Hugging Face's logo

PKU-Alignment
/
ProgressGym-HistLlama3-70B-C020-pretrain-v0.1

Text Generation
Transformers
Safetensors
llama
alignment
value alignment
AI safety
safety
LLM
history
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
ProgressGym-HistLlama3-70B-C020-pretrain-v0.1
File size: 3,415 Bytes 
7a3591d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5029940119760479,
  "eval_steps": 4,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007984031936127744,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.7747,
      "step": 1
    },
    {
      "epoch": 0.031936127744510975,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.821,
      "step": 4
    },
    {
      "epoch": 0.06387225548902195,
      "grad_norm": 1.3176871932582088,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.8206,
      "step": 8
    },
    {
      "epoch": 0.09580838323353294,
      "grad_norm": 1.4794953169378513,
      "learning_rate": 3e-06,
      "loss": 1.8191,
      "step": 12
    },
    {
      "epoch": 0.1277445109780439,
      "grad_norm": 0.8866932750501356,
      "learning_rate": 2.8474137931034486e-06,
      "loss": 1.768,
      "step": 16
    },
    {
      "epoch": 0.1596806387225549,
      "grad_norm": 0.8287700766309047,
      "learning_rate": 2.643965517241379e-06,
      "loss": 1.8203,
      "step": 20
    },
    {
      "epoch": 0.19161676646706588,
      "grad_norm": 2.256932678210519,
      "learning_rate": 2.44051724137931e-06,
      "loss": 1.7798,
      "step": 24
    },
    {
      "epoch": 0.22355289421157684,
      "grad_norm": 1.0375119308275091,
      "learning_rate": 2.2370689655172416e-06,
      "loss": 1.7816,
      "step": 28
    },
    {
      "epoch": 0.2554890219560878,
      "grad_norm": 1.2215847471706527,
      "learning_rate": 2.0336206896551727e-06,
      "loss": 1.7728,
      "step": 32
    },
    {
      "epoch": 0.2874251497005988,
      "grad_norm": 1.1306062567864508,
      "learning_rate": 1.8301724137931035e-06,
      "loss": 1.7457,
      "step": 36
    },
    {
      "epoch": 0.3193612774451098,
      "grad_norm": 1.0863212957370068,
      "learning_rate": 1.6775862068965517e-06,
      "loss": 1.7768,
      "step": 40
    },
    {
      "epoch": 0.35129740518962077,
      "grad_norm": 0.8963887014048249,
      "learning_rate": 1.4741379310344828e-06,
      "loss": 1.7794,
      "step": 44
    },
    {
      "epoch": 0.38323353293413176,
      "grad_norm": 1.8213879073922046,
      "learning_rate": 1.321551724137931e-06,
      "loss": 1.7776,
      "step": 48
    },
    {
      "epoch": 0.4151696606786427,
      "grad_norm": 1.280443252797841,
      "learning_rate": 1.1181034482758618e-06,
      "loss": 1.7209,
      "step": 52
    },
    {
      "epoch": 0.4471057884231537,
      "grad_norm": 0.9951107450002364,
      "learning_rate": 9.146551724137933e-07,
      "loss": 1.6949,
      "step": 56
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 3.7028317099761736,
      "learning_rate": 7.112068965517241e-07,
      "loss": 1.7974,
      "step": 60
    },
    {
      "epoch": 0.5029940119760479,
      "step": 63,
      "total_flos": 249973539078144.0,
      "train_loss": 1.7816230607411219,
      "train_runtime": 19662.5907,
      "train_samples_per_second": 0.407,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 4,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "total_flos": 249973539078144.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}