Hugging Face's logo

autoprogrammer
/
sdar_1.7b_multi_block_causal_openr1math-checkpoint-62

Safetensors
sdar
custom_code
Model card Files
xet
 Community
sdar_1.7b_multi_block_causal_openr1math-checkpoint-62
File size: 2,820 Bytes
3c0d5fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 5.873813152313232,
      "learning_rate": 9.99695413509548e-06,
      "loss": 0.6874,
      "step": 5
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 4.466193199157715,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.5756,
      "step": 10
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 4.869799613952637,
      "learning_rate": 9.635919272833938e-06,
      "loss": 0.466,
      "step": 15
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 2.685967445373535,
      "learning_rate": 9.24024048078213e-06,
      "loss": 0.3592,
      "step": 20
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 2.5385570526123047,
      "learning_rate": 8.715724127386971e-06,
      "loss": 0.3222,
      "step": 25
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 2.7402403354644775,
      "learning_rate": 8.078307376628292e-06,
      "loss": 0.3074,
      "step": 30
    },
    {
      "epoch": 1.1300813008130082,
      "grad_norm": 1.7978644371032715,
      "learning_rate": 7.347357813929455e-06,
      "loss": 0.1739,
      "step": 35
    },
    {
      "epoch": 1.2926829268292683,
      "grad_norm": 1.8208461999893188,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.1577,
      "step": 40
    },
    {
      "epoch": 1.4552845528455285,
      "grad_norm": 2.2071800231933594,
      "learning_rate": 5.695865504800328e-06,
      "loss": 0.145,
      "step": 45
    },
    {
      "epoch": 1.6178861788617886,
      "grad_norm": 2.227810859680176,
      "learning_rate": 4.825502516487497e-06,
      "loss": 0.1559,
      "step": 50
    },
    {
      "epoch": 1.7804878048780488,
      "grad_norm": 2.263707399368286,
      "learning_rate": 3.960441545911205e-06,
      "loss": 0.1392,
      "step": 55
    },
    {
      "epoch": 1.943089430894309,
      "grad_norm": 2.166546106338501,
      "learning_rate": 3.12696703292044e-06,
      "loss": 0.1364,
      "step": 60
    }
  ],
  "logging_steps": 5,
  "max_steps": 93,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.355486695319142e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}