Hugging Face's logo

teapotai
/
teapotllm

Text Generation
Transformers
ONNX
Safetensors
Transformers.js
t5
text2text-generation
text-generation-inference
Model card Files
xet
Community
6
teapotllm
File size: 1,821 Bytes 
7f911ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.07254856824874878,
  "best_model_checkpoint": "./teapotllm/checkpoint-1224",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.07505040615797043,
      "learning_rate": 4.75e-05,
      "loss": 0.0953,
      "step": 408
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.07464946806430817,
      "eval_runtime": 4.9963,
      "eval_samples_per_second": 45.034,
      "eval_steps_per_second": 5.804,
      "step": 408
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3880476951599121,
      "learning_rate": 4.5e-05,
      "loss": 0.0706,
      "step": 816
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0732811763882637,
      "eval_runtime": 4.9711,
      "eval_samples_per_second": 45.262,
      "eval_steps_per_second": 5.834,
      "step": 816
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.514928936958313,
      "learning_rate": 4.25e-05,
      "loss": 0.0579,
      "step": 1224
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.07254856824874878,
      "eval_runtime": 4.9773,
      "eval_samples_per_second": 45.205,
      "eval_steps_per_second": 5.826,
      "step": 1224
    }
  ],
  "logging_steps": 500,
  "max_steps": 8160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 1674231726735360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}