File size: 5,765 Bytes
65a8cca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.8767404952738379,
  "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-700",
  "epoch": 0.6396588486140725,
  "eval_steps": 100,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053304904051172705,
      "eval_accuracy": 0.6321578647928374,
      "eval_f1": 0.6321578647928374,
      "eval_loss": 0.9594171643257141,
      "eval_precision": 0.6321578647928374,
      "eval_recall": 0.6321578647928374,
      "eval_runtime": 69.4219,
      "eval_samples_per_second": 23.148,
      "eval_steps_per_second": 0.735,
      "step": 100
    },
    {
      "epoch": 0.10660980810234541,
      "eval_accuracy": 0.8202860650583409,
      "eval_f1": 0.8202860650583409,
      "eval_loss": 0.6088714599609375,
      "eval_precision": 0.8202860650583409,
      "eval_recall": 0.8202860650583409,
      "eval_runtime": 69.0048,
      "eval_samples_per_second": 23.288,
      "eval_steps_per_second": 0.739,
      "step": 200
    },
    {
      "epoch": 0.15991471215351813,
      "eval_accuracy": 0.7378602014233383,
      "eval_f1": 0.7378602014233383,
      "eval_loss": 0.7009087800979614,
      "eval_precision": 0.7378602014233383,
      "eval_recall": 0.7378602014233383,
      "eval_runtime": 68.7975,
      "eval_samples_per_second": 23.358,
      "eval_steps_per_second": 0.741,
      "step": 300
    },
    {
      "epoch": 0.21321961620469082,
      "eval_accuracy": 0.7694710890634513,
      "eval_f1": 0.7694710890634513,
      "eval_loss": 0.5369378328323364,
      "eval_precision": 0.7694710890634513,
      "eval_recall": 0.7694710890634513,
      "eval_runtime": 69.0856,
      "eval_samples_per_second": 23.261,
      "eval_steps_per_second": 0.738,
      "step": 400
    },
    {
      "epoch": 0.26652452025586354,
      "grad_norm": 443972.875,
      "learning_rate": 1.4669509594882732e-05,
      "loss": 0.7136,
      "step": 500
    },
    {
      "epoch": 0.26652452025586354,
      "eval_accuracy": 0.8621777276492958,
      "eval_f1": 0.8621777276492958,
      "eval_loss": 0.4052257537841797,
      "eval_precision": 0.8621777276492958,
      "eval_recall": 0.8621777276492958,
      "eval_runtime": 68.528,
      "eval_samples_per_second": 23.45,
      "eval_steps_per_second": 0.744,
      "step": 500
    },
    {
      "epoch": 0.31982942430703626,
      "eval_accuracy": 0.8714304251050535,
      "eval_f1": 0.8714304251050535,
      "eval_loss": 0.40161609649658203,
      "eval_precision": 0.8714304251050535,
      "eval_recall": 0.8714304251050535,
      "eval_runtime": 68.104,
      "eval_samples_per_second": 23.596,
      "eval_steps_per_second": 0.749,
      "step": 600
    },
    {
      "epoch": 0.373134328358209,
      "eval_accuracy": 0.8767404952738379,
      "eval_f1": 0.8767404952738379,
      "eval_loss": 0.38839995861053467,
      "eval_precision": 0.8767404952738379,
      "eval_recall": 0.8767404952738379,
      "eval_runtime": 69.1004,
      "eval_samples_per_second": 23.256,
      "eval_steps_per_second": 0.738,
      "step": 700
    },
    {
      "epoch": 0.42643923240938164,
      "eval_accuracy": 0.866569515006937,
      "eval_f1": 0.866569515006937,
      "eval_loss": 0.4080258309841156,
      "eval_precision": 0.866569515006937,
      "eval_recall": 0.866569515006937,
      "eval_runtime": 68.4146,
      "eval_samples_per_second": 23.489,
      "eval_steps_per_second": 0.745,
      "step": 800
    },
    {
      "epoch": 0.47974413646055436,
      "eval_accuracy": 0.8303472506413008,
      "eval_f1": 0.8303472506413008,
      "eval_loss": 0.45843783020973206,
      "eval_precision": 0.8303472506413008,
      "eval_recall": 0.8303472506413008,
      "eval_runtime": 68.5359,
      "eval_samples_per_second": 23.448,
      "eval_steps_per_second": 0.744,
      "step": 900
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 97385.5703125,
      "learning_rate": 9.339019189765458e-06,
      "loss": 0.4387,
      "step": 1000
    },
    {
      "epoch": 0.5330490405117271,
      "eval_accuracy": 0.7901524149839799,
      "eval_f1": 0.7901524149839798,
      "eval_loss": 0.525492250919342,
      "eval_precision": 0.7901524149839799,
      "eval_recall": 0.7901524149839799,
      "eval_runtime": 69.1745,
      "eval_samples_per_second": 23.231,
      "eval_steps_per_second": 0.737,
      "step": 1000
    },
    {
      "epoch": 0.5863539445628998,
      "eval_accuracy": 0.8467964905626478,
      "eval_f1": 0.8467964905626478,
      "eval_loss": 0.43574053049087524,
      "eval_precision": 0.8467964905626478,
      "eval_recall": 0.8467964905626478,
      "eval_runtime": 68.6889,
      "eval_samples_per_second": 23.395,
      "eval_steps_per_second": 0.742,
      "step": 1100
    },
    {
      "epoch": 0.6396588486140725,
      "eval_accuracy": 0.8247676844301157,
      "eval_f1": 0.8247676844301157,
      "eval_loss": 0.434725821018219,
      "eval_precision": 0.8247676844301157,
      "eval_recall": 0.8247676844301157,
      "eval_runtime": 68.391,
      "eval_samples_per_second": 23.497,
      "eval_steps_per_second": 0.746,
      "step": 1200
    }
  ],
  "logging_steps": 500,
  "max_steps": 1876,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2670453492940800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}