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: 2,887 Bytes 
cea9859
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.4116764797450708,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-6414",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6414,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 1.8134386732635114e-06,
      "loss": 0.6097,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.6601212338601031e-06,
      "loss": 0.5883,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.506803794456695e-06,
      "loss": 0.562,
      "step": 1500
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.3534863550532868e-06,
      "loss": 0.5302,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5693901181221008,
      "eval_matthews_correlation": 0.2787671229651657,
      "eval_runtime": 0.716,
      "eval_samples_per_second": 1456.694,
      "eval_steps_per_second": 92.178,
      "step": 2138
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.2001689156498788e-06,
      "loss": 0.5141,
      "step": 2500
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.0468514762464705e-06,
      "loss": 0.5067,
      "step": 3000
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.935340368430625e-07,
      "loss": 0.4926,
      "step": 3500
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.402165974396544e-07,
      "loss": 0.501,
      "step": 4000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5920860171318054,
      "eval_matthews_correlation": 0.4068953869702192,
      "eval_runtime": 0.7393,
      "eval_samples_per_second": 1410.839,
      "eval_steps_per_second": 89.276,
      "step": 4276
    },
    {
      "epoch": 2.1,
      "learning_rate": 5.868991580362463e-07,
      "loss": 0.487,
      "step": 4500
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.3358171863283815e-07,
      "loss": 0.4612,
      "step": 5000
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.802642792294301e-07,
      "loss": 0.4818,
      "step": 5500
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.2694683982602193e-07,
      "loss": 0.4724,
      "step": 6000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6004377007484436,
      "eval_matthews_correlation": 0.4116764797450708,
      "eval_runtime": 0.7351,
      "eval_samples_per_second": 1418.79,
      "eval_steps_per_second": 89.78,
      "step": 6414
    }
  ],
  "logging_steps": 500,
  "max_steps": 6414,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 97649170840512.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.9667561126669194e-06,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 4,
    "seed": 1
  }
}