FINGU-AI commited on
Commit
e2b2dbf
1 Parent(s): 0a8c510

FinguAI-Chat-Mid-v1

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: Qwen/Qwen1.5-0.5B-Chat
4
+ tags:
5
+ - trl
6
+ - orpo
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Qwen-Orpo-v1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Qwen-Orpo-v1
17
+
18
+ This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.8005
21
+ - Rewards/chosen: -0.1607
22
+ - Rewards/rejected: -0.2097
23
+ - Rewards/accuracies: 0.8936
24
+ - Rewards/margins: 0.0490
25
+ - Logps/rejected: -2.0968
26
+ - Logps/chosen: -1.6067
27
+ - Logits/rejected: -1.4714
28
+ - Logits/chosen: -1.5480
29
+ - Nll Loss: 1.7529
30
+ - Log Odds Ratio: -0.4757
31
+ - Log Odds Chosen: 0.5760
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 8e-06
51
+ - train_batch_size: 2
52
+ - eval_batch_size: 2
53
+ - seed: 42
54
+ - gradient_accumulation_steps: 4
55
+ - total_train_batch_size: 8
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_steps: 10
59
+ - num_epochs: 1
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
64
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
65
+ | 1.9413 | 0.5001 | 1744 | 1.8005 | -0.1607 | -0.2097 | 0.8936 | 0.0490 | -2.0968 | -1.6067 | -1.4714 | -1.5480 | 1.7529 | -0.4757 | 0.5760 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.40.2
71
+ - Pytorch 2.2.0+cu121
72
+ - Datasets 2.19.1
73
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151644,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 151645,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": 32768,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151646
29
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151644,
3
+ "do_sample": true,
4
+ "eos_token_id": 151645,
5
+ "pad_token_id": 151645,
6
+ "repetition_penalty": 1.1,
7
+ "top_p": 0.8,
8
+ "transformers_version": "4.40.2"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881f2ced2c5c864f0e8bf6e99f3859761773decb637acdf14eac8b7896e54a58
3
+ size 927414184
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>"
21
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": "<|im_start|>",
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|im_end|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7b2e20a4346e6e5dee44f19c0dba75be19c2c8f5a67c19ca4105a6ad65a47c
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff