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: 2,158 Bytes 
69801c1
 
 
8b257e3
69801c1
8b257e3
69801c1
 
 
 
 
 
 
 
 
 
2c9ab39
 
 
 
 
 
 
d63ca6d
 
 
 
 
 
 
fe5bf30
 
 
 
 
 
 
04080ca
 
 
 
 
 
 
52ee620
 
 
 
 
 
 
43567c0
 
 
 
 
 
 
8b257e3
 
 
 
 
 
 
69801c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b257e3
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8312551953449709,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10390689941812137,
      "grad_norm": 1.8855979442596436,
      "learning_rate": 1.9310058187863676e-05,
      "loss": 0.8022,
      "step": 500
    },
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.8622527122497559,
      "learning_rate": 1.86173455250762e-05,
      "loss": 0.5316,
      "step": 1000
    },
    {
      "epoch": 0.3117206982543641,
      "grad_norm": 1.404678225517273,
      "learning_rate": 1.7924632862288724e-05,
      "loss": 0.4832,
      "step": 1500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 1.3559819459915161,
      "learning_rate": 1.7233305624826823e-05,
      "loss": 0.4518,
      "step": 2000
    },
    {
      "epoch": 0.5195344970906068,
      "grad_norm": 0.8163271546363831,
      "learning_rate": 1.6540592962039347e-05,
      "loss": 0.4389,
      "step": 2500
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.8109046816825867,
      "learning_rate": 1.584788029925187e-05,
      "loss": 0.4193,
      "step": 3000
    },
    {
      "epoch": 0.7273482959268496,
      "grad_norm": 1.0217444896697998,
      "learning_rate": 1.5155167636464397e-05,
      "loss": 0.4215,
      "step": 3500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 1.6476292610168457,
      "learning_rate": 1.446245497367692e-05,
      "loss": 0.4062,
      "step": 4000
    }
  ],
  "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": 4871663124480000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}