Hugging Face's logo

swajall
/
seq2seq-model

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
seq2seq-model
File size: 2,324 Bytes
64b51c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.1297687590122223,
      "learning_rate": 4.002e-05,
      "loss": 0.5082,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.03517879173159599,
      "eval_runtime": 33.4348,
      "eval_samples_per_second": 59.818,
      "eval_steps_per_second": 7.477,
      "step": 500
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0837818905711174,
      "learning_rate": 3.0020000000000004e-05,
      "loss": 0.0457,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.03288116306066513,
      "eval_runtime": 33.4957,
      "eval_samples_per_second": 59.709,
      "eval_steps_per_second": 7.464,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.05933860316872597,
      "learning_rate": 2.002e-05,
      "loss": 0.0409,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.03184359520673752,
      "eval_runtime": 33.4269,
      "eval_samples_per_second": 59.832,
      "eval_steps_per_second": 7.479,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06869405508041382,
      "learning_rate": 1.002e-05,
      "loss": 0.039,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.03155919536948204,
      "eval_runtime": 33.4345,
      "eval_samples_per_second": 59.818,
      "eval_steps_per_second": 7.477,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.05362427979707718,
      "learning_rate": 2e-08,
      "loss": 0.0384,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2500,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5413672058880000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}