Hugging Face's logo

Rakhman16
/
program-synthesis-java-codet5-xlcost

Text Generation
Transformers
TensorBoard
Safetensors
English
t5
text2text-generation
code
text-generation-inference
Model card Files
xet
 Metrics Community
program-synthesis-java-codet5-xlcost
File size: 5,394 Bytes
e4fe6f7
 
 
0547431
e4fe6f7
0547431
e4fe6f7
 
 
 
 
 
 
 
 
 
f83c9fb
 
 
 
 
 
 
c989f5d
 
 
 
 
 
 
6030f73
 
 
 
 
 
 
a61a76e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39f55a5
 
 
 
 
 
 
913fd2a
 
 
 
 
 
 
1dba68d
 
 
 
 
 
 
17cd956
 
 
 
 
 
 
c299718
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a6f55c
 
 
 
 
 
 
b59c5a3
 
 
 
 
 
 
8203b67
 
 
 
 
 
 
8445695
 
 
 
 
 
 
3440cfd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09c7cb8
 
 
 
 
 
 
f19eb5a
 
 
 
 
 
 
810027e
 
 
 
 
 
 
996cc6b
 
 
 
 
 
 
7d63dd4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e9b1604
 
 
 
 
 
 
0547431
 
 
 
 
 
 
e4fe6f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0547431
e4fe6f7
 
 
 
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
216
217
218
219
220
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.57190357439734,
  "eval_steps": 500,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.7872959971427917,
      "learning_rate": 1.917206982543641e-05,
      "loss": 0.7834,
      "step": 500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 0.9406130313873291,
      "learning_rate": 1.834081463009144e-05,
      "loss": 0.4895,
      "step": 1000
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.4806763529777527,
      "learning_rate": 1.7509559434746467e-05,
      "loss": 0.4473,
      "step": 1500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 0.5443118214607239,
      "learning_rate": 1.6678304239401496e-05,
      "loss": 0.4326,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.33564111590385437,
      "eval_runtime": 26.7564,
      "eval_samples_per_second": 18.463,
      "eval_steps_per_second": 4.634,
      "step": 2406
    },
    {
      "epoch": 1.0390689941812137,
      "grad_norm": 0.7427258491516113,
      "learning_rate": 1.5847049044056525e-05,
      "loss": 0.4225,
      "step": 2500
    },
    {
      "epoch": 1.2468827930174564,
      "grad_norm": 0.4491533637046814,
      "learning_rate": 1.5015793848711555e-05,
      "loss": 0.3857,
      "step": 3000
    },
    {
      "epoch": 1.4546965918536992,
      "grad_norm": 0.4072982668876648,
      "learning_rate": 1.4184538653366584e-05,
      "loss": 0.3754,
      "step": 3500
    },
    {
      "epoch": 1.6625103906899419,
      "grad_norm": 0.8853089213371277,
      "learning_rate": 1.3353283458021613e-05,
      "loss": 0.3765,
      "step": 4000
    },
    {
      "epoch": 1.8703241895261846,
      "grad_norm": 0.59534752368927,
      "learning_rate": 1.2522028262676643e-05,
      "loss": 0.3677,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3049054443836212,
      "eval_runtime": 26.7561,
      "eval_samples_per_second": 18.463,
      "eval_steps_per_second": 4.634,
      "step": 4812
    },
    {
      "epoch": 2.0781379883624274,
      "grad_norm": 0.5839773416519165,
      "learning_rate": 1.1690773067331672e-05,
      "loss": 0.3488,
      "step": 5000
    },
    {
      "epoch": 2.28595178719867,
      "grad_norm": 0.8203754425048828,
      "learning_rate": 1.086118038237739e-05,
      "loss": 0.3526,
      "step": 5500
    },
    {
      "epoch": 2.493765586034913,
      "grad_norm": 0.7811100482940674,
      "learning_rate": 1.0029925187032419e-05,
      "loss": 0.3438,
      "step": 6000
    },
    {
      "epoch": 2.7015793848711556,
      "grad_norm": 0.823439359664917,
      "learning_rate": 9.19866999168745e-06,
      "loss": 0.3406,
      "step": 6500
    },
    {
      "epoch": 2.9093931837073983,
      "grad_norm": 0.5342724323272705,
      "learning_rate": 8.367414796342478e-06,
      "loss": 0.3333,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2934778034687042,
      "eval_runtime": 26.7608,
      "eval_samples_per_second": 18.46,
      "eval_steps_per_second": 4.634,
      "step": 7218
    },
    {
      "epoch": 3.117206982543641,
      "grad_norm": 0.4342059791088104,
      "learning_rate": 7.536159600997507e-06,
      "loss": 0.3313,
      "step": 7500
    },
    {
      "epoch": 3.3250207813798838,
      "grad_norm": 0.9092524647712708,
      "learning_rate": 6.704904405652536e-06,
      "loss": 0.3265,
      "step": 8000
    },
    {
      "epoch": 3.5328345802161265,
      "grad_norm": 0.7057175040245056,
      "learning_rate": 5.873649210307565e-06,
      "loss": 0.3219,
      "step": 8500
    },
    {
      "epoch": 3.7406483790523692,
      "grad_norm": 0.8144080638885498,
      "learning_rate": 5.0423940149625935e-06,
      "loss": 0.316,
      "step": 9000
    },
    {
      "epoch": 3.9484621778886115,
      "grad_norm": 0.5943393707275391,
      "learning_rate": 4.212801330008313e-06,
      "loss": 0.3155,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2871634364128113,
      "eval_runtime": 26.8766,
      "eval_samples_per_second": 18.38,
      "eval_steps_per_second": 4.614,
      "step": 9624
    },
    {
      "epoch": 4.156275976724855,
      "grad_norm": 1.265112280845642,
      "learning_rate": 3.381546134663342e-06,
      "loss": 0.3036,
      "step": 10000
    },
    {
      "epoch": 4.364089775561097,
      "grad_norm": 0.7941420078277588,
      "learning_rate": 2.550290939318371e-06,
      "loss": 0.3129,
      "step": 10500
    },
    {
      "epoch": 4.57190357439734,
      "grad_norm": 0.956358015537262,
      "learning_rate": 1.7190357439733998e-06,
      "loss": 0.3166,
      "step": 11000
    }
  ],
  "logging_steps": 500,
  "max_steps": 12030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.679171135307776e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}