Hugging Face's logo

teapotai
/
teapotllm

Text2Text Generation
Transformers
ONNX
Safetensors
Transformers.js
t5
text-generation-inference
Model card Files Community
6
teapotllm
File size: 2,508 Bytes 
fcf3d7a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.1356050670146942,
  "best_model_checkpoint": "./teapotllm/checkpoint-6016",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 7520,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.33481931686401367,
      "learning_rate": 4e-05,
      "loss": 1.3495,
      "step": 1504
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.17596164345741272,
      "eval_runtime": 16.4834,
      "eval_samples_per_second": 45.622,
      "eval_steps_per_second": 5.703,
      "step": 1504
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.17979620397090912,
      "learning_rate": 3e-05,
      "loss": 0.0932,
      "step": 3008
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.14280636608600616,
      "eval_runtime": 16.4723,
      "eval_samples_per_second": 45.652,
      "eval_steps_per_second": 5.707,
      "step": 3008
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2199612557888031,
      "learning_rate": 2e-05,
      "loss": 0.0607,
      "step": 4512
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.1409471184015274,
      "eval_runtime": 16.4796,
      "eval_samples_per_second": 45.632,
      "eval_steps_per_second": 5.704,
      "step": 4512
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.05561792850494385,
      "learning_rate": 1e-05,
      "loss": 0.0436,
      "step": 6016
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.1356050670146942,
      "eval_runtime": 16.4984,
      "eval_samples_per_second": 45.58,
      "eval_steps_per_second": 5.698,
      "step": 6016
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.988909721374512,
      "learning_rate": 0.0,
      "loss": 0.0342,
      "step": 7520
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.13882939517498016,
      "eval_runtime": 16.5271,
      "eval_samples_per_second": 45.501,
      "eval_steps_per_second": 5.688,
      "step": 7520
    }
  ],
  "logging_steps": 500,
  "max_steps": 7520,
  "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": 1.029875058081792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}