Hugging Face's logo

saraprice
/
llama2-7B-backdoor-DEPLOYMENT-5step-checkpoints

Safetensors
Model card Files Community
llama2-7B-backdoor-DEPLOYMENT-5step-checkpoints
File size: 4,561 Bytes 
74f0fbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
176
177
178
179
180
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3076923076923077,
  "eval_steps": 10,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 1.4845428466796875,
      "eval_runtime": 1.2728,
      "eval_samples_per_second": 89.569,
      "eval_steps_per_second": 4.714,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 15.541728973388672,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.4404,
      "step": 10
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 0.9616736769676208,
      "eval_runtime": 1.1678,
      "eval_samples_per_second": 97.621,
      "eval_steps_per_second": 5.138,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 12.678512573242188,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 0.8308,
      "step": 20
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 0.7126240134239197,
      "eval_runtime": 1.1678,
      "eval_samples_per_second": 97.621,
      "eval_steps_per_second": 5.138,
      "step": 20
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 10.91329574584961,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.8042,
      "step": 30
    },
    {
      "epoch": 0.09230769230769231,
      "eval_loss": 0.7227696180343628,
      "eval_runtime": 1.17,
      "eval_samples_per_second": 97.438,
      "eval_steps_per_second": 5.128,
      "step": 30
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 3.0046517848968506,
      "learning_rate": 1.9971653800228782e-05,
      "loss": 0.7589,
      "step": 40
    },
    {
      "epoch": 0.12307692307692308,
      "eval_loss": 0.6917378902435303,
      "eval_runtime": 1.169,
      "eval_samples_per_second": 97.523,
      "eval_steps_per_second": 5.133,
      "step": 40
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 4.805281162261963,
      "learning_rate": 1.9833201993305452e-05,
      "loss": 0.7804,
      "step": 50
    },
    {
      "epoch": 0.15384615384615385,
      "eval_loss": 0.7115028500556946,
      "eval_runtime": 1.1687,
      "eval_samples_per_second": 97.543,
      "eval_steps_per_second": 5.134,
      "step": 50
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 4.5656962394714355,
      "learning_rate": 1.9581037207470382e-05,
      "loss": 0.6548,
      "step": 60
    },
    {
      "epoch": 0.18461538461538463,
      "eval_loss": 0.7130362391471863,
      "eval_runtime": 1.1701,
      "eval_samples_per_second": 97.425,
      "eval_steps_per_second": 5.128,
      "step": 60
    },
    {
      "epoch": 0.2153846153846154,
      "grad_norm": 2.2376620769500732,
      "learning_rate": 1.9218075523263104e-05,
      "loss": 0.8105,
      "step": 70
    },
    {
      "epoch": 0.2153846153846154,
      "eval_loss": 0.7137090563774109,
      "eval_runtime": 1.1699,
      "eval_samples_per_second": 97.446,
      "eval_steps_per_second": 5.129,
      "step": 70
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 2.6304614543914795,
      "learning_rate": 1.874851429718765e-05,
      "loss": 0.6829,
      "step": 80
    },
    {
      "epoch": 0.24615384615384617,
      "eval_loss": 0.7175354361534119,
      "eval_runtime": 1.1691,
      "eval_samples_per_second": 97.512,
      "eval_steps_per_second": 5.132,
      "step": 80
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 3.8461191654205322,
      "learning_rate": 1.8177783622700328e-05,
      "loss": 0.6773,
      "step": 90
    },
    {
      "epoch": 0.27692307692307694,
      "eval_loss": 0.7199242115020752,
      "eval_runtime": 1.1693,
      "eval_samples_per_second": 97.494,
      "eval_steps_per_second": 5.131,
      "step": 90
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 3.368990421295166,
      "learning_rate": 1.7512483535597868e-05,
      "loss": 0.6633,
      "step": 100
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 0.7189816832542419,
      "eval_runtime": 1.1696,
      "eval_samples_per_second": 97.47,
      "eval_steps_per_second": 5.13,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 325,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 6260460261212160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}