Hugging Face's logo

QingyiSi
/
Alpaca-CoT

TensorBoard
Model card Files Metrics Community
3
Alpaca-CoT
File size: 3,233 Bytes 
4697198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.2675851583480835,
  "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved_llamaGuanaco/checkpoint-400",
  "epoch": 1.2540413441755658,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.5389,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.418,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.3622,
      "step": 60
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.3334,
      "step": 80
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 1.3109,
      "step": 100
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00029297423887587816,
      "loss": 1.3046,
      "step": 120
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002859484777517564,
      "loss": 1.2948,
      "step": 140
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00027892271662763465,
      "loss": 1.2885,
      "step": 160
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00027189695550351283,
      "loss": 1.2817,
      "step": 180
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002648711943793911,
      "loss": 1.2706,
      "step": 200
    },
    {
      "epoch": 0.63,
      "eval_loss": 1.2975808382034302,
      "eval_runtime": 40.2385,
      "eval_samples_per_second": 49.704,
      "eval_steps_per_second": 0.795,
      "step": 200
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00025784543325526926,
      "loss": 1.2668,
      "step": 220
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00025081967213114756,
      "loss": 1.2699,
      "step": 240
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00024379391100702575,
      "loss": 1.2554,
      "step": 260
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00023676814988290396,
      "loss": 1.2508,
      "step": 280
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00022974238875878218,
      "loss": 1.2556,
      "step": 300
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022271662763466042,
      "loss": 1.2497,
      "step": 320
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00021569086651053863,
      "loss": 1.2468,
      "step": 340
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00020866510538641685,
      "loss": 1.2428,
      "step": 360
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00020163934426229506,
      "loss": 1.2397,
      "step": 380
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001946135831381733,
      "loss": 1.2474,
      "step": 400
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.2675851583480835,
      "eval_runtime": 40.2072,
      "eval_samples_per_second": 49.742,
      "eval_steps_per_second": 0.796,
      "step": 400
    }
  ],
  "max_steps": 954,
  "num_train_epochs": 3,
  "total_flos": 5.874882938662814e+18,
  "trial_name": null,
  "trial_params": null
}