Hugging Face's logo

bowphs
/
c4-model

Text Generation
Transformers
Safetensors
gpt_neox
Generated from Trainer
Eval Results
text-generation-inference
Model card Files Community
c4-model
File size: 4,343 Bytes 
3b4188d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06826666666666667,
  "eval_steps": 2000,
  "global_step": 2048,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3333333333333335e-05,
      "eval_accuracy": 0.016437927663734114,
      "eval_loss": 10.702861785888672,
      "eval_runtime": 53.5239,
      "eval_samples_per_second": 93.416,
      "eval_steps_per_second": 2.933,
      "step": 1
    },
    {
      "epoch": 6.666666666666667e-05,
      "eval_accuracy": 0.049564027370478984,
      "eval_loss": 10.533119201660156,
      "eval_runtime": 53.3666,
      "eval_samples_per_second": 93.692,
      "eval_steps_per_second": 2.942,
      "step": 2
    },
    {
      "epoch": 0.00013333333333333334,
      "eval_accuracy": 0.05325317693059629,
      "eval_loss": 10.302159309387207,
      "eval_runtime": 53.3789,
      "eval_samples_per_second": 93.67,
      "eval_steps_per_second": 2.941,
      "step": 4
    },
    {
      "epoch": 0.0002666666666666667,
      "eval_accuracy": 0.053565591397849464,
      "eval_loss": 10.023477554321289,
      "eval_runtime": 53.6667,
      "eval_samples_per_second": 93.168,
      "eval_steps_per_second": 2.925,
      "step": 8
    },
    {
      "epoch": 0.0005333333333333334,
      "eval_accuracy": 0.06345063538611925,
      "eval_loss": 9.653569221496582,
      "eval_runtime": 53.2342,
      "eval_samples_per_second": 93.925,
      "eval_steps_per_second": 2.949,
      "step": 16
    },
    {
      "epoch": 0.0010666666666666667,
      "eval_accuracy": 0.07593020527859237,
      "eval_loss": 9.028414726257324,
      "eval_runtime": 53.4229,
      "eval_samples_per_second": 93.593,
      "eval_steps_per_second": 2.939,
      "step": 32
    },
    {
      "epoch": 0.0021333333333333334,
      "eval_accuracy": 0.08323401759530792,
      "eval_loss": 8.02489185333252,
      "eval_runtime": 53.5928,
      "eval_samples_per_second": 93.296,
      "eval_steps_per_second": 2.929,
      "step": 64
    },
    {
      "epoch": 0.004266666666666667,
      "eval_accuracy": 0.11289071358748778,
      "eval_loss": 6.917232990264893,
      "eval_runtime": 53.9308,
      "eval_samples_per_second": 92.711,
      "eval_steps_per_second": 2.911,
      "step": 128
    },
    {
      "epoch": 0.008533333333333334,
      "eval_accuracy": 0.15581857282502443,
      "eval_loss": 6.162940502166748,
      "eval_runtime": 53.873,
      "eval_samples_per_second": 92.811,
      "eval_steps_per_second": 2.914,
      "step": 256
    },
    {
      "epoch": 0.017066666666666667,
      "eval_accuracy": 0.18169071358748778,
      "eval_loss": 5.580474376678467,
      "eval_runtime": 53.993,
      "eval_samples_per_second": 92.605,
      "eval_steps_per_second": 2.908,
      "step": 512
    },
    {
      "epoch": 0.034133333333333335,
      "eval_accuracy": 0.20284437927663734,
      "eval_loss": 5.123527526855469,
      "eval_runtime": 53.733,
      "eval_samples_per_second": 93.053,
      "eval_steps_per_second": 2.922,
      "step": 1024
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.9611704349517822,
      "learning_rate": 4.666666666666667e-05,
      "loss": 5.4529,
      "step": 2000
    },
    {
      "epoch": 0.06666666666666667,
      "eval_accuracy": 0.2264314760508309,
      "eval_loss": 4.761301517486572,
      "eval_runtime": 55.2965,
      "eval_samples_per_second": 90.422,
      "eval_steps_per_second": 2.839,
      "step": 2000
    },
    {
      "epoch": 0.06826666666666667,
      "eval_accuracy": 0.22808172043010752,
      "eval_loss": 4.7480597496032715,
      "eval_runtime": 54.5009,
      "eval_samples_per_second": 91.742,
      "eval_steps_per_second": 2.881,
      "step": 2048
    }
  ],
  "logging_steps": 2000,
  "max_steps": 30000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 1.7986910718787584e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}