Hugging Face's logo

HiAmNear
/
cafebert-ViISA

Safetensors
xlm-roberta
Model card Files
xet
Community
cafebert-ViISA
File size: 3,909 Bytes
bd5c773
b6f53f4
 
4345e72
bd5c773
4345e72
bd5c773
 
 
 
 
 
 
 
 
 
 
 
0840c33
 
 
 
 
 
 
 
 
cc1242f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b6f53f4
 
 
 
 
 
 
 
 
88a185c
 
 
 
 
 
 
 
 
6c2ba5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f35d711
 
 
 
 
 
 
 
 
346dc2e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e86ff05
 
 
 
 
 
 
 
 
4345e72
 
 
 
 
 
 
 
 
bd5c773
 
 
 
 
 
 
 
 
 
 
 
 
 
4345e72
bd5c773
 
 
 
4345e72
bd5c773
 
 
 
 
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
 
{
  "best_metric": 0.7774524158125915,
  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1990,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7635431918008785,
      "eval_loss": 0.5437253713607788,
      "eval_runtime": 119.9317,
      "eval_samples_per_second": 11.39,
      "eval_steps_per_second": 5.695,
      "step": 199
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.773792093704246,
      "eval_loss": 0.5396685004234314,
      "eval_runtime": 124.413,
      "eval_samples_per_second": 10.98,
      "eval_steps_per_second": 5.49,
      "step": 398
    },
    {
      "epoch": 2.5125628140703515,
      "grad_norm": 592.5914916992188,
      "learning_rate": 7.487437185929649e-06,
      "loss": 0.5014,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7730600292825769,
      "eval_loss": 0.5995632410049438,
      "eval_runtime": 59.0331,
      "eval_samples_per_second": 23.14,
      "eval_steps_per_second": 11.57,
      "step": 597
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7774524158125915,
      "eval_loss": 0.7029575109481812,
      "eval_runtime": 123.6878,
      "eval_samples_per_second": 11.044,
      "eval_steps_per_second": 5.522,
      "step": 796
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7693997071742313,
      "eval_loss": 0.8647988438606262,
      "eval_runtime": 112.0996,
      "eval_samples_per_second": 12.186,
      "eval_steps_per_second": 6.093,
      "step": 995
    },
    {
      "epoch": 5.025125628140704,
      "grad_norm": 2496.794189453125,
      "learning_rate": 4.974874371859297e-06,
      "loss": 0.2005,
      "step": 1000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7642752562225475,
      "eval_loss": 1.0910539627075195,
      "eval_runtime": 111.8459,
      "eval_samples_per_second": 12.213,
      "eval_steps_per_second": 6.107,
      "step": 1194
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7723279648609077,
      "eval_loss": 1.2653732299804688,
      "eval_runtime": 110.9037,
      "eval_samples_per_second": 12.317,
      "eval_steps_per_second": 6.158,
      "step": 1393
    },
    {
      "epoch": 7.5376884422110555,
      "grad_norm": 1611.986083984375,
      "learning_rate": 2.462311557788945e-06,
      "loss": 0.0881,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.773792093704246,
      "eval_loss": 1.5597944259643555,
      "eval_runtime": 115.9058,
      "eval_samples_per_second": 11.785,
      "eval_steps_per_second": 5.893,
      "step": 1592
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7693997071742313,
      "eval_loss": 1.7513818740844727,
      "eval_runtime": 113.5331,
      "eval_samples_per_second": 12.032,
      "eval_steps_per_second": 6.016,
      "step": 1791
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7679355783308931,
      "eval_loss": 1.8216043710708618,
      "eval_runtime": 170.3389,
      "eval_samples_per_second": 8.019,
      "eval_steps_per_second": 4.01,
      "step": 1990
    }
  ],
  "logging_steps": 500,
  "max_steps": 1990,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.95568855112096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}