mekbus/codebert-xss-php

1{
2  "best_metric": 0.9907529722589168,
3  "best_model_checkpoint": "./php_cwe79_codebert_output\\checkpoint-627",
4  "epoch": 5.996810207336523,
5  "global_step": 940,
6  "is_hyper_param_search": false,
7  "is_local_process_zero": true,
8  "is_world_process_zero": true,
9  "log_history": [
10    {
11      "epoch": 0.32,
12      "learning_rate": 3.205128205128206e-06,
13      "loss": 0.6994,
14      "step": 50
15    },
16    {
17      "epoch": 0.64,
18      "learning_rate": 6.410256410256412e-06,
19      "loss": 0.6957,
20      "step": 100
21    },
22    {
23      "epoch": 0.96,
24      "learning_rate": 9.615384615384616e-06,
25      "loss": 0.6873,
26      "step": 150
27    },
28    {
29      "epoch": 1.0,
30      "eval_accuracy": 0.6689265536723163,
31      "eval_f1": 0.6689265536723163,
32      "eval_loss": 0.6734532713890076,
33      "eval_precision": 0.581532416502947,
34      "eval_recall": 0.7872340425531915,
35      "eval_runtime": 11.4008,
36      "eval_samples_per_second": 77.626,
37      "eval_steps_per_second": 4.912,
38      "step": 156
39    },
40    {
41      "epoch": 1.28,
42      "learning_rate": 1.2820512820512823e-05,
43      "loss": 0.6729,
44      "step": 200
45    },
46    {
47      "epoch": 1.59,
48      "learning_rate": 1.602564102564103e-05,
49      "loss": 0.5098,
50      "step": 250
51    },
52    {
53      "epoch": 1.91,
54      "learning_rate": 1.923076923076923e-05,
55      "loss": 0.3065,
56      "step": 300
57    },
58    {
59      "epoch": 2.0,
60      "eval_accuracy": 0.9299435028248587,
61      "eval_f1": 0.9146005509641874,
62      "eval_loss": 0.16874603927135468,
63      "eval_precision": 0.9485714285714286,
64      "eval_recall": 0.8829787234042553,
65      "eval_runtime": 11.7337,
66      "eval_samples_per_second": 75.424,
67      "eval_steps_per_second": 4.773,
68      "step": 313
69    },
70    {
71      "epoch": 2.23,
72      "learning_rate": 1.972934472934473e-05,
73      "loss": 0.2084,
74      "step": 350
75    },
76    {
77      "epoch": 2.55,
78      "learning_rate": 1.9373219373219374e-05,
79      "loss": 0.1386,
80      "step": 400
81    },
82    {
83      "epoch": 2.87,
84      "learning_rate": 1.9017094017094017e-05,
85      "loss": 0.0805,
86      "step": 450
87    },
88    {
89      "epoch": 3.0,
90      "eval_accuracy": 0.9796610169491525,
91      "eval_f1": 0.9757412398921833,
92      "eval_loss": 0.046507738530635834,
93      "eval_precision": 0.9890710382513661,
94      "eval_recall": 0.9627659574468085,
95      "eval_runtime": 11.7373,
96      "eval_samples_per_second": 75.401,
97      "eval_steps_per_second": 4.771,
98      "step": 470
99    },
100    {
101      "epoch": 3.19,
102      "learning_rate": 1.8660968660968664e-05,
103      "loss": 0.0677,
104      "step": 500
105    },
106    {
107      "epoch": 3.51,
108      "learning_rate": 1.8304843304843308e-05,
109      "loss": 0.0628,
110      "step": 550
111    },
112    {
113      "epoch": 3.83,
114      "learning_rate": 1.794871794871795e-05,
115      "loss": 0.0359,
116      "step": 600
117    },
118    {
119      "epoch": 4.0,
120      "eval_accuracy": 0.992090395480226,
121      "eval_f1": 0.9907529722589168,
122      "eval_loss": 0.03131083399057388,
123      "eval_precision": 0.984251968503937,
124      "eval_recall": 0.9973404255319149,
125      "eval_runtime": 11.9166,
126      "eval_samples_per_second": 74.266,
127      "eval_steps_per_second": 4.699,
128      "step": 627
129    },
130    {
131      "epoch": 4.15,
132      "learning_rate": 1.7599715099715102e-05,
133      "loss": 0.0412,
134      "step": 650
135    },
136    {
137      "epoch": 4.47,
138      "learning_rate": 1.7243589743589745e-05,
139      "loss": 0.0457,
140      "step": 700
141    },
142    {
143      "epoch": 4.78,
144      "learning_rate": 1.688746438746439e-05,
145      "loss": 0.0316,
146      "step": 750
147    },
148    {
149      "epoch": 5.0,
150      "eval_accuracy": 0.9909604519774011,
151      "eval_f1": 0.9894736842105263,
152      "eval_loss": 0.02798781916499138,
153      "eval_precision": 0.9791666666666666,
154      "eval_recall": 1.0,
155      "eval_runtime": 11.9117,
156      "eval_samples_per_second": 74.297,
157      "eval_steps_per_second": 4.701,
158      "step": 783
159    },
160    {
161      "epoch": 5.1,
162      "learning_rate": 1.6531339031339032e-05,
163      "loss": 0.0355,
164      "step": 800
165    },
166    {
167      "epoch": 5.42,
168      "learning_rate": 1.6175213675213675e-05,
169      "loss": 0.0285,
170      "step": 850
171    },
172    {
173      "epoch": 5.74,
174      "learning_rate": 1.581908831908832e-05,
175      "loss": 0.0285,
176      "step": 900
177    },
178    {
179      "epoch": 6.0,
180      "eval_accuracy": 0.9909604519774011,
181      "eval_f1": 0.9894179894179894,
182      "eval_loss": 0.027588626369833946,
183      "eval_precision": 0.9842105263157894,
184      "eval_recall": 0.9946808510638298,
185      "eval_runtime": 12.0204,
186      "eval_samples_per_second": 73.625,
187      "eval_steps_per_second": 4.659,
188      "step": 940
189    }
190  ],
191  "max_steps": 3120,
192  "num_train_epochs": 20,
193  "total_flos": 7915432989450240.0,
194  "trial_name": null,
195  "trial_params": null
196}
197