Hugging Face's logo

Aratako
/
Japanese-Novel-Reward-sarashina2.1-1b

Text Classification
Transformers
Safetensors
Japanese
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Aratako commited on
Commit
f3a0967
·
verified ·
1 Parent(s): f8b2b8b

Aratako/reward-test-sarashina

Browse files
Files changed (8) hide show
  1. README.md +135 -0
  2. config.json +38 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +171 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: sbintuitions/sarashina2.1-1b
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - pearsonr
9
+ - spearmanr
10
+ model-index:
11
+ - name: test-clf-sarashina
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # test-clf-sarashina
19
+
20
+ This model is a fine-tuned version of [sbintuitions/sarashina2.1-1b](https://huggingface.co/sbintuitions/sarashina2.1-1b) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.0627
23
+ - Mae: 0.7734
24
+ - R2: 0.4137
25
+ - Pearsonr: 0.6549
26
+ - Spearmanr: 0.6483
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 4
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 16
51
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine_with_min_lr
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 3
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Mae | R2 | Pearsonr | Spearmanr |
59
+ |:-------------:|:------:|:----:|:---------------:|:------:|:--------:|:--------:|:---------:|
60
+ | 33.4003 | 0.0440 | 30 | 41.9736 | 5.0785 | -19.5514 | 0.0060 | 0.0030 |
61
+ | 68.9791 | 0.0880 | 60 | 26.7601 | 3.9223 | -12.1025 | 0.0141 | 0.0121 |
62
+ | 7.0015 | 0.1320 | 90 | 18.4436 | 3.2333 | -8.0305 | 0.0940 | 0.1009 |
63
+ | 9.5128 | 0.1760 | 120 | 12.7227 | 2.6544 | -5.2294 | 0.1979 | 0.2112 |
64
+ | 8.1175 | 0.2200 | 150 | 8.9334 | 2.3069 | -3.3740 | 0.2409 | 0.2638 |
65
+ | 5.7487 | 0.2640 | 180 | 5.1040 | 1.6855 | -1.4991 | 0.3342 | 0.3609 |
66
+ | 4.2498 | 0.3080 | 210 | 6.3587 | 2.0904 | -2.1134 | 0.3393 | 0.3770 |
67
+ | 3.211 | 0.3520 | 240 | 2.5982 | 1.2158 | -0.2722 | 0.4370 | 0.4679 |
68
+ | 12.1813 | 0.3960 | 270 | 2.2745 | 1.0969 | -0.1137 | 0.4647 | 0.4956 |
69
+ | 2.4104 | 0.4400 | 300 | 2.1392 | 1.1266 | -0.0474 | 0.4725 | 0.5040 |
70
+ | 2.3 | 0.4840 | 330 | 2.0064 | 1.1148 | 0.0176 | 0.5250 | 0.5458 |
71
+ | 4.1499 | 0.5281 | 360 | 2.4043 | 1.1457 | -0.1772 | 0.5252 | 0.5581 |
72
+ | 1.6108 | 0.5721 | 390 | 1.6467 | 0.9633 | 0.1937 | 0.5714 | 0.5802 |
73
+ | 1.81 | 0.6161 | 420 | 1.5801 | 0.9609 | 0.2263 | 0.5978 | 0.6000 |
74
+ | 2.1724 | 0.6601 | 450 | 1.6209 | 0.9791 | 0.2063 | 0.5482 | 0.4986 |
75
+ | 2.0144 | 0.7041 | 480 | 1.7803 | 0.9999 | 0.1283 | 0.6017 | 0.5923 |
76
+ | 4.5503 | 0.7481 | 510 | 1.3499 | 0.8849 | 0.3391 | 0.5942 | 0.5621 |
77
+ | 4.3733 | 0.7921 | 540 | 3.5365 | 1.6830 | -0.7316 | 0.6105 | 0.5996 |
78
+ | 1.4027 | 0.8361 | 570 | 1.3477 | 0.9035 | 0.3401 | 0.6328 | 0.6183 |
79
+ | 2.429 | 0.8801 | 600 | 1.2318 | 0.8174 | 0.3969 | 0.6315 | 0.6103 |
80
+ | 0.9818 | 0.9241 | 630 | 1.8458 | 1.0223 | 0.0962 | 0.6372 | 0.6054 |
81
+ | 1.5284 | 0.9681 | 660 | 1.2547 | 0.8434 | 0.3856 | 0.6402 | 0.6157 |
82
+ | 1.5741 | 1.0117 | 690 | 1.3692 | 0.8539 | 0.3296 | 0.6279 | 0.6049 |
83
+ | 2.251 | 1.0557 | 720 | 1.7575 | 1.1040 | 0.1395 | 0.6439 | 0.6396 |
84
+ | 0.5807 | 1.0997 | 750 | 1.2974 | 0.8208 | 0.3648 | 0.6481 | 0.6275 |
85
+ | 1.8142 | 1.1437 | 780 | 1.5116 | 0.9475 | 0.2599 | 0.6530 | 0.6302 |
86
+ | 0.8249 | 1.1878 | 810 | 1.3097 | 0.8618 | 0.3588 | 0.6447 | 0.6145 |
87
+ | 1.4956 | 1.2318 | 840 | 2.2229 | 1.2553 | -0.0884 | 0.6392 | 0.6362 |
