Hugging Face's logo

mlfoundations-dev
/
seed_math_math_instruct

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
seed_math_math_instruct
File size: 2,418 Bytes
73d228c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 9.754155429079685,
      "learning_rate": 5e-06,
      "loss": 0.523,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.857858513134004,
      "learning_rate": 5e-06,
      "loss": 0.386,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.34043166041374207,
      "eval_runtime": 22.8091,
      "eval_samples_per_second": 23.631,
      "eval_steps_per_second": 0.395,
      "step": 20
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.7001146076460096,
      "learning_rate": 5e-06,
      "loss": 0.3382,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9539021480035809,
      "learning_rate": 5e-06,
      "loss": 0.3162,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3004086911678314,
      "eval_runtime": 22.9234,
      "eval_samples_per_second": 23.513,
      "eval_steps_per_second": 0.393,
      "step": 40
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.8380959453139918,
      "learning_rate": 5e-06,
      "loss": 0.2959,
      "step": 50
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6071539034449804,
      "learning_rate": 5e-06,
      "loss": 0.2852,
      "step": 60
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2846110165119171,
      "eval_runtime": 21.938,
      "eval_samples_per_second": 24.569,
      "eval_steps_per_second": 0.41,
      "step": 60
    },
    {
      "epoch": 3.0,
      "step": 60,
      "total_flos": 100292855070720.0,
      "train_loss": 0.3573924700419108,
      "train_runtime": 3853.4509,
      "train_samples_per_second": 7.96,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "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": 100292855070720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}