File size: 2,499 Bytes
86d4c6b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
{
  "model_name": "xlm-roberta-large",
  "model_id": "M4_4.2_XLM_RoBERTa",
  "member": 4,
  "spec_compliance": {
    "seed": 42,
    "max_length": 128,
    "batch_size": 8,
    "gradient_accumulation_steps": 2,
    "effective_batch_size": 16,
    "learning_rate": 1e-05,
    "epochs_trained": 3,
    "total_epochs_limit": 5,
    "early_stopping_patience": 5,
    "primary_metric": "val_macro_f1",
    "data_augmentation": true,
    "target_minority_size": 0.05
  },
  "training_results": {
    "best_epoch": 3,
    "best_val_macro_f1": 0.6920319606014477,
    "best_val_macro_precision": 0.6935400158042497,
    "best_val_macro_recall": 0.6959520837420035,
    "best_val_weighted_f1": 0.7889787090902882,
    "best_val_accuracy": 0.7843488649940262,
    "training_loss": 0.531401620691845
  },
  "test_results": {
    "test_loss": 0.8419096413437215,
    "test_accuracy": 0.7831937799043063,
    "test_macro_precision": 0.7109259717505931,
    "test_macro_recall": 0.6740476446561174,
    "test_macro_f1": 0.682211638723438,
    "test_weighted_precision": 0.7917048623914406,
    "test_weighted_recall": 0.7831937799043063,
    "test_weighted_f1": 0.78430327538584,
    "per_class_f1": {
      "F": 0.8503589177250138,
      "R": 0.804436660828955,
      "N": 0.8322618351841029,
      "M": 0.6457399103139013,
      "S": 0.2782608695652174
    }
  },
  "data_augmentation": {
    "original_train_size": 15699,
    "augmented_train_size": 16156,
    "augmented_samples": 457,
    "target_minority_percentage": 5.0
  },
  "hardware": {
    "device": "cuda",
    "cuda_available": true,
    "python_version": "3.11.11",
    "platform": "Linux-6.8.0-87-generic-x86_64-with-glibc2.35",
    "cpu_count": 128,
    "ram_gb": 754.5698852539062,
    "gpu_device": "NVIDIA H100 NVL MIG 1g.24gb",
    "gpu_memory_gb": 23.219666944
  },
  "training_time": {
    "total_seconds": 4912.679862,
    "total_minutes": 81.8779977,
    "average_per_epoch": 982.5344182000001,
    "timestamp_start": "2025-12-25T13:51:24.634125",
    "timestamp_end": "2025-12-25T16:18:05.909736"
  },
  "library_versions": {
    "pytorch": "2.7.1+cu118",
    "transformers": "4.57.3",
    "numpy": "1.26.4",
    "pandas": "2.2.3",
    "scikit-learn": "1.6.1",
    "python": "3.11.11"
  },
  "data": {
    "train_samples_original": 15699,
    "train_samples_augmented": 16156,
    "val_samples": 3348,
    "test_samples": 3344,
    "num_classes": 5,
    "class_names": [
      "F",
      "R",
      "N",
      "M",
      "S"
    ]
  }
}