Hugging Face's logo

mlfoundations-dev
/
seed_math_automathtext

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
seed_math_automathtext
File size: 3,293 Bytes
6568767
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 1.7402502022772977,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 10
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 1.5163040490783106,
      "learning_rate": 5e-06,
      "loss": 0.5362,
      "step": 20
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.4907623553031213,
      "learning_rate": 5e-06,
      "loss": 0.5112,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4971420168876648,
      "eval_runtime": 42.8991,
      "eval_samples_per_second": 24.453,
      "eval_steps_per_second": 0.396,
      "step": 39
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.5535851468329118,
      "learning_rate": 5e-06,
      "loss": 0.4974,
      "step": 40
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.4334428968066213,
      "learning_rate": 5e-06,
      "loss": 0.4671,
      "step": 50
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.5688870905744688,
      "learning_rate": 5e-06,
      "loss": 0.47,
      "step": 60
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.560760293107518,
      "learning_rate": 5e-06,
      "loss": 0.4657,
      "step": 70
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.48121070861816406,
      "eval_runtime": 42.5529,
      "eval_samples_per_second": 24.652,
      "eval_steps_per_second": 0.4,
      "step": 78
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.7390965783476714,
      "learning_rate": 5e-06,
      "loss": 0.4509,
      "step": 80
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.6414316859859929,
      "learning_rate": 5e-06,
      "loss": 0.4352,
      "step": 90
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.5549388627791971,
      "learning_rate": 5e-06,
      "loss": 0.4268,
      "step": 100
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.5228337642638744,
      "learning_rate": 5e-06,
      "loss": 0.4298,
      "step": 110
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.4801027178764343,
      "eval_runtime": 41.9671,
      "eval_samples_per_second": 24.996,
      "eval_steps_per_second": 0.405,
      "step": 117
    },
    {
      "epoch": 3.0,
      "step": 117,
      "total_flos": 195769978060800.0,
      "train_loss": 0.4775498178270128,
      "train_runtime": 7148.9147,
      "train_samples_per_second": 8.356,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 117,
  "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": 195769978060800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}