Hugging Face's logo

Heejindo
/
rationale_model_e10

Text Generation
Transformers
Safetensors
llama
trl
sft
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
Heejindo commited on
Commit
8ce26f1
·
verified ·
1 Parent(s): 00f41a8

training_output/rationale_model_e10/

Browse files
Files changed (3) hide show
  1. README.md +121 -0
  2. generation_config.json +9 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-1B
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: rationale_model_e10
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
+ # rationale_model_e10
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.9041
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | 2.0662 | 0.0477 | 500 | 1.9416 |
53
+ | 1.8844 | 0.0954 | 1000 | 1.9136 |
54
+ | 1.7819 | 0.1431 | 1500 | 1.9041 |
55
+ | 1.6587 | 0.1908 | 2000 | 1.9142 |
56
+ | 1.5711 | 0.2385 | 2500 | 1.9290 |
57
+ | 1.4686 | 0.2862 | 3000 | 1.9362 |
58
+ | 1.3787 | 0.3338 | 3500 | 2.0431 |
59
+ | 1.2464 | 0.3815 | 4000 | 2.0219 |
60
+ | 1.1407 | 0.4292 | 4500 | 2.0494 |
61
+ | 1.0591 | 0.4769 | 5000 | 2.0871 |
62
+ | 0.9351 | 0.5246 | 5500 | 2.1374 |
63
+ | 0.8295 | 0.5723 | 6000 | 2.1954 |
64
+ | 0.7724 | 0.6200 | 6500 | 2.2344 |
65
+ | 0.6506 | 0.6677 | 7000 | 2.2971 |
66
+ | 0.6109 | 0.7154 | 7500 | 2.3390 |
67
+ | 0.5302 | 0.7631 | 8000 | 2.4308 |
68
+ | 0.4378 | 0.8108 | 8500 | 2.5308 |
69
+ | 0.383 | 0.8585 | 9000 | 2.6438 |
70
+ | 0.3419 | 0.9061 | 9500 | 2.6942 |
71
+ | 0.2983 | 0.9538 | 10000 | 2.7862 |
72
+ | 0.2568 | 1.0015 | 10500 | 2.9069 |
73
+ | 0.186 | 1.0492 | 11000 | 2.8744 |
74
+ | 0.1799 | 1.0969 | 11500 | 2.9436 |
75
+ | 0.1831 | 1.1446 | 12000 | 2.9253 |
76
+ | 0.1751 | 1.1923 | 12500 | 3.0272 |
77
+ | 0.1652 | 1.2400 | 13000 | 3.0354 |
78
+ | 0.1644 | 1.2877 | 13500 | 3.0101 |
79
+ | 0.1569 | 1.3354 | 14000 | 3.0530 |
80
+ | 0.1554 | 1.3831 | 14500 | 3.0933 |
81
+ | 0.1498 | 1.4308 | 15000 | 3.1092 |
82
+ | 0.1424 | 1.4784 | 15500 | 3.1997 |
83
+ | 0.1417 | 1.5261 | 16000 | 3.1469 |
84
+ | 0.1385 | 1.5738 | 16500 | 3.2502 |
85
+ | 0.1355 | 1.6215 | 17000 | 3.2343 |
86
+ | 0.1323 | 1.6692 | 17500 | 3.2179 |
87
+ | 0.1279 | 1.7169 | 18000 | 3.2491 |
88
+ | 0.1268 | 1.7646 | 18500 | 3.2739 |
89
+ | 0.1206 | 1.8123 | 19000 | 3.3483 |
90
+ | 0.1211 | 1.8600 | 19500 | 3.3606 |
91
+ | 0.118 | 1.9077 | 20000 | 3.3723 |
92
+ | 0.1162 | 1.9554 | 20500 | 3.3527 |
93
+ | 0.1124 | 2.0031 | 21000 | 3.5134 |
94
+ | 0.0983 | 2.0507 | 21500 | 3.4884 |
95
+ | 0.1002 | 2.0984 | 22000 | 3.5197 |
96
+ | 0.1018 | 2.1461 | 22500 | 3.5413 |
97
+ | 0.0981 | 2.1938 | 23000 | 3.5697 |
98
+ | 0.097 | 2.2415 | 23500 | 3.5927 |
99
+ | 0.0949 | 2.2892 | 24000 | 3.5983 |
100
+ | 0.0971 | 2.3369 | 24500 | 3.6530 |
101
+ | 0.0952 | 2.3846 | 25000 | 3.6665 |
102
+ | 0.0973 | 2.4323 | 25500 | 3.6585 |
103
+ | 0.0915 | 2.4800 | 26000 | 3.7384 |
104
+ | 0.0918 | 2.5277 | 26500 | 3.7284 |
105
+ | 0.0918 | 2.5754 | 27000 | 3.7835 |
106
+ | 0.0885 | 2.6230 | 27500 | 3.8170 |
107
+ | 0.0891 | 2.6707 | 28000 | 3.8412 |
108
+ | 0.0901 | 2.7184 | 28500 | 3.8526 |
109
+ | 0.0878 | 2.7661 | 29000 | 3.8645 |
110
+ | 0.0864 | 2.8138 | 29500 | 3.9049 |
111
+ | 0.0866 | 2.8615 | 30000 | 3.9255 |
112
+ | 0.0853 | 2.9092 | 30500 | 3.9378 |
113
+ | 0.0858 | 2.9569 | 31000 | 3.9455 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.46.3
119
+ - Pytorch 2.3.0
120
+ - Datasets 2.14.4
121
+ - Tokenizers 0.20.3
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.3"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6952ba71d8fce5446bcbb07dad889b676145ac1c276b4bd72ffca437d086ad
3
  size 4943274328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b137a939c815648af42957fa26bf0e6b262443799d63630fbaf317133a443745
3
  size 4943274328