Hugging Face's logo

rakhman-llm
/
code-synthesis-java-snippet

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
code-synthesis-java-snippet
File size: 3,230 Bytes 
69801c1
 
 
f93d491
69801c1
f93d491
69801c1
 
 
 
 
 
7051856
 
 
69801c1
a72edac
 
 
 
 
 
 
25241dc
 
 
 
 
 
 
b902a6a
 
 
 
 
 
 
779f68e
 
 
 
 
 
 
5dde5f1
 
 
 
 
 
 
d46a7fc
 
 
 
 
 
 
e7fd55f
 
 
 
 
 
 
8d0a493
 
 
 
 
 
 
2a5af68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
426e64f
 
 
 
 
 
 
f783eea
 
 
 
 
 
 
f93d491
 
 
 
 
 
 
69801c1
 
 
 
 
 
 
 
 
 
 
 
 
 
7051856
69801c1
 
 
 
f93d491
69801c1
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3507896924355778,
  "eval_steps": 500,
  "global_step": 6500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10390689941812137,
      "grad_norm": 3.488266944885254,
      "learning_rate": 1.9311443613189252e-05,
      "loss": 0.8436,
      "step": 500
    },
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.8393851518630981,
      "learning_rate": 1.8618730950401776e-05,
      "loss": 0.5316,
      "step": 1000
    },
    {
      "epoch": 0.3117206982543641,
      "grad_norm": 1.4351526498794556,
      "learning_rate": 1.79260182876143e-05,
      "loss": 0.483,
      "step": 1500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 1.4630037546157837,
      "learning_rate": 1.7233305624826823e-05,
      "loss": 0.4516,
      "step": 2000
    },
    {
      "epoch": 0.5195344970906068,
      "grad_norm": 0.854028046131134,
      "learning_rate": 1.6540592962039347e-05,
      "loss": 0.4387,
      "step": 2500
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.8339985013008118,
      "learning_rate": 1.584788029925187e-05,
      "loss": 0.4192,
      "step": 3000
    },
    {
      "epoch": 0.7273482959268496,
      "grad_norm": 1.0237222909927368,
      "learning_rate": 1.5155167636464397e-05,
      "loss": 0.422,
      "step": 3500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 1.0825960636138916,
      "learning_rate": 1.446245497367692e-05,
      "loss": 0.4065,
      "step": 4000
    },
    {
      "epoch": 0.9351620947630923,
      "grad_norm": 1.4909119606018066,
      "learning_rate": 1.3769742310889445e-05,
      "loss": 0.4031,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3220335841178894,
      "eval_runtime": 31.3207,
      "eval_samples_per_second": 15.772,
      "eval_steps_per_second": 7.886,
      "step": 4812
    },
    {
      "epoch": 1.0390689941812137,
      "grad_norm": 0.6415828466415405,
      "learning_rate": 1.3077029648101969e-05,
      "loss": 0.4064,
      "step": 5000
    },
    {
      "epoch": 1.142975893599335,
      "grad_norm": 0.6136273741722107,
      "learning_rate": 1.2384316985314493e-05,
      "loss": 0.3599,
      "step": 5500
    },
    {
      "epoch": 1.2468827930174564,
      "grad_norm": 0.49429360032081604,
      "learning_rate": 1.1692989747852592e-05,
      "loss": 0.3737,
      "step": 6000
    },
    {
      "epoch": 1.3507896924355778,
      "grad_norm": 1.103445053100586,
      "learning_rate": 1.1000277085065116e-05,
      "loss": 0.3626,
      "step": 6500
    }
  ],
  "logging_steps": 500,
  "max_steps": 14436,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7915843619389440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}