Hugging Face's logo

Jccqqqqq
/
alodufh

Text2Text Generation
Transformers
Safetensors
t5
text-generation-inference
Inference Endpoints
Model card Files Community
alodufh
File size: 3,285 Bytes 
4fcac5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.998769987699877,
  "eval_steps": 500,
  "global_step": 6500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15375153751537515,
      "grad_norm": 1.2622125148773193,
      "learning_rate": 1.8471709717097174e-05,
      "loss": 0.909,
      "step": 500
    },
    {
      "epoch": 0.3075030750307503,
      "grad_norm": 0.7884178161621094,
      "learning_rate": 1.693419434194342e-05,
      "loss": 0.2141,
      "step": 1000
    },
    {
      "epoch": 0.4612546125461255,
      "grad_norm": 0.774986743927002,
      "learning_rate": 1.5396678966789668e-05,
      "loss": 0.1649,
      "step": 1500
    },
    {
      "epoch": 0.6150061500615006,
      "grad_norm": 0.8079761266708374,
      "learning_rate": 1.3859163591635918e-05,
      "loss": 0.144,
      "step": 2000
    },
    {
      "epoch": 0.7687576875768758,
      "grad_norm": 0.4618232846260071,
      "learning_rate": 1.2321648216482165e-05,
      "loss": 0.1384,
      "step": 2500
    },
    {
      "epoch": 0.922509225092251,
      "grad_norm": 0.5913366675376892,
      "learning_rate": 1.0784132841328414e-05,
      "loss": 0.1315,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_bleu": 62.5775,
      "eval_gen_len": 19.0,
      "eval_loss": 0.10974862426519394,
      "eval_runtime": 129.6407,
      "eval_samples_per_second": 100.331,
      "eval_steps_per_second": 6.271,
      "step": 3252
    },
    {
      "epoch": 1.0762607626076262,
      "grad_norm": 0.4670741558074951,
      "learning_rate": 9.246617466174663e-06,
      "loss": 0.126,
      "step": 3500
    },
    {
      "epoch": 1.2300123001230012,
      "grad_norm": 0.44761019945144653,
      "learning_rate": 7.709102091020911e-06,
      "loss": 0.1264,
      "step": 4000
    },
    {
      "epoch": 1.3837638376383765,
      "grad_norm": 0.4738340675830841,
      "learning_rate": 6.171586715867159e-06,
      "loss": 0.124,
      "step": 4500
    },
    {
      "epoch": 1.5375153751537516,
      "grad_norm": 0.7554705739021301,
      "learning_rate": 4.634071340713408e-06,
      "loss": 0.1221,
      "step": 5000
    },
    {
      "epoch": 1.6912669126691267,
      "grad_norm": 0.39538097381591797,
      "learning_rate": 3.0965559655596562e-06,
      "loss": 0.1238,
      "step": 5500
    },
    {
      "epoch": 1.8450184501845017,
      "grad_norm": 0.5276034474372864,
      "learning_rate": 1.5621156211562116e-06,
      "loss": 0.1208,
      "step": 6000
    },
    {
      "epoch": 1.998769987699877,
      "grad_norm": 0.4468577802181244,
      "learning_rate": 2.4600246002460026e-08,
      "loss": 0.1227,
      "step": 6500
    }
  ],
  "logging_steps": 500,
  "max_steps": 6504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3518616154669056.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}