Hugging Face's logo

Azrail
/
smallm_140_rope

Text Generation
Transformers
Safetensors
smallm
Generated from Trainer
Model card Files
xet
Community
Azrail commited on
Commit
64c1cb3
·
verified ·
1 Parent(s): 7117390

Model save

Browse files
Files changed (6) hide show
  1. README.md +119 -0
  2. generation_config.json +7 -0
  3. special_tokens_map.json +23 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +115 -0
  6. trainer_state.json +0 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: smallm_140_rope
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # smallm_140_rope
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 2.8849
18
+ - Num Input Tokens Seen: 7864320000
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0006
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 256
43
+ - optimizer: Use OptimizerNames.ADAMW_APEX_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 600
46
+ - training_steps: 30000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
51
+ |:-------------:|:------:|:-----:|:---------------:|:-----------------:|
52
+ | 22.7795 | 0.0034 | 500 | 5.5598 | 131072000 |
53
+ | 17.4367 | 0.0067 | 1000 | 4.2485 | 262144000 |
54
+ | 15.7688 | 0.0101 | 1500 | 3.8666 | 393216000 |
55
+ | 14.9894 | 0.0135 | 2000 | 3.6752 | 524288000 |
56
+ | 14.5031 | 0.0168 | 2500 | 3.5482 | 655360000 |
57
+ | 14.2405 | 0.0202 | 3000 | 3.4691 | 786432000 |
58
+ | 13.9742 | 0.0235 | 3500 | 3.4102 | 917504000 |
59
+ | 13.7434 | 0.0269 | 4000 | 3.3646 | 1048576000 |
60
+ | 13.6039 | 0.0303 | 4500 | 3.3241 | 1179648000 |
61
+ | 13.4891 | 0.0336 | 5000 | 3.2917 | 1310720000 |
62
+ | 13.3718 | 0.0370 | 5500 | 3.2622 | 1441792000 |
63
+ | 13.3443 | 0.0404 | 6000 | 3.2371 | 1572864000 |
64
+ | 13.1945 | 0.0437 | 6500 | 3.2159 | 1703936000 |
65
+ | 13.0997 | 0.0471 | 7000 | 3.1944 | 1835008000 |
66
+ | 13.1213 | 0.0504 | 7500 | 3.1756 | 1966080000 |
67
+ | 12.977 | 0.0538 | 8000 | 3.1572 | 2097152000 |
68
+ | 12.8892 | 0.0572 | 8500 | 3.1434 | 2228224000 |
69
+ | 12.8258 | 0.0605 | 9000 | 3.1286 | 2359296000 |
70
+ | 12.8312 | 0.0639 | 9500 | 3.1131 | 2490368000 |
71
+ | 12.7303 | 0.0673 | 10000 | 3.1027 | 2621440000 |
72
+ | 12.6896 | 0.0706 | 10500 | 3.0884 | 2752512000 |
73
+ | 12.6273 | 0.0740 | 11000 | 3.0768 | 2883584000 |
74
+ | 12.6166 | 0.0774 | 11500 | 3.0653 | 3014656000 |
75
+ | 12.57 | 0.0807 | 12000 | 3.0549 | 3145728000 |
76
+ | 12.5742 | 0.0841 | 12500 | 3.0441 | 3276800000 |
77
+ | 12.4583 | 0.0874 | 13000 | 3.0347 | 3407872000 |
78
+ | 12.4483 | 0.0908 | 13500 | 3.0267 | 3538944000 |
79
+ | 12.3991 | 0.0942 | 14000 | 3.0163 | 3670016000 |
80
+ | 12.4215 | 0.0975 | 14500 | 3.0072 | 3801088000 |
81
+ | 12.367 | 0.1009 | 15000 | 2.9978 | 3932160000 |
82
+ | 12.3038 | 0.1043 | 15500 | 2.9913 | 4063232000 |
83
+ | 12.2584 | 0.1076 | 16000 | 2.9842 | 4194304000 |
84
+ | 12.2762 | 0.1110 | 16500 | 2.9755 | 4325376000 |
85
+ | 12.2252 | 0.1144 | 17000 | 2.9685 | 4456448000 |
86
+ | 12.2031 | 0.1177 | 17500 | 2.9616 | 4587520000 |
87
+ | 12.1477 | 0.1211 | 18000 | 2.9548 | 4718592000 |
88
+ | 12.1604 | 0.1244 | 18500 | 2.9489 | 4849664000 |
89
+ | 12.0931 | 0.1278 | 19000 | 2.9431 | 4980736000 |
90
+ | 12.0719 | 0.1312 | 19500 | 2.9375 | 5111808000 |
91
+ | 12.0672 | 0.1345 | 20000 | 2.9316 | 5242880000 |
92
+ | 12.0664 | 0.1379 | 20500 | 2.9268 | 5373952000 |
93
+ | 12.029 | 0.1413 | 21000 | 2.9219 | 5505024000 |
94
+ | 12.0514 | 0.1446 | 21500 | 2.9168 | 5636096000 |
95
+ | 12.0284 | 0.1480 | 22000 | 2.9136 | 5767168000 |
96
+ | 11.9863 | 0.1513 | 22500 | 2.9087 | 5898240000 |
97
+ | 11.9845 | 0.1547 | 23000 | 2.9054 | 6029312000 |
98
+ | 11.9285 | 0.1581 | 23500 | 2.9019 | 6160384000 |
99
+ | 11.9322 | 0.1614 | 24000 | 2.8988 | 6291456000 |
100
+ | 11.9627 | 0.1648 | 24500 | 2.8965 | 6422528000 |
101
+ | 11.9144 | 0.1682 | 25000 | 2.8939 | 6553600000 |
102
+ | 11.926 | 0.1715 | 25500 | 2.8921 | 6684672000 |
103
+ | 11.9298 | 0.1749 | 26000 | 2.8901 | 6815744000 |
104
+ | 11.9117 | 0.1783 | 26500 | 2.8888 | 6946816000 |
105
+ | 11.945 | 0.1816 | 27000 | 2.8873 | 7077888000 |
106
+ | 11.9267 | 0.1850 | 27500 | 2.8867 | 7208960000 |
107
+ | 11.9013 | 0.1883 | 28000 | 2.8857 | 7340032000 |
108
+ | 11.9102 | 0.1917 | 28500 | 2.8853 | 7471104000 |
109
+ | 11.9402 | 0.1951 | 29000 | 2.8851 | 7602176000 |
110
+ | 11.9125 | 0.1984 | 29500 | 2.8849 | 7733248000 |
111
+ | 11.9242 | 0.2018 | 30000 | 2.8849 | 7864320000 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.50.3
117
+ - Pytorch 2.6.0+cu126
118
+ - Datasets 3.5.0
119
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.50.3"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|beginoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|beginoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|reserved_token_1|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|reserved_token_2|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|reserved_token_3|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<|reserved_token_4|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<|reserved_token_5|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<|reserved_token_6|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<|reserved_token_7|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<|reserved_token_8|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<|reserved_token_9|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<|reserved_token_10|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<|reserved_token_11|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ }
107
+ },
108
+ "bos_token": "<|beginoftext|>",
109
+ "clean_up_tokenization_spaces": false,
110
+ "eos_token": "<|endoftext|>",
111
+ "extra_special_tokens": {},
112
+ "model_max_length": 1000000000000000019884624838656,
113
+ "pad_token": "<|endoftext|>",
114
+ "tokenizer_class": "PreTrainedTokenizer"
115
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff