Hugging Face's logo

Mardiyyah
/
TAPT_data-V2_Bioformer-16L_LR-0.0001

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
TAPT_data-V2_Bioformer-16L_LR-0.0001
File size: 4,646 Bytes
197c8f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
{
  "best_metric": 2.2633635997772217,
  "best_model_checkpoint": "./TAPT_data-V2_Bioformer-16L_LR-0.0001/checkpoint-5481",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 6090,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 22.574710845947266,
      "learning_rate": 9.575471698113208e-05,
      "loss": 2.1948,
      "step": 609
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.278985023498535,
      "eval_runtime": 2.0974,
      "eval_samples_per_second": 927.339,
      "eval_steps_per_second": 58.167,
      "step": 609
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.863845825195312,
      "learning_rate": 8.511530398322851e-05,
      "loss": 1.9627,
      "step": 1218
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.301274299621582,
      "eval_runtime": 2.1066,
      "eval_samples_per_second": 923.304,
      "eval_steps_per_second": 57.914,
      "step": 1218
    },
    {
      "epoch": 3.0,
      "grad_norm": 31.829483032226562,
      "learning_rate": 7.447589098532494e-05,
      "loss": 1.7865,
      "step": 1827
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.3832926750183105,
      "eval_runtime": 2.1089,
      "eval_samples_per_second": 922.269,
      "eval_steps_per_second": 57.849,
      "step": 1827
    },
    {
      "epoch": 4.0,
      "grad_norm": 27.37325668334961,
      "learning_rate": 6.383647798742139e-05,
      "loss": 1.6375,
      "step": 2436
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.314645528793335,
      "eval_runtime": 2.1064,
      "eval_samples_per_second": 923.362,
      "eval_steps_per_second": 57.918,
      "step": 2436
    },
    {
      "epoch": 5.0,
      "grad_norm": 27.514528274536133,
      "learning_rate": 5.319706498951782e-05,
      "loss": 1.5212,
      "step": 3045
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.3126285076141357,
      "eval_runtime": 2.1144,
      "eval_samples_per_second": 919.883,
      "eval_steps_per_second": 57.7,
      "step": 3045
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.764179229736328,
      "learning_rate": 4.2557651991614255e-05,
      "loss": 1.4298,
      "step": 3654
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.300107002258301,
      "eval_runtime": 2.1035,
      "eval_samples_per_second": 924.65,
      "eval_steps_per_second": 57.999,
      "step": 3654
    },
    {
      "epoch": 7.0,
      "grad_norm": 18.094470977783203,
      "learning_rate": 3.1918238993710694e-05,
      "loss": 1.361,
      "step": 4263
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.3267035484313965,
      "eval_runtime": 2.0949,
      "eval_samples_per_second": 928.437,
      "eval_steps_per_second": 58.236,
      "step": 4263
    },
    {
      "epoch": 8.0,
      "grad_norm": 47.55793762207031,
      "learning_rate": 2.1278825995807127e-05,
      "loss": 1.2688,
      "step": 4872
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.3043582439422607,
      "eval_runtime": 2.1027,
      "eval_samples_per_second": 925.011,
      "eval_steps_per_second": 58.021,
      "step": 4872
    },
    {
      "epoch": 9.0,
      "grad_norm": 29.515283584594727,
      "learning_rate": 1.0639412997903564e-05,
      "loss": 1.2074,
      "step": 5481
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.2633635997772217,
      "eval_runtime": 2.0972,
      "eval_samples_per_second": 927.418,
      "eval_steps_per_second": 58.172,
      "step": 5481
    },
    {
      "epoch": 10.0,
      "grad_norm": 13.775968551635742,
      "learning_rate": 0.0,
      "loss": 1.1643,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.289745807647705,
      "eval_runtime": 2.1117,
      "eval_samples_per_second": 921.05,
      "eval_steps_per_second": 57.773,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "step": 6090,
      "total_flos": 1536221652235776.0,
      "train_loss": 1.5534028151939656,
      "train_runtime": 363.1065,
      "train_samples_per_second": 268.048,
      "train_steps_per_second": 16.772
    }
  ],
  "logging_steps": 500,
  "max_steps": 6090,
  "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": 1536221652235776.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}