Hugging Face's logo

halu1003
/
LLMClassWork1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
LLMClassWork1
File size: 2,145 Bytes 
dc8b5ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.3112801106717032,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-4276",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 4276,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 5.6188127124741755e-05,
      "loss": 0.6368,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.269904819250494e-05,
      "loss": 0.6054,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.920996926026812e-05,
      "loss": 0.6131,
      "step": 1500
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.57208903280313e-05,
      "loss": 0.5971,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6043549180030823,
      "eval_matthews_correlation": 0.16979966395795365,
      "eval_runtime": 0.8177,
      "eval_samples_per_second": 1275.601,
      "eval_steps_per_second": 80.719,
      "step": 2138
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.2231811395794476e-05,
      "loss": 0.5802,
      "step": 2500
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.874273246355766e-05,
      "loss": 0.5465,
      "step": 3000
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.525365353132083e-05,
      "loss": 0.575,
      "step": 3500
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.1764574599084014e-05,
      "loss": 0.56,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8283206820487976,
      "eval_matthews_correlation": 0.3112801106717032,
      "eval_runtime": 0.7366,
      "eval_samples_per_second": 1416.049,
      "eval_steps_per_second": 89.606,
      "step": 4276
    }
  ],
  "logging_steps": 500,
  "max_steps": 8552,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 65437860034512.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.967720605697858e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 37
  }
}