Billyyy commited on
Commit
ff085b6
·
verified ·
1 Parent(s): cff3dac

Model save

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/nllb-200-distilled-1.3B
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: mon_nllb_3B_r32
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # mon_nllb_3B_r32
16
+
17
+ This model is a fine-tuned version of [facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 7.2132
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 40
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 160
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: cosine
46
+ - lr_scheduler_warmup_steps: 500
47
+ - num_epochs: 2
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:-----:|:---------------:|
54
+ | 7.4511 | 0.0761 | 500 | 7.2785 |
55
+ | 7.3373 | 0.1522 | 1000 | 7.2305 |
56
+ | 7.2568 | 0.2283 | 1500 | 7.2138 |
57
+ | 7.2365 | 0.3044 | 2000 | 7.2126 |
58
+ | 7.2619 | 0.3805 | 2500 | 7.2130 |
59
+ | 7.2272 | 0.4567 | 3000 | 7.2117 |
60
+ | 7.2336 | 0.5328 | 3500 | 7.2137 |
61
+ | 7.2263 | 0.6089 | 4000 | 7.2139 |
62
+ | 7.2321 | 0.6850 | 4500 | 7.2129 |
63
+ | 7.2257 | 0.7611 | 5000 | 7.2124 |
64
+ | 7.2248 | 0.8372 | 5500 | 7.2121 |
65
+ | 7.2289 | 0.9133 | 6000 | 7.2121 |
66
+ | 7.2144 | 0.9894 | 6500 | 7.2131 |
67
+ | 7.2155 | 1.0656 | 7000 | 7.2133 |
68
+ | 7.215 | 1.1417 | 7500 | 7.2130 |
69
+ | 7.2146 | 1.2178 | 8000 | 7.2122 |
70
+ | 7.1995 | 1.2939 | 8500 | 7.2126 |
71
+ | 7.2025 | 1.3700 | 9000 | 7.2136 |
72
+ | 7.2302 | 1.4462 | 9500 | 7.2128 |
73
+ | 7.2078 | 1.5223 | 10000 | 7.2133 |
74
+ | 7.2063 | 1.5984 | 10500 | 7.2133 |
75
+ | 7.216 | 1.6745 | 11000 | 7.2128 |
76
+ | 7.1949 | 1.7506 | 11500 | 7.2132 |
77
+ | 7.2213 | 1.8267 | 12000 | 7.2131 |
78
+ | 7.2236 | 1.9028 | 12500 | 7.2132 |
79
+ | 7.2244 | 1.9789 | 13000 | 7.2132 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - PEFT 0.14.0
85
+ - Transformers 4.49.0
86
+ - Pytorch 2.6.0+cu124
87
+ - Datasets 3.3.2
88
+ - Tokenizers 0.21.0