Hugging Face's logo

Mardiyyah
/
TAPT_data-V2_Bioformer-16L_LR-2e-05

Fill-Mask
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
TAPT_data-V2_Bioformer-16L_LR-2e-05
File size: 4,645 Bytes
954c21c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.972524881362915,
  "best_model_checkpoint": "./TAPT_data-V2_Bioformer-16L_LR-2e-05/checkpoint-2436",
  "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": 25.086040496826172,
      "learning_rate": 1.9150943396226415e-05,
      "loss": 2.2144,
      "step": 609
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.0326976776123047,
      "eval_runtime": 2.0957,
      "eval_samples_per_second": 928.082,
      "eval_steps_per_second": 58.214,
      "step": 609
    },
    {
      "epoch": 2.0,
      "grad_norm": 25.068096160888672,
      "learning_rate": 1.7023060796645702e-05,
      "loss": 1.9612,
      "step": 1218
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9747841358184814,
      "eval_runtime": 2.0904,
      "eval_samples_per_second": 930.443,
      "eval_steps_per_second": 58.362,
      "step": 1218
    },
    {
      "epoch": 3.0,
      "grad_norm": 24.59003448486328,
      "learning_rate": 1.4895178197064991e-05,
      "loss": 1.839,
      "step": 1827
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.05035138130188,
      "eval_runtime": 2.2132,
      "eval_samples_per_second": 878.802,
      "eval_steps_per_second": 55.123,
      "step": 1827
    },
    {
      "epoch": 4.0,
      "grad_norm": 24.1608829498291,
      "learning_rate": 1.2767295597484276e-05,
      "loss": 1.7475,
      "step": 2436
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.972524881362915,
      "eval_runtime": 2.1181,
      "eval_samples_per_second": 918.286,
      "eval_steps_per_second": 57.599,
      "step": 2436
    },
    {
      "epoch": 5.0,
      "grad_norm": 32.5782356262207,
      "learning_rate": 1.0639412997903564e-05,
      "loss": 1.6781,
      "step": 3045
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.0161244869232178,
      "eval_runtime": 2.1106,
      "eval_samples_per_second": 921.539,
      "eval_steps_per_second": 57.804,
      "step": 3045
    },
    {
      "epoch": 6.0,
      "grad_norm": 18.229835510253906,
      "learning_rate": 8.511530398322851e-06,
      "loss": 1.6427,
      "step": 3654
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.9868873357772827,
      "eval_runtime": 2.1141,
      "eval_samples_per_second": 920.02,
      "eval_steps_per_second": 57.708,
      "step": 3654
    },
    {
      "epoch": 7.0,
      "grad_norm": 19.829086303710938,
      "learning_rate": 6.383647798742138e-06,
      "loss": 1.6113,
      "step": 4263
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.0333664417266846,
      "eval_runtime": 2.1163,
      "eval_samples_per_second": 919.049,
      "eval_steps_per_second": 57.647,
      "step": 4263
    },
    {
      "epoch": 8.0,
      "grad_norm": 24.086036682128906,
      "learning_rate": 4.2557651991614255e-06,
      "loss": 1.5701,
      "step": 4872
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.9919387102127075,
      "eval_runtime": 2.1017,
      "eval_samples_per_second": 925.423,
      "eval_steps_per_second": 58.047,
      "step": 4872
    },
    {
      "epoch": 9.0,
      "grad_norm": 32.23151397705078,
      "learning_rate": 2.1278825995807127e-06,
      "loss": 1.5342,
      "step": 5481
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.9797741174697876,
      "eval_runtime": 2.1025,
      "eval_samples_per_second": 925.096,
      "eval_steps_per_second": 58.027,
      "step": 5481
    },
    {
      "epoch": 10.0,
      "grad_norm": 15.350183486938477,
      "learning_rate": 0.0,
      "loss": 1.5188,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.00888991355896,
      "eval_runtime": 2.1152,
      "eval_samples_per_second": 919.522,
      "eval_steps_per_second": 57.677,
      "step": 6090
    },
    {
      "epoch": 10.0,
      "step": 6090,
      "total_flos": 1536221652235776.0,
      "train_loss": 1.731730433872768,
      "train_runtime": 362.8983,
      "train_samples_per_second": 268.202,
      "train_steps_per_second": 16.782
    }
  ],
  "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
}