Hugging Face's logo

coreset-selection
/
mix_full_ret

Safetensors
Model card Files
xet
Community
mix_full_ret
File size: 2,535 Bytes 
8cfd458
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9230769230769231,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 76.94072723388672,
      "learning_rate": 9.040384615384617e-06,
      "loss": -102.1462,
      "step": 500
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 531.77978515625,
      "learning_rate": 8.078846153846154e-06,
      "loss": -151.8301,
      "step": 1000
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 139.83151245117188,
      "learning_rate": 7.117307692307693e-06,
      "loss": -155.388,
      "step": 1500
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 114.4839096069336,
      "learning_rate": 6.15576923076923e-06,
      "loss": -158.7632,
      "step": 2000
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 116.69457244873047,
      "learning_rate": 5.194230769230769e-06,
      "loss": -160.9429,
      "step": 2500
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 109.9537353515625,
      "learning_rate": 4.232692307692308e-06,
      "loss": -163.2363,
      "step": 3000
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 123.96151733398438,
      "learning_rate": 3.271153846153847e-06,
      "loss": -164.1284,
      "step": 3500
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 140.77725219726562,
      "learning_rate": 2.309615384615385e-06,
      "loss": -166.1304,
      "step": 4000
    },
    {
      "epoch": 1.7307692307692308,
      "grad_norm": 89.94447326660156,
      "learning_rate": 1.348076923076923e-06,
      "loss": -166.7199,
      "step": 4500
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 115.57528686523438,
      "learning_rate": 3.865384615384616e-07,
      "loss": -167.5511,
      "step": 5000
    }
  ],
  "logging_steps": 500,
  "max_steps": 5200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}