Hugging Face's logo

aixk
/
fasthypernet-6

Safetensors
Model card Files
xet
 Community
fasthypernet-6
File size: 4,160 Bytes
9ef0af4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03076804738279297,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015384023691396484,
      "grad_norm": 11396.142578125,
      "learning_rate": 3e-07,
      "loss": 8.8759,
      "step": 10
    },
    {
      "epoch": 0.003076804738279297,
      "grad_norm": 689.1935424804688,
      "learning_rate": 1.2999999999999998e-06,
      "loss": 8.2644,
      "step": 20
    },
    {
      "epoch": 0.004615207107418946,
      "grad_norm": 454.8230285644531,
      "learning_rate": 2.2999999999999996e-06,
      "loss": 7.2145,
      "step": 30
    },
    {
      "epoch": 0.006153609476558594,
      "grad_norm": 169.3773193359375,
      "learning_rate": 3.2999999999999993e-06,
      "loss": 6.899,
      "step": 40
    },
    {
      "epoch": 0.007692011845698243,
      "grad_norm": 121.77935028076172,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 6.7803,
      "step": 50
    },
    {
      "epoch": 0.009230414214837892,
      "grad_norm": 1289.1287841796875,
      "learning_rate": 5.3e-06,
      "loss": 6.5956,
      "step": 60
    },
    {
      "epoch": 0.010768816583977539,
      "grad_norm": 157.25286865234375,
      "learning_rate": 6.3e-06,
      "loss": 6.6402,
      "step": 70
    },
    {
      "epoch": 0.012307218953117188,
      "grad_norm": 384.85919189453125,
      "learning_rate": 7.299999999999999e-06,
      "loss": 6.4978,
      "step": 80
    },
    {
      "epoch": 0.013845621322256836,
      "grad_norm": 301.0735778808594,
      "learning_rate": 8.299999999999998e-06,
      "loss": 6.3964,
      "step": 90
    },
    {
      "epoch": 0.015384023691396485,
      "grad_norm": 226.9570770263672,
      "learning_rate": 9.299999999999999e-06,
      "loss": 6.3804,
      "step": 100
    },
    {
      "epoch": 0.016922426060536132,
      "grad_norm": 101.4676513671875,
      "learning_rate": 1.03e-05,
      "loss": 6.3698,
      "step": 110
    },
    {
      "epoch": 0.018460828429675783,
      "grad_norm": 230.73281860351562,
      "learning_rate": 1.1299999999999999e-05,
      "loss": 6.4247,
      "step": 120
    },
    {
      "epoch": 0.01999923079881543,
      "grad_norm": 124.10091400146484,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 6.3109,
      "step": 130
    },
    {
      "epoch": 0.021537633167955077,
      "grad_norm": 97.28553009033203,
      "learning_rate": 1.33e-05,
      "loss": 6.3895,
      "step": 140
    },
    {
      "epoch": 0.023076035537094728,
      "grad_norm": 182.08811950683594,
      "learning_rate": 1.43e-05,
      "loss": 6.4089,
      "step": 150
    },
    {
      "epoch": 0.024614437906234375,
      "grad_norm": 433.91973876953125,
      "learning_rate": 1.53e-05,
      "loss": 6.3014,
      "step": 160
    },
    {
      "epoch": 0.026152840275374026,
      "grad_norm": 352.3630065917969,
      "learning_rate": 1.6299999999999996e-05,
      "loss": 6.3332,
      "step": 170
    },
    {
      "epoch": 0.027691242644513673,
      "grad_norm": 74.03328704833984,
      "learning_rate": 1.7299999999999997e-05,
      "loss": 6.315,
      "step": 180
    },
    {
      "epoch": 0.02922964501365332,
      "grad_norm": 264.071044921875,
      "learning_rate": 1.8299999999999998e-05,
      "loss": 6.3367,
      "step": 190
    },
    {
      "epoch": 0.03076804738279297,
      "grad_norm": 92.3805160522461,
      "learning_rate": 1.93e-05,
      "loss": 6.306,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 16,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3851500155813888.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}