88
+ | 2.0046 | 1.2758 | 870 | 2.1057 | 1.2350 | -0.0310 | 0.6468 | 0.6260 |
89
+ | 1.3633 | 1.3198 | 900 | 1.2954 | 0.8883 | 0.3657 | 0.6533 | 0.6312 |
90
+ | 3.1957 | 1.3638 | 930 | 1.8696 | 1.1447 | 0.0846 | 0.6451 | 0.6154 |
91
+ | 0.793 | 1.4078 | 960 | 1.2303 | 0.8429 | 0.3976 | 0.6413 | 0.6052 |
92
+ | 2.2954 | 1.4518 | 990 | 1.3201 | 0.8624 | 0.3537 | 0.6571 | 0.6240 |
93
+ | 1.7479 | 1.4958 | 1020 | 1.2562 | 0.8144 | 0.3849 | 0.6399 | 0.6125 |
94
+ | 1.6785 | 1.5398 | 1050 | 1.7362 | 1.0790 | 0.1499 | 0.6492 | 0.6269 |
95
+ | 1.4885 | 1.5838 | 1080 | 2.3715 | 1.3151 | -0.1612 | 0.6480 | 0.6215 |
96
+ | 3.2869 | 1.6278 | 1110 | 1.5134 | 0.9746 | 0.2590 | 0.6498 | 0.6329 |
97
+ | 2.7832 | 1.6718 | 1140 | 1.2013 | 0.8259 | 0.4118 | 0.6593 | 0.6298 |
98
+ | 1.4801 | 1.7158 | 1170 | 1.5599 | 1.0123 | 0.2362 | 0.6573 | 0.6294 |
99
+ | 1.3236 | 1.7598 | 1200 | 1.9116 | 1.1420 | 0.0640 | 0.6457 | 0.6253 |
100
+ | 0.627 | 1.8038 | 1230 | 1.3976 | 0.9289 | 0.3157 | 0.6609 | 0.6430 |
101
+ | 1.0075 | 1.8478 | 1260 | 1.2831 | 0.8849 | 0.3718 | 0.6589 | 0.6491 |
102
+ | 1.2107 | 1.8918 | 1290 | 1.1647 | 0.7974 | 0.4298 | 0.6625 | 0.6453 |
103
+ | 0.8244 | 1.9358 | 1320 | 1.5123 | 0.9705 | 0.2595 | 0.6544 | 0.6296 |
104
+ | 1.1668 | 1.9798 | 1350 | 1.2957 | 0.8695 | 0.3656 | 0.6584 | 0.6356 |
105
+ | 1.0709 | 2.0235 | 1380 | 1.1780 | 0.8212 | 0.4232 | 0.6648 | 0.6458 |
106
+ | 0.8817 | 2.0675 | 1410 | 1.2616 | 0.8664 | 0.3823 | 0.6662 | 0.6506 |
107
+ | 1.3163 | 2.1115 | 1440 | 1.1625 | 0.7953 | 0.4308 | 0.6615 | 0.6458 |
108
+ | 1.3449 | 2.1555 | 1470 | 1.4815 | 0.9598 | 0.2746 | 0.6547 | 0.6425 |
109
+ | 1.1915 | 2.1995 | 1500 | 1.2140 | 0.8206 | 0.4056 | 0.6677 | 0.6518 |
110
+ | 0.7156 | 2.2435 | 1530 | 1.2342 | 0.8335 | 0.3957 | 0.6633 | 0.6468 |
111
+ | 0.8369 | 2.2875 | 1560 | 1.2145 | 0.8241 | 0.4053 | 0.6672 | 0.6503 |
112
+ | 1.2756 | 2.3315 | 1590 | 1.4552 | 0.9521 | 0.2875 | 0.6693 | 0.6523 |
113
+ | 1.2847 | 2.3755 | 1620 | 1.3366 | 0.8992 | 0.3456 | 0.6706 | 0.6490 |
114
+ | 0.9743 | 2.4195 | 1650 | 1.3276 | 0.8922 | 0.3500 | 0.6680 | 0.6471 |
115
+ | 1.2146 | 2.4635 | 1680 | 1.2658 | 0.8572 | 0.3802 | 0.6711 | 0.6509 |
116
+ | 1.0538 | 2.5075 | 1710 | 1.2478 | 0.8455 | 0.3890 | 0.6710 | 0.6516 |
117
+ | 0.7843 | 2.5515 | 1740 | 1.3749 | 0.9140 | 0.3268 | 0.6665 | 0.6479 |
118
+ | 1.9038 | 2.5955 | 1770 | 1.2816 | 0.8703 | 0.3725 | 0.6678 | 0.6488 |
119
+ | 2.0116 | 2.6395 | 1800 | 1.2002 | 0.8211 | 0.4124 | 0.6693 | 0.6500 |
120
+ | 1.5984 | 2.6835 | 1830 | 1.3324 | 0.8956 | 0.3476 | 0.6699 | 0.6503 |
121
+ | 0.7943 | 2.7275 | 1860 | 1.2132 | 0.8308 | 0.4060 | 0.6691 | 0.6477 |
122
+ | 0.544 | 2.7715 | 1890 | 1.3286 | 0.8932 | 0.3495 | 0.6699 | 0.6497 |
123
+ | 1.9314 | 2.8155 | 1920 | 1.3196 | 0.8859 | 0.3539 | 0.6688 | 0.6490 |
124
+ | 0.5876 | 2.8596 | 1950 | 1.2934 | 0.8711 | 0.3667 | 0.6688 | 0.6488 |
125
+ | 0.5792 | 2.9036 | 1980 | 1.2532 | 0.8488 | 0.3864 | 0.6697 | 0.6494 |
126
+ | 0.8113 | 2.9476 | 2010 | 1.2244 | 0.8336 | 0.4005 | 0.6705 | 0.6496 |
127
+ | 0.8149 | 2.9916 | 2040 | 1.2827 | 0.8662 | 0.3720 | 0.6698 | 0.6502 |
128
+
129
+
130
+ ### Framework versions
131
+
132
+ - Transformers 4.49.0
133
+ - Pytorch 2.6.0+cu124
134
+ - Datasets 3.3.2
135
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sbintuitions/sarashina2.1-1b",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 112,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1792,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 6272,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "max_position_embeddings": 8192,
