Hugging Face's logo

izzcw
/
cooking_sft_fail_new_mem

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
izzcw commited on
Commit
3fb0a28
·
verified ·
1 Parent(s): 48e379b

Model save

Browse files
Files changed (2) hide show
  1. README.md +139 -0
  2. generation_config.json +12 -0
README.md ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: cooking_sft_fail_new_mem
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
+ # cooking_sft_fail_new_mem
17
+
18
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2037
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - gradient_accumulation_steps: 16
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 8
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1.0
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.3821 | 0.0133 | 50 | 0.4735 |
58
+ | 0.302 | 0.0267 | 100 | 0.3178 |
59
+ | 0.2988 | 0.0400 | 150 | 0.3253 |
60
+ | 0.3054 | 0.0533 | 200 | 0.3250 |
61
+ | 0.2967 | 0.0666 | 250 | 0.3232 |
62
+ | 0.3137 | 0.0800 | 300 | 0.3207 |
63
+ | 0.3221 | 0.0933 | 350 | 0.3211 |
64
+ | 0.3188 | 0.1066 | 400 | 0.3204 |
65
+ | 0.308 | 0.1200 | 450 | 0.3149 |
66
+ | 0.3123 | 0.1333 | 500 | 0.3106 |
67
+ | 0.3138 | 0.1466 | 550 | 0.3050 |
68
+ | 0.3032 | 0.1600 | 600 | 0.3046 |
69
+ | 0.2827 | 0.1733 | 650 | 0.3017 |
70
+ | 0.2953 | 0.1866 | 700 | 0.2970 |
71
+ | 0.2854 | 0.1999 | 750 | 0.2924 |
72
+ | 0.2872 | 0.2133 | 800 | 0.2896 |
73
+ | 0.2866 | 0.2266 | 850 | 0.2836 |
74
+ | 0.2925 | 0.2399 | 900 | 0.2794 |
75
+ | 0.2843 | 0.2533 | 950 | 0.2823 |
76
+ | 0.292 | 0.2666 | 1000 | 0.2789 |
77
+ | 0.2775 | 0.2799 | 1050 | 0.2763 |
78
+ | 0.2652 | 0.2933 | 1100 | 0.2717 |
79
+ | 0.27 | 0.3066 | 1150 | 0.2712 |
80
+ | 0.277 | 0.3199 | 1200 | 0.2749 |
81
+ | 0.2681 | 0.3332 | 1250 | 0.2709 |
82
+ | 0.2699 | 0.3466 | 1300 | 0.2718 |
83
+ | 0.2682 | 0.3599 | 1350 | 0.2676 |
84
+ | 0.2668 | 0.3732 | 1400 | 0.2662 |
85
+ | 0.2615 | 0.3866 | 1450 | 0.2689 |
86
+ | 0.2501 | 0.3999 | 1500 | 0.2583 |
87
+ | 0.2545 | 0.4132 | 1550 | 0.2568 |
88
+ | 0.2618 | 0.4265 | 1600 | 0.2523 |
89
+ | 0.2615 | 0.4399 | 1650 | 0.2550 |
90
+ | 0.2512 | 0.4532 | 1700 | 0.2488 |
91
+ | 0.245 | 0.4665 | 1750 | 0.2504 |
92
+ | 0.2503 | 0.4799 | 1800 | 0.2481 |
93
+ | 0.2402 | 0.4932 | 1850 | 0.2450 |
94
+ | 0.2346 | 0.5065 | 1900 | 0.2440 |
95
+ | 0.2413 | 0.5199 | 1950 | 0.2425 |
96
+ | 0.24 | 0.5332 | 2000 | 0.2383 |
97
+ | 0.2398 | 0.5465 | 2050 | 0.2408 |
98
+ | 0.2473 | 0.5598 | 2100 | 0.2384 |
99
+ | 0.2423 | 0.5732 | 2150 | 0.2348 |
100
+ | 0.2294 | 0.5865 | 2200 | 0.2311 |
101
+ | 0.2403 | 0.5998 | 2250 | 0.2323 |
102
+ | 0.2319 | 0.6132 | 2300 | 0.2297 |
103
+ | 0.222 | 0.6265 | 2350 | 0.2288 |
104
+ | 0.2193 | 0.6398 | 2400 | 0.2303 |
105
+ | 0.2252 | 0.6531 | 2450 | 0.2247 |
106
+ | 0.2304 | 0.6665 | 2500 | 0.2211 |
107
+ | 0.2139 | 0.6798 | 2550 | 0.2199 |
108
+ | 0.2186 | 0.6931 | 2600 | 0.2192 |
109
+ | 0.2156 | 0.7065 | 2650 | 0.2183 |
110
+ | 0.2187 | 0.7198 | 2700 | 0.2159 |
111
+ | 0.222 | 0.7331 | 2750 | 0.2174 |
112
+ | 0.2162 | 0.7465 | 2800 | 0.2153 |
113
+ | 0.2253 | 0.7598 | 2850 | 0.2132 |
114
+ | 0.2066 | 0.7731 | 2900 | 0.2134 |
115
+ | 0.2113 | 0.7864 | 2950 | 0.2107 |
116
+ | 0.2107 | 0.7998 | 3000 | 0.2085 |
117
+ | 0.2055 | 0.8131 | 3050 | 0.2097 |
118
+ | 0.2045 | 0.8264 | 3100 | 0.2075 |
119
+ | 0.2172 | 0.8398 | 3150 | 0.2062 |
120
+ | 0.2138 | 0.8531 | 3200 | 0.2075 |
121
+ | 0.194 | 0.8664 | 3250 | 0.2051 |
122
+ | 0.2133 | 0.8798 | 3300 | 0.2051 |
123
+ | 0.2025 | 0.8931 | 3350 | 0.2047 |
124
+ | 0.2088 | 0.9064 | 3400 | 0.2050 |
125
+ | 0.204 | 0.9197 | 3450 | 0.2044 |
126
+ | 0.2059 | 0.9331 | 3500 | 0.2039 |
127
+ | 0.2103 | 0.9464 | 3550 | 0.2039 |
128
+ | 0.2102 | 0.9597 | 3600 | 0.2039 |
129
+ | 0.2051 | 0.9731 | 3650 | 0.2038 |
130
+ | 0.2017 | 0.9864 | 3700 | 0.2037 |
131
+ | 0.2088 | 0.9997 | 3750 | 0.2037 |
132
+
133
+
134
+ ### Framework versions
135
+
136
+ - Transformers 4.49.0
137
+ - Pytorch 2.5.1+cu124
138
+ - Datasets 3.2.0
139
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.49.0"
12
+ }