Hugging Face's logo

triki07
/
trocr-large-printed-cmc7_tesseract_MICR_ocr

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
triki07 commited on
Commit
a182712
•
1 Parent(s): 164ec6a

Model save

Browse files
Files changed (1) hide show
  1. trainer_state.json +238 -0
trainer_state.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 936,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 134.19052124023438,
14
+ "learning_rate": 4.996794871794872e-05,
15
+ "loss": 9.1177,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "grad_norm": 46.553192138671875,
21
+ "learning_rate": 4.9006410256410256e-05,
22
+ "loss": 2.6116,
23
+ "step": 31
24
+ },
25
+ {
26
+ "epoch": 0.2,
27
+ "grad_norm": 17.68166732788086,
28
+ "learning_rate": 4.8012820512820516e-05,
29
+ "loss": 0.8879,
30
+ "step": 62
31
+ },
32
+ {
33
+ "epoch": 0.3,
34
+ "grad_norm": 17.172128677368164,
35
+ "learning_rate": 4.701923076923077e-05,
36
+ "loss": 1.0567,
37
+ "step": 93
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "grad_norm": 104.65974426269531,
42
+ "learning_rate": 4.602564102564102e-05,
43
+ "loss": 0.9872,
44
+ "step": 124
45
+ },
46
+ {
47
+ "epoch": 0.5,
48
+ "grad_norm": 16.036008834838867,
49
+ "learning_rate": 4.503205128205128e-05,
50
+ "loss": 0.9717,
51
+ "step": 155
52
+ },
53
+ {
54
+ "epoch": 0.6,
55
+ "grad_norm": 27.394895553588867,
56
+ "learning_rate": 4.403846153846154e-05,
57
+ "loss": 0.8679,
58
+ "step": 186
59
+ },
60
+ {
61
+ "epoch": 0.7,
62
+ "grad_norm": 37.157169342041016,
63
+ "learning_rate": 4.30448717948718e-05,
64
+ "loss": 0.8257,
65
+ "step": 217
66
+ },
67
+ {
68
+ "epoch": 0.79,
69
+ "grad_norm": 8.90817928314209,
70
+ "learning_rate": 4.205128205128206e-05,
71
+ "loss": 0.8604,
72
+ "step": 248
73
+ },
74
+ {
75
+ "epoch": 0.89,
76
+ "grad_norm": 13.38546085357666,
77
+ "learning_rate": 4.105769230769231e-05,
78
+ "loss": 0.8587,
79
+ "step": 279
80
+ },
81
+ {
82
+ "epoch": 0.99,
83
+ "grad_norm": 32.03287124633789,
84
+ "learning_rate": 4.006410256410257e-05,
85
+ "loss": 0.8512,
86
+ "step": 310
87
+ },
88
+ {
89
+ "epoch": 1.09,
90
+ "grad_norm": 20.29245376586914,
91
+ "learning_rate": 3.9070512820512824e-05,
92
+ "loss": 0.6728,
93
+ "step": 341
94
+ },
95
+ {
96
+ "epoch": 1.19,
97
+ "grad_norm": 10.910124778747559,
98
+ "learning_rate": 3.807692307692308e-05,
99
+ "loss": 0.611,
100
+ "step": 372
101
+ },
102
+ {
103
+ "epoch": 1.29,
104
+ "grad_norm": 14.703102111816406,
105
+ "learning_rate": 3.708333333333334e-05,
106
+ "loss": 0.6468,
107
+ "step": 403
108
+ },
109
+ {
110
+ "epoch": 1.39,
111
+ "grad_norm": 9.841747283935547,
112
+ "learning_rate": 3.608974358974359e-05,
113
+ "loss": 0.5327,
114
+ "step": 434
115
+ },
116
+ {
117
+ "epoch": 1.49,
118
+ "grad_norm": 15.09598445892334,
119
