Hugging Face's logo

yashshinde0080
/
regnet_y_400mf-mlxim-finetuned-chest_xray-pneumonia

Image Classification
Transformers
Safetensors
regnet
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
yashshinde0080 commited on
Commit
5d48597
·
verified ·
1 Parent(s): 56315c9

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +13 -0
  2. eval_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +224 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8706896551724138,
4
+ "eval_loss": 0.33842238783836365,
5
+ "eval_runtime": 125.3951,
6
+ "eval_samples_per_second": 8.326,
7
+ "eval_steps_per_second": 0.263,
8
+ "total_flos": 4.975400461644104e+17,
9
+ "train_loss": 0.3838548327351476,
10
+ "train_runtime": 9417.8372,
11
+ "train_samples_per_second": 2.99,
12
+ "train_steps_per_second": 0.024
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8706896551724138,
4
+ "eval_loss": 0.33842238783836365,
5
+ "eval_runtime": 125.3951,
6
+ "eval_samples_per_second": 8.326,
7
+ "eval_steps_per_second": 0.263
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4.975400461644104e+17,
4
+ "train_loss": 0.3838548327351476,
5
+ "train_runtime": 9417.8372,
6
+ "train_samples_per_second": 2.99,
7
+ "train_steps_per_second": 0.024
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 222,
3
+ "best_metric": 0.8706896551724138,
4
+ "best_model_checkpoint": "regnet_y_400mf-mlxim-finetuned-chest_xray-pneumonia\\checkpoint-222",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 222,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1360544217687075,
14
+ "grad_norm": 28.7855167388916,
15
+ "learning_rate": 1.956521739130435e-05,
16
+ "loss": 0.6087,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.272108843537415,
21
+ "grad_norm": 43.801177978515625,
22
+ "learning_rate": 4.130434782608696e-05,
23
+ "loss": 0.5084,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.40816326530612246,
28
+ "grad_norm": 25.356504440307617,
29
+ "learning_rate": 4.849246231155779e-05,
30
+ "loss": 0.4925,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.54421768707483,
35
+ "grad_norm": 26.614465713500977,
36
+ "learning_rate": 4.597989949748744e-05,
37
+ "loss": 0.4521,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.6802721088435374,
42
+ "grad_norm": 19.9810848236084,
43
+ "learning_rate": 4.346733668341709e-05,
44
+ "loss": 0.4434,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.8163265306122449,
49
+ "grad_norm": 25.83266258239746,
50
+ "learning_rate": 4.095477386934674e-05,
51
+ "loss": 0.381,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.9523809523809523,
56
+ "grad_norm": 39.32706069946289,
57
+ "learning_rate": 3.844221105527639e-05,
58
+ "loss": 0.4107,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "eval_accuracy": 0.6829501915708812,
64
+ "eval_loss": 0.6099166870117188,
65
+ "eval_runtime": 112.6101,
66
+ "eval_samples_per_second": 9.271,
67
+ "eval_steps_per_second": 0.293,
68
+ "step": 74
69
+ },
70
+ {
71
+ "epoch": 1.0816326530612246,
72
+ "grad_norm": 26.652603149414062,
73
+ "learning_rate": 3.592964824120603e-05,
74
+ "loss": 0.3729,
75
+ "step": 80
76
+ },
77
+ {
78
+ "epoch": 1.217687074829932,
79
+ "grad_norm": 30.554269790649414,
80
+ "learning_rate": 3.341708542713568e-05,
81
+ "loss": 0.3731,
82
+ "step": 90
83
+ },
84
+ {
85
+ "epoch": 1.3537414965986394,
86
+ "grad_norm": 20.16573143005371,
87
+ "learning_rate": 3.0904522613065326e-05,
88
+ "loss": 0.3633,
