Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0581

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Model-J__MAE__model_idx_0581
File size: 4,492 Bytes 
ee0b3b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8962666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0581/checkpoints/checkpoint-2997",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 2997,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 4.446112779446113e-05,
      "loss": 1.7458,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8146666666666667,
      "eval_loss": 0.742637038230896,
      "eval_runtime": 10.8286,
      "eval_samples_per_second": 346.304,
      "eval_steps_per_second": 5.449,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.098543167114258,
      "learning_rate": 3.8905572238905574e-05,
      "loss": 0.501,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5293413400650024,
      "eval_runtime": 11.4877,
      "eval_samples_per_second": 326.437,
      "eval_steps_per_second": 5.136,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5597025156021118,
      "learning_rate": 3.335001668335002e-05,
      "loss": 0.252,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8701333333333333,
      "eval_loss": 0.4542345702648163,
      "eval_runtime": 10.9875,
      "eval_samples_per_second": 341.296,
      "eval_steps_per_second": 5.37,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.7948410511016846,
      "learning_rate": 2.7794461127794462e-05,
      "loss": 0.131,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8818666666666667,
      "eval_loss": 0.44216179847717285,
      "eval_runtime": 11.554,
      "eval_samples_per_second": 324.562,
      "eval_steps_per_second": 5.106,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4461965560913086,
      "learning_rate": 2.2238905572238907e-05,
      "loss": 0.0637,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.4370324909687042,
      "eval_runtime": 10.7774,
      "eval_samples_per_second": 347.95,
      "eval_steps_per_second": 5.474,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.404895305633545,
      "learning_rate": 1.668335001668335e-05,
      "loss": 0.0285,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.41438257694244385,
      "eval_runtime": 10.7633,
      "eval_samples_per_second": 348.407,
      "eval_steps_per_second": 5.482,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.173116445541382,
      "learning_rate": 1.1127794461127795e-05,
      "loss": 0.0107,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.4165852665901184,
      "eval_runtime": 10.8834,
      "eval_samples_per_second": 344.562,
      "eval_steps_per_second": 5.421,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.23237021267414093,
      "learning_rate": 5.572238905572239e-06,
      "loss": 0.0049,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8957333333333334,
      "eval_loss": 0.4219040274620056,
      "eval_runtime": 10.7657,
      "eval_samples_per_second": 348.329,
      "eval_steps_per_second": 5.48,
      "step": 2664
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.2952362298965454,
      "learning_rate": 1.6683350016683353e-08,
      "loss": 0.0037,
      "step": 2997
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8962666666666667,
      "eval_loss": 0.4160127639770508,
      "eval_runtime": 10.84,
      "eval_samples_per_second": 345.942,
      "eval_steps_per_second": 5.443,
      "step": 2997
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.482671885603328e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}