File size: 5,364 Bytes
93a6d82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
{
  "best_metric": 0.05933728814125061,
  "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/models/t5-small-codesearchnet-python/checkpoint-2625",
  "epoch": 12.0,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_avg_length": 17.1074,
      "eval_bleu": 0.0358,
      "eval_loss": 0.0800933688879013,
      "eval_rouge1": 0.6174,
      "eval_rouge2": 0.6,
      "eval_runtime": 148.3283,
      "eval_samples_per_second": 33.709,
      "eval_steps_per_second": 4.214,
      "step": 375
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.011601821519434452,
      "loss": 1.6066,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_avg_length": 17.0262,
      "eval_bleu": 0.036,
      "eval_loss": 0.06744839996099472,
      "eval_rouge1": 0.6249,
      "eval_rouge2": 0.6068,
      "eval_runtime": 143.9281,
      "eval_samples_per_second": 34.74,
      "eval_steps_per_second": 4.342,
      "step": 750
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.02322324924170971,
      "loss": 0.0584,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_avg_length": 16.9962,
      "eval_bleu": 0.0351,
      "eval_loss": 0.06323764473199844,
      "eval_rouge1": 0.6255,
      "eval_rouge2": 0.6075,
      "eval_runtime": 142.3288,
      "eval_samples_per_second": 35.13,
      "eval_steps_per_second": 4.391,
      "step": 1125
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.03487098217010498,
      "loss": 0.0484,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_avg_length": 17.003,
      "eval_bleu": 0.0351,
      "eval_loss": 0.06048833578824997,
      "eval_rouge1": 0.6251,
      "eval_rouge2": 0.6071,
      "eval_runtime": 142.2689,
      "eval_samples_per_second": 35.145,
      "eval_steps_per_second": 4.393,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_avg_length": 17.0012,
      "eval_bleu": 0.035,
      "eval_loss": 0.05961951985955238,
      "eval_rouge1": 0.6255,
      "eval_rouge2": 0.6075,
      "eval_runtime": 147.0583,
      "eval_samples_per_second": 34.0,
      "eval_steps_per_second": 4.25,
      "step": 1875
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.04655396565794945,
      "loss": 0.0418,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_avg_length": 16.9958,
      "eval_bleu": 0.035,
      "eval_loss": 0.0601988285779953,
      "eval_rouge1": 0.6258,
      "eval_rouge2": 0.608,
      "eval_runtime": 140.3104,
      "eval_samples_per_second": 35.635,
      "eval_steps_per_second": 4.454,
      "step": 2250
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0582905150949955,
      "loss": 0.0377,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_avg_length": 17.0004,
      "eval_bleu": 0.0351,
      "eval_loss": 0.05933728814125061,
      "eval_rouge1": 0.6259,
      "eval_rouge2": 0.6079,
      "eval_runtime": 143.9238,
      "eval_samples_per_second": 34.741,
      "eval_steps_per_second": 4.343,
      "step": 2625
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.07008866220712662,
      "loss": 0.033,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_avg_length": 17.0032,
      "eval_bleu": 0.035,
      "eval_loss": 0.06179109960794449,
      "eval_rouge1": 0.6257,
      "eval_rouge2": 0.6078,
      "eval_runtime": 140.711,
      "eval_samples_per_second": 35.534,
      "eval_steps_per_second": 4.442,
      "step": 3000
    },
    {
      "epoch": 9.0,
      "eval_avg_length": 16.998,
      "eval_bleu": 0.035,
      "eval_loss": 0.06367889791727066,
      "eval_rouge1": 0.6257,
      "eval_rouge2": 0.6078,
      "eval_runtime": 140.8974,
      "eval_samples_per_second": 35.487,
      "eval_steps_per_second": 4.436,
      "step": 3375
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.08194742351770401,
      "loss": 0.028,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_avg_length": 16.9984,
      "eval_bleu": 0.035,
      "eval_loss": 0.06447886675596237,
      "eval_rouge1": 0.6257,
      "eval_rouge2": 0.6079,
      "eval_runtime": 145.6234,
      "eval_samples_per_second": 34.335,
      "eval_steps_per_second": 4.292,
      "step": 3750
    },
    {
      "epoch": 10.67,
      "learning_rate": 0.0939134731888771,
      "loss": 0.0255,
      "step": 4000
    },
    {
      "epoch": 11.0,
      "eval_avg_length": 17.0008,
      "eval_bleu": 0.035,
      "eval_loss": 0.06500716507434845,
      "eval_rouge1": 0.6255,
      "eval_rouge2": 0.6078,
      "eval_runtime": 142.8222,
      "eval_samples_per_second": 35.009,
      "eval_steps_per_second": 4.376,
      "step": 4125
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.10600020736455917,
      "loss": 0.0226,
      "step": 4500
    },
    {
      "epoch": 12.0,
      "eval_avg_length": 16.9976,
      "eval_bleu": 0.035,
      "eval_loss": 0.07480558753013611,
      "eval_rouge1": 0.6254,
      "eval_rouge2": 0.6076,
      "eval_runtime": 140.6294,
      "eval_samples_per_second": 35.554,
      "eval_steps_per_second": 4.444,
      "step": 4500
    }
  ],
  "max_steps": 5625,
  "num_train_epochs": 15,
  "total_flos": 2.436152426496e+16,
  "trial_name": null,
  "trial_params": null
}