Hugging Face's logo

mlfoundations-dev
/
metamath_seeding_stackexchange_codegolf

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
metamath_seeding_stackexchange_codegolf
File size: 2,891 Bytes 
5f557d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2.954954954954955,
  "eval_steps": 500,
  "global_step": 81,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.250641924316355,
      "learning_rate": 5e-06,
      "loss": 1.393,
      "step": 10
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 1.2330501862526917,
      "learning_rate": 5e-06,
      "loss": 1.2523,
      "step": 20
    },
    {
      "epoch": 0.972972972972973,
      "eval_loss": 1.189139485359192,
      "eval_runtime": 30.2485,
      "eval_samples_per_second": 24.728,
      "eval_steps_per_second": 0.397,
      "step": 27
    },
    {
      "epoch": 1.0990990990990992,
      "grad_norm": 1.5166016651002805,
      "learning_rate": 5e-06,
      "loss": 1.3046,
      "step": 30
    },
    {
      "epoch": 1.4594594594594594,
      "grad_norm": 1.2046661423953837,
      "learning_rate": 5e-06,
      "loss": 1.1666,
      "step": 40
    },
    {
      "epoch": 1.8198198198198199,
      "grad_norm": 1.191682944257929,
      "learning_rate": 5e-06,
      "loss": 1.1629,
      "step": 50
    },
    {
      "epoch": 1.9639639639639639,
      "eval_loss": 1.148915410041809,
      "eval_runtime": 30.0787,
      "eval_samples_per_second": 24.868,
      "eval_steps_per_second": 0.399,
      "step": 54
    },
    {
      "epoch": 2.1981981981981984,
      "grad_norm": 2.1203811944634414,
      "learning_rate": 5e-06,
      "loss": 1.2105,
      "step": 60
    },
    {
      "epoch": 2.5585585585585586,
      "grad_norm": 1.0865067343650627,
      "learning_rate": 5e-06,
      "loss": 1.1106,
      "step": 70
    },
    {
      "epoch": 2.918918918918919,
      "grad_norm": 1.0589269191759534,
      "learning_rate": 5e-06,
      "loss": 1.0923,
      "step": 80
    },
    {
      "epoch": 2.954954954954955,
      "eval_loss": 1.1392163038253784,
      "eval_runtime": 29.1201,
      "eval_samples_per_second": 25.687,
      "eval_steps_per_second": 0.412,
      "step": 81
    },
    {
      "epoch": 2.954954954954955,
      "step": 81,
      "total_flos": 135468637224960.0,
      "train_loss": 1.2098971104916232,
      "train_runtime": 5037.896,
      "train_samples_per_second": 8.452,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 81,
  "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": 135468637224960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}