Hugging Face's logo

Hartunka
/
tiny_bert_rand_100_v1_mnli

TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
tiny_bert_rand_100_v1_mnli
File size: 4,718 Bytes
d433369
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8466889262199402,
  "best_model_checkpoint": "tiny_bert_rand_100_v1_mnli/checkpoint-7670",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 15340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0576350688934326,
      "learning_rate": 4.9e-05,
      "loss": 0.9939,
      "step": 1534
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5477330616403464,
      "eval_loss": 0.9340195059776306,
      "eval_runtime": 3.4588,
      "eval_samples_per_second": 2837.716,
      "eval_steps_per_second": 11.276,
      "step": 1534
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.441909909248352,
      "learning_rate": 4.8e-05,
      "loss": 0.9106,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5792154865002547,
      "eval_loss": 0.8887940645217896,
      "eval_runtime": 3.3917,
      "eval_samples_per_second": 2893.827,
      "eval_steps_per_second": 11.499,
      "step": 3068
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4226245880126953,
      "learning_rate": 4.7e-05,
      "loss": 0.8576,
      "step": 4602
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6055017829852267,
      "eval_loss": 0.8593698143959045,
      "eval_runtime": 3.44,
      "eval_samples_per_second": 2853.221,
      "eval_steps_per_second": 11.337,
      "step": 4602
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.7679719924926758,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.8116,
      "step": 6136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6134488028527764,
      "eval_loss": 0.8515642881393433,
      "eval_runtime": 3.3552,
      "eval_samples_per_second": 2925.297,
      "eval_steps_per_second": 11.624,
      "step": 6136
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6639595031738281,
      "learning_rate": 4.5e-05,
      "loss": 0.7679,
      "step": 7670
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6203769740193581,
      "eval_loss": 0.8466889262199402,
      "eval_runtime": 3.3919,
      "eval_samples_per_second": 2893.668,
      "eval_steps_per_second": 11.498,
      "step": 7670
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.073934555053711,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7263,
      "step": 9204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6275089149261335,
      "eval_loss": 0.85952228307724,
      "eval_runtime": 3.4134,
      "eval_samples_per_second": 2875.409,
      "eval_steps_per_second": 11.425,
      "step": 9204
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.292513847351074,
      "learning_rate": 4.3e-05,
      "loss": 0.6861,
      "step": 10738
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6258787570045848,
      "eval_loss": 0.8680656552314758,
      "eval_runtime": 3.3969,
      "eval_samples_per_second": 2889.423,
      "eval_steps_per_second": 11.481,
      "step": 10738
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.142648935317993,
      "learning_rate": 4.2e-05,
      "loss": 0.6464,
      "step": 12272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6231278655119715,
      "eval_loss": 0.905820369720459,
      "eval_runtime": 3.474,
      "eval_samples_per_second": 2825.266,
      "eval_steps_per_second": 11.226,
      "step": 12272
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.892969846725464,
      "learning_rate": 4.1e-05,
      "loss": 0.6076,
      "step": 13806
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6246561385634233,
      "eval_loss": 0.9309349060058594,
      "eval_runtime": 3.4173,
      "eval_samples_per_second": 2872.186,
      "eval_steps_per_second": 11.413,
      "step": 13806
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.507983684539795,
      "learning_rate": 4e-05,
      "loss": 0.5699,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6231278655119715,
      "eval_loss": 0.993652880191803,
      "eval_runtime": 3.3978,
      "eval_samples_per_second": 2888.612,
      "eval_steps_per_second": 11.478,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "step": 15340,
      "total_flos": 1.029836100834816e+17,
      "train_loss": 0.7577745300850004,
      "train_runtime": 2592.0889,
      "train_samples_per_second": 7575.01,
      "train_steps_per_second": 29.59
    }
  ],
  "logging_steps": 1,
  "max_steps": 76700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 1.029836100834816e+17,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}