89
+ "step": 100
90
+ },
91
+ {
92
+ "epoch": 1.489795918367347,
93
+ "grad_norm": 38.18863296508789,
94
+ "learning_rate": 2.8391959798994978e-05,
95
+ "loss": 0.3606,
96
+ "step": 110
97
+ },
98
+ {
99
+ "epoch": 1.6258503401360545,
100
+ "grad_norm": 32.72572326660156,
101
+ "learning_rate": 2.5879396984924626e-05,
102
+ "loss": 0.3292,
103
+ "step": 120
104
+ },
105
+ {
106
+ "epoch": 1.7619047619047619,
107
+ "grad_norm": 30.875274658203125,
108
+ "learning_rate": 2.3366834170854275e-05,
109
+ "loss": 0.3345,
110
+ "step": 130
111
+ },
112
+ {
113
+ "epoch": 1.8979591836734695,
114
+ "grad_norm": 36.543487548828125,
115
+ "learning_rate": 2.085427135678392e-05,
116
+ "loss": 0.3186,
117
+ "step": 140
118
+ },
119
+ {
120
+ "epoch": 2.0,
121
+ "eval_accuracy": 0.7452107279693486,
122
+ "eval_loss": 0.5401968955993652,
123
+ "eval_runtime": 118.9784,
124
+ "eval_samples_per_second": 8.775,
125
+ "eval_steps_per_second": 0.277,
126
+ "step": 148
127
+ },
128
+ {
129
+ "epoch": 2.0272108843537415,
130
+ "grad_norm": 34.06245040893555,
131
+ "learning_rate": 1.834170854271357e-05,
132
+ "loss": 0.3627,
133
+ "step": 150
134
+ },
135
+ {
136
+ "epoch": 2.163265306122449,
137
+ "grad_norm": 28.00713539123535,
138
+ "learning_rate": 1.5829145728643217e-05,
139
+ "loss": 0.3284,
140
+ "step": 160
141
+ },
142
+ {
143
+ "epoch": 2.2993197278911564,
144
+ "grad_norm": 41.861385345458984,
145
+ "learning_rate": 1.3316582914572864e-05,
146
+ "loss": 0.3309,
147
+ "step": 170
148
+ },
149
+ {
150
+ "epoch": 2.435374149659864,
151
+ "grad_norm": 23.51487922668457,
152
+ "learning_rate": 1.0804020100502512e-05,
153
+ "loss": 0.3197,
154
+ "step": 180
155
+ },
156
+ {
157
+ "epoch": 2.571428571428571,
158
+ "grad_norm": 34.21602249145508,
159
+ "learning_rate": 8.291457286432161e-06,
160
+ "loss": 0.3373,
161
+ "step": 190
162
+ },
163
+ {
164
+ "epoch": 2.707482993197279,
165
+ "grad_norm": 28.09819221496582,
166
+ "learning_rate": 5.778894472361809e-06,
167
+ "loss": 0.3174,
168
+ "step": 200
169
+ },
170
+ {
171
+ "epoch": 2.8435374149659864,
172
+ "grad_norm": 31.80492401123047,
173
+ "learning_rate": 3.2663316582914575e-06,
174
+ "loss": 0.3282,
175
+ "step": 210
176
+ },
177
+ {
178
+ "epoch": 2.979591836734694,
179
+ "grad_norm": 59.607566833496094,
180
+ "learning_rate": 7.537688442211055e-07,
181
+ "loss": 0.3731,
182
+ "step": 220
183
+ },
184
+ {
185
+ "epoch": 3.0,
186
+ "eval_accuracy": 0.8706896551724138,
187
+ "eval_loss": 0.33842238783836365,
188
+ "eval_runtime": 110.0941,
189
+ "eval_samples_per_second": 9.483,
190
+ "eval_steps_per_second": 0.3,
191
+ "step": 222
192
+ },
193
+ {
194
+ "epoch": 3.0,
195
+ "step": 222,
196
+ "total_flos": 4.975400461644104e+17,
197
+ "train_loss": 0.3838548327351476,
198
+ "train_runtime": 9417.8372,
199
+ "train_samples_per_second": 2.99,
200
+ "train_steps_per_second": 0.024
201
+ }
202
+ ],
203
+ "logging_steps": 10,
204
+ "max_steps": 222,
205
+ "num_input_tokens_seen": 0,
206
+ "num_train_epochs": 3,
207
+ "save_steps": 500,
208
+ "stateful_callbacks": {
209
+ "TrainerControl": {
210
+ "args": {
211
+ "should_epoch_stop": false,
212
+ "should_evaluate": false,
213
+ "should_log": false,
214
+ "should_save": true,
215
+ "should_training_stop": true
216
+ },
217
+ "attributes": {}
218
+ }
219
+ },
220
+ "total_flos": 4.975400461644104e+17,
221
+ "train_batch_size": 32,
222
+ "trial_name": null,
223
+ "trial_params": null
224
+ }