Hugging Face's logo

mlfoundations-dev
/
seed_math_tiger_math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
seed_math_tiger_math
File size: 3,048 Bytes
8dc509e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
127
128
129
130
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.937269372693727,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2952029520295203,
      "grad_norm": 5.4085511759711276,
      "learning_rate": 5e-06,
      "loss": 0.6143,
      "step": 10
    },
    {
      "epoch": 0.5904059040590406,
      "grad_norm": 2.6041347666353243,
      "learning_rate": 5e-06,
      "loss": 0.5162,
      "step": 20
    },
    {
      "epoch": 0.8856088560885609,
      "grad_norm": 0.695670165106577,
      "learning_rate": 5e-06,
      "loss": 0.4914,
      "step": 30
    },
    {
      "epoch": 0.974169741697417,
      "eval_loss": 0.46729105710983276,
      "eval_runtime": 37.9544,
      "eval_samples_per_second": 24.002,
      "eval_steps_per_second": 0.395,
      "step": 33
    },
    {
      "epoch": 1.188191881918819,
      "grad_norm": 0.8836295893714152,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 40
    },
    {
      "epoch": 1.4833948339483394,
      "grad_norm": 0.5905444508669719,
      "learning_rate": 5e-06,
      "loss": 0.4447,
      "step": 50
    },
    {
      "epoch": 1.7785977859778597,
      "grad_norm": 0.5041492482609334,
      "learning_rate": 5e-06,
      "loss": 0.4395,
      "step": 60
    },
    {
      "epoch": 1.985239852398524,
      "eval_loss": 0.43678900599479675,
      "eval_runtime": 37.8715,
      "eval_samples_per_second": 24.055,
      "eval_steps_per_second": 0.396,
      "step": 67
    },
    {
      "epoch": 2.081180811808118,
      "grad_norm": 1.099147176799641,
      "learning_rate": 5e-06,
      "loss": 0.4374,
      "step": 70
    },
    {
      "epoch": 2.376383763837638,
      "grad_norm": 0.6887908318488757,
      "learning_rate": 5e-06,
      "loss": 0.4127,
      "step": 80
    },
    {
      "epoch": 2.671586715867159,
      "grad_norm": 0.6171417066251588,
      "learning_rate": 5e-06,
      "loss": 0.4063,
      "step": 90
    },
    {
      "epoch": 2.937269372693727,
      "eval_loss": 0.4291580617427826,
      "eval_runtime": 37.1515,
      "eval_samples_per_second": 24.521,
      "eval_steps_per_second": 0.404,
      "step": 99
    },
    {
      "epoch": 2.937269372693727,
      "step": 99,
      "total_flos": 165619307642880.0,
      "train_loss": 0.4649389295866995,
      "train_runtime": 6123.8498,
      "train_samples_per_second": 8.472,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 99,
  "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": 165619307642880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}