+ "learning_rate": 3.5096153846153845e-05,
120
+ "loss": 0.5669,
121
+ "step": 465
122
+ },
123
+ {
124
+ "epoch": 1.59,
125
+ "grad_norm": 18.652040481567383,
126
+ "learning_rate": 3.4102564102564105e-05,
127
+ "loss": 0.4854,
128
+ "step": 496
129
+ },
130
+ {
131
+ "epoch": 1.69,
132
+ "grad_norm": 8.733405113220215,
133
+ "learning_rate": 3.310897435897436e-05,
134
+ "loss": 0.5627,
135
+ "step": 527
136
+ },
137
+ {
138
+ "epoch": 1.79,
139
+ "grad_norm": 21.200965881347656,
140
+ "learning_rate": 3.211538461538462e-05,
141
+ "loss": 0.5001,
142
+ "step": 558
143
+ },
144
+ {
145
+ "epoch": 1.89,
146
+ "grad_norm": 7.368778228759766,
147
+ "learning_rate": 3.112179487179487e-05,
148
+ "loss": 0.4897,
149
+ "step": 589
150
+ },
151
+ {
152
+ "epoch": 1.99,
153
+ "grad_norm": 16.03817367553711,
154
+ "learning_rate": 3.012820512820513e-05,
155
+ "loss": 0.5294,
156
+ "step": 620
157
+ },
158
+ {
159
+ "epoch": 2.09,
160
+ "grad_norm": 35.705631256103516,
161
+ "learning_rate": 2.913461538461539e-05,
162
+ "loss": 0.4197,
163
+ "step": 651
164
+ },
165
+ {
166
+ "epoch": 2.19,
167
+ "grad_norm": 10.462698936462402,
168
+ "learning_rate": 2.8141025641025643e-05,
169
+ "loss": 0.3589,
170
+ "step": 682
171
+ },
172
+ {
173
+ "epoch": 2.29,
174
+ "grad_norm": 7.011005878448486,
175
+ "learning_rate": 2.7147435897435896e-05,
176
+ "loss": 0.4396,
177
+ "step": 713
178
+ },
179
+ {
180
+ "epoch": 2.38,
181
+ "grad_norm": 4.32899284362793,
182
+ "learning_rate": 2.6153846153846157e-05,
183
+ "loss": 0.4604,
184
+ "step": 744
185
+ },
186
+ {
187
+ "epoch": 2.48,
188
+ "grad_norm": 5.010735988616943,
189
+ "learning_rate": 2.516025641025641e-05,
190
+ "loss": 0.3764,
191
+ "step": 775
192
+ },
193
+ {
194
+ "epoch": 2.58,
195
+ "grad_norm": 6.4428582191467285,
196
+ "learning_rate": 2.4166666666666667e-05,
197
+ "loss": 0.3035,
198
+ "step": 806
199
+ },
200
+ {
201
+ "epoch": 2.68,
202
+ "grad_norm": 11.917937278747559,
203
+ "learning_rate": 2.3173076923076924e-05,
204
+ "loss": 0.3287,
205
+ "step": 837
206
+ },
207
+ {
208
+ "epoch": 2.78,
209
+ "grad_norm": 18.710346221923828,
210
+ "learning_rate": 2.217948717948718e-05,
211
+ "loss": 0.3209,
212
+ "step": 868
213
+ },
214
+ {
215
+ "epoch": 2.88,
216
+ "grad_norm": 5.8296990394592285,
217
+ "learning_rate": 2.1185897435897437e-05,
218
+ "loss": 0.329,
219
+ "step": 899
220
+ },
221
+ {
222
+ "epoch": 2.98,
223
+ "grad_norm": 11.532828330993652,
224
+ "learning_rate": 2.0192307692307694e-05,
225
+ "loss": 0.2934,
226
+ "step": 930
227
+ }
228
+ ],
229
+ "logging_steps": 31,
230
+ "max_steps": 1560,
231
+ "num_input_tokens_seen": 0,
232
+ "num_train_epochs": 5,
233
+ "save_steps": 500,
234
+ "total_flos": 1.1075205215224332e+19,
235
+ "train_batch_size": 8,
236
+ "trial_name": null,
237
+ "trial_params": null
238
+ }