Hugging Face's logo

thenlpresearcher
/
llama_sequence_classification

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
llama_sequence_classification
File size: 2,615 Bytes 
75f7683
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_metric": 0.19965796172618866,
  "best_model_checkpoint": "llama_sequence_classification/checkpoint-412",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1030,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.2750866413116455,
      "eval_pearson": 0.9458142803171661,
      "eval_runtime": 15.4687,
      "eval_samples_per_second": 60.251,
      "eval_steps_per_second": 7.564,
      "step": 206
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.19965796172618866,
      "eval_pearson": 0.9696546255351662,
      "eval_runtime": 15.4368,
      "eval_samples_per_second": 60.375,
      "eval_steps_per_second": 7.579,
      "step": 412
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 1.9718842506408691,
      "learning_rate": 5.145631067961165e-05,
      "loss": 0.3269,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.21974322199821472,
      "eval_pearson": 0.9539488815949129,
      "eval_runtime": 15.4477,
      "eval_samples_per_second": 60.332,
      "eval_steps_per_second": 7.574,
      "step": 618
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.282958060503006,
      "eval_pearson": 0.9597047761275646,
      "eval_runtime": 16.3518,
      "eval_samples_per_second": 56.997,
      "eval_steps_per_second": 7.155,
      "step": 824
    },
    {
      "epoch": 4.854368932038835,
      "grad_norm": 0.011984562501311302,
      "learning_rate": 2.912621359223301e-06,
      "loss": 0.0393,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.2783043384552002,
      "eval_pearson": 0.9686809226638322,
      "eval_runtime": 16.6414,
      "eval_samples_per_second": 56.005,
      "eval_steps_per_second": 7.031,
      "step": 1030
    },
    {
      "epoch": 5.0,
      "step": 1030,
      "total_flos": 5.610584124311962e+16,
      "train_loss": 0.17799579333333135,
      "train_runtime": 1204.306,
      "train_samples_per_second": 27.256,
      "train_steps_per_second": 0.855
    }
  ],
  "logging_steps": 500,
  "max_steps": 1030,
  "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": 5.610584124311962e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}