -257.4367 | -29.9166 | -27.7871 |
|
70 |
+
| 0.3946 | 1.36 | 1750 | 0.4488 | -0.1271 | -2.3911 | 0.8519 | 2.2640 | -305.9676 | -257.6003 | -29.8426 | -27.7085 |
|
71 |
+
| 0.3982 | 1.56 | 2000 | 0.4362 | -0.0692 | -2.2448 | 0.8515 | 2.1756 | -304.5043 | -257.0213 | -30.1425 | -27.9918 |
|
72 |
+
| 0.3943 | 1.75 | 2250 | 0.4453 | 0.0607 | -2.1390 | 0.8491 | 2.1997 | -303.4470 | -255.7220 | -30.2768 | -28.1039 |
|
73 |
+
| 0.3741 | 1.94 | 2500 | 0.4273 | 0.0867 | -2.0180 | 0.8507 | 2.1047 | -302.2360 | -255.4620 | -30.1318 | -27.9690 |
|
74 |
+
| 0.3321 | 2.14 | 2750 | 0.4565 | -0.0808 | -2.5300 | 0.8499 | 2.4492 | -307.3560 | -257.1368 | -30.0401 | -27.8877 |
|
75 |
+
| 0.3323 | 2.33 | 3000 | 0.4463 | 0.0323 | -2.2984 | 0.8503 | 2.3307 | -305.0405 | -256.0064 | -30.1648 | -27.9869 |
|
76 |
+
| 0.3495 | 2.53 | 3250 | 0.4299 | 0.1988 | -1.8994 | 0.8511 | 2.0982 | -301.0504 | -254.3410 | -30.2768 | -28.0945 |
|
77 |
+
| 0.3423 | 2.72 | 3500 | 0.4385 | 0.0237 | -2.1481 | 0.8499 | 2.1718 | -303.5371 | -256.0920 | -30.1685 | -27.9889 |
|
78 |
+
| 0.334 | 2.92 | 3750 | 0.4356 | 0.0467 | -2.1581 | 0.8499 | 2.2047 | -303.6373 | -255.8624 | -30.1857 | -27.9928 |
|
79 |
+
| 0.2933 | 3.11 | 4000 | 0.4540 | 0.0275 | -2.4119 | 0.8503 | 2.4394 | -306.1758 | -256.0542 | -30.1524 | -27.9559 |
|
80 |
+
| 0.3138 | 3.3 | 4250 | 0.4487 | -0.0797 | -2.4315 | 0.8499 | 2.3517 | -306.3710 | -257.1263 | -30.0450 | -27.8772 |
|
81 |
+
| 0.28 | 3.5 | 4500 | 0.4696 | -0.2282 | -2.8278 | 0.8519 | 2.5996 | -310.3340 | -258.6105 | -30.0594 | -27.8809 |
|
82 |
+
| 0.2796 | 3.69 | 4750 | 0.4545 | -0.0877 | -2.5133 | 0.8499 | 2.4256 | -307.1899 | -257.2065 | -30.0334 | -27.8598 |
|
83 |
+
| 0.2859 | 3.89 | 5000 | 0.4540 | -0.1038 | -2.5361 | 0.8507 | 2.4323 | -307.4171 | -257.3667 | -29.9932 | -27.8206 |
|
84 |
+
| 0.2785 | 4.08 | 5250 | 0.4619 | -0.1923 | -2.7125 | 0.8488 | 2.5202 | -309.1819 | -258.2524 | -29.9455 | -27.7723 |
|
85 |
+
| 0.2751 | 4.28 | 5500 | 0.4614 | -0.1893 | -2.7226 | 0.8488 | 2.5333 | -309.2824 | -258.2219 | -29.9548 | -27.7857 |
|
86 |
+
| 0.2522 | 4.47 | 5750 | 0.4606 | -0.1197 | -2.5970 | 0.8507 | 2.4773 | -308.0268 | -257.5265 | -30.0076 | -27.8263 |
|
87 |
+
| 0.2497 | 4.67 | 6000 | 0.4674 | -0.1855 | -2.7709 | 0.8503 | 2.5854 | -309.7651 | -258.1835 | -29.9580 | -27.7820 |
|
88 |
+
| 0.2634 | 4.86 | 6250 | 0.4752 | -0.2074 | -2.7558 | 0.8491 | 2.5483 | -309.6141 | -258.4032 | -29.9596 | -27.7808 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- PEFT 0.8.2
|
94 |
+
- Transformers 4.38.0
|
95 |
+
- Pytorch 2.1.0+cu121
|
96 |
+
- Datasets 2.17.0
|
97 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b",
|
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": 0.0,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"down_proj",
|
23 |
+
"o_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09b94e4802b26d7e6ecc27c4d9745b793869678c269d47633b6c55b0e195f531
|
3 |
+
size 39256456
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c03899f815d29b91d4c45c69e25dc7c2e93c9b90aee2637c9fe5a710da5f37b
|
3 |
+
size 4920
|