22
+ "mlp_bias": false,
23
+ "model_type": "llama",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "num_key_value_heads": 8,
27
+ "pad_token_id": 3,
28
+ "pretraining_tp": 1,
29
+ "problem_type": "regression",
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "rope_theta": 500000,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.49.0",
36
+ "use_cache": true,
37
+ "vocab_size": 102400
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44123612045086f9a8a4afa63c8db6b86870b24b37164b00cef02f22c422bae8
3
+ size 2448105072
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_dummy_prefix_space": false,
4
+ "add_eos_token": false,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "0": {
8
+ "content": "<unk>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "1": {
16
+ "content": "<s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "2": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "3": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "4": {
40
+ "content": "<sep>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "5": {
48
+ "content": "<mask>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "6": {
56
+ "content": "<cls>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false,
61
+ "special": true
62
+ },
63
+ "7": {
64
+ "content": "<|system|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "8": {
72
+ "content": "<|assistant|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": false,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "9": {
80
+ "content": "<|user|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "10": {
88
+ "content": "<|available_tools|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "11": {
96
+ "content": "<|tool_calls|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false
102
+ },
103
+ "12": {
104
+ "content": "<|tool_results|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false,
109
+ "special": false
110
+ },
111
+ "13": {
112
+ "content": "<|code|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false,
117
+ "special": false
118
+ },
119
+ "14": {
120
+ "content": "<|file|>",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false,
125
+ "special": false
126
+ },
127
+ "102397": {
128
+ "content": "<|prefix|>",
129
+ "lstrip": false,
130
+ "normalized": false,
131
+ "rstrip": false,
132
+ "single_word": false,
133
+ "special": false
134
+ },
135
+ "102398": {
136
+ "content": "<|suffix|>",
137
+ "lstrip": false,
138
+ "normalized": false,
139
+ "rstrip": false,
140
+ "single_word": false,
141
+ "special": false
142
+ },
143
+ "102399": {
144
+ "content": "<|middle|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false,
149
+ "special": false
150
+ }
151
+ },
152
+ "bos_token": "<s>",
153
+ "clean_up_tokenization_spaces": false,
154
+ "cls_token": "<cls>",
155
+ "do_lower_case": false,
156
+ "eos_token": "</s>",
157
+ "extra_ids": 0,
158
+ "extra_special_tokens": {},
159
+ "keep_accents": true,
160
+ "legacy": false,
161
+ "mask_token": "<mask>",
162
+ "model_max_length": 8192,
163
+ "pad_token": "<pad>",
164
+ "padding_side": "left",
165
+ "sep_token": "<sep>",
166
+ "sp_model_kwargs": {},
167
+ "spaces_between_special_tokens": false,
168
+ "tokenizer_class": "LlamaTokenizer",
169
+ "unk_token": "<unk>",
170
+ "use_default_system_prompt": false
171
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2025e822a93d31255510dc63d53d95c7588c132c1cb5959db0016213b84edaf6
3
+ size 5368