Hugging Face's logo

Elkelouizajo
/
bert_mnli_augmented

Safetensors
bert
Generated from Trainer
Model card Files Community
bert_mnli_augmented
File size: 2,406 Bytes 
bc980bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9985007496251876,
  "eval_steps": 500,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 1.5337328910827637,
      "learning_rate": 1.900049975012494e-05,
      "loss": 0.4281,
      "step": 500
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.992353081703186,
      "learning_rate": 1.8000999500249876e-05,
      "loss": 0.2656,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.4741365909576416,
      "learning_rate": 1.7001499250374815e-05,
      "loss": 0.263,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5607998967170715,
      "learning_rate": 1.600199900049975e-05,
      "loss": 0.2228,
      "step": 2000
    },
    {
      "epoch": 1.25,
      "grad_norm": 56.73757553100586,
      "learning_rate": 1.500249875062469e-05,
      "loss": 0.1552,
      "step": 2500
    },
    {
      "epoch": 1.5,
      "grad_norm": 10.09034252166748,
      "learning_rate": 1.4002998500749626e-05,
      "loss": 0.1395,
      "step": 3000
    },
    {
      "epoch": 1.75,
      "grad_norm": 49.66099166870117,
      "learning_rate": 1.3003498250874565e-05,
      "loss": 0.1396,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.33147394657135,
      "learning_rate": 1.2003998000999502e-05,
      "loss": 0.1468,
      "step": 4000
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.00538645638152957,
      "learning_rate": 1.100449775112444e-05,
      "loss": 0.0595,
      "step": 4500
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.2792365550994873,
      "learning_rate": 1.0004997501249377e-05,
      "loss": 0.0529,
      "step": 5000
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.09408382326364517,
      "learning_rate": 9.005497251374314e-06,
      "loss": 0.0578,
      "step": 5500
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.005479688756167889,
      "learning_rate": 8.005997001499251e-06,
      "loss": 0.0523,
      "step": 6000
    }
  ],
  "logging_steps": 500,
  "max_steps": 10005,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.1179914600164352e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}