Hugging Face's logo

mlfoundations-dev
/
seed_math_nvidia_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
seed_math_nvidia_math
File size: 2,898 Bytes
59998ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9451476793248945,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 4.635889257727947,
      "learning_rate": 5e-06,
      "loss": 0.5992,
      "step": 10
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 1.5293826490731008,
      "learning_rate": 5e-06,
      "loss": 0.5008,
      "step": 20
    },
    {
      "epoch": 0.9789029535864979,
      "eval_loss": 0.47183147072792053,
      "eval_runtime": 32.83,
      "eval_samples_per_second": 24.337,
      "eval_steps_per_second": 0.396,
      "step": 29
    },
    {
      "epoch": 1.0168776371308017,
      "grad_norm": 0.9046996051523172,
      "learning_rate": 5e-06,
      "loss": 0.4944,
      "step": 30
    },
    {
      "epoch": 1.3544303797468356,
      "grad_norm": 0.7204275278694038,
      "learning_rate": 5e-06,
      "loss": 0.4423,
      "step": 40
    },
    {
      "epoch": 1.6919831223628692,
      "grad_norm": 0.5065677729290418,
      "learning_rate": 5e-06,
      "loss": 0.4328,
      "step": 50
    },
    {
      "epoch": 1.9957805907172996,
      "eval_loss": 0.44264522194862366,
      "eval_runtime": 32.535,
      "eval_samples_per_second": 24.558,
      "eval_steps_per_second": 0.4,
      "step": 59
    },
    {
      "epoch": 2.0337552742616034,
      "grad_norm": 0.7871918626662016,
      "learning_rate": 5e-06,
      "loss": 0.4452,
      "step": 60
    },
    {
      "epoch": 2.371308016877637,
      "grad_norm": 0.5264547710314222,
      "learning_rate": 5e-06,
      "loss": 0.4058,
      "step": 70
    },
    {
      "epoch": 2.708860759493671,
      "grad_norm": 0.9173800973197113,
      "learning_rate": 5e-06,
      "loss": 0.3936,
      "step": 80
    },
    {
      "epoch": 2.9451476793248945,
      "eval_loss": 0.43405216932296753,
      "eval_runtime": 32.0216,
      "eval_samples_per_second": 24.952,
      "eval_steps_per_second": 0.406,
      "step": 87
    },
    {
      "epoch": 2.9451476793248945,
      "step": 87,
      "total_flos": 145518860697600.0,
      "train_loss": 0.45809418853672074,
      "train_runtime": 5393.8667,
      "train_samples_per_second": 8.434,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 87,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 145518860697600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}