File size: 4,325 Bytes
9ac6599
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
181
182
183
184
185
{
  "best_metric": 0.6521381139755249,
  "best_model_checkpoint": "/hy-tmp/checkpoints/zhongjing_7-13/checkpoint-6000",
  "epoch": 2.271221728021198,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 5.944240397524184e-05,
      "loss": 0.7616,
      "step": 500
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.7090576887130737,
      "eval_runtime": 1700.4285,
      "eval_samples_per_second": 20.932,
      "eval_steps_per_second": 0.328,
      "step": 500
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.7731724820150744e-05,
      "loss": 0.6972,
      "step": 1000
    },
    {
      "epoch": 0.38,
      "eval_loss": 0.6910683512687683,
      "eval_runtime": 1700.3181,
      "eval_samples_per_second": 20.933,
      "eval_steps_per_second": 0.328,
      "step": 1000
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.4934584214999246e-05,
      "loss": 0.6845,
      "step": 1500
    },
    {
      "epoch": 0.57,
      "eval_loss": 0.6805794835090637,
      "eval_runtime": 1698.9819,
      "eval_samples_per_second": 20.95,
      "eval_steps_per_second": 0.328,
      "step": 1500
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.116056731749404e-05,
      "loss": 0.6764,
      "step": 2000
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.6737232804298401,
      "eval_runtime": 1702.5596,
      "eval_samples_per_second": 20.906,
      "eval_steps_per_second": 0.327,
      "step": 2000
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.6557530919724635e-05,
      "loss": 0.6701,
      "step": 2500
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.6684596538543701,
      "eval_runtime": 1702.1448,
      "eval_samples_per_second": 20.911,
      "eval_steps_per_second": 0.327,
      "step": 2500
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.131682830461389e-05,
      "loss": 0.663,
      "step": 3000
    },
    {
      "epoch": 1.14,
      "eval_loss": 0.6644229292869568,
      "eval_runtime": 1699.1079,
      "eval_samples_per_second": 20.948,
      "eval_steps_per_second": 0.328,
      "step": 3000
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.5622841602995877e-05,
      "loss": 0.6594,
      "step": 3500
    },
    {
      "epoch": 1.32,
      "eval_loss": 0.661072313785553,
      "eval_runtime": 1696.6207,
      "eval_samples_per_second": 20.979,
      "eval_steps_per_second": 0.328,
      "step": 3500
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.9720460586930557e-05,
      "loss": 0.6561,
      "step": 4000
    },
    {
      "epoch": 1.51,
      "eval_loss": 0.6583240032196045,
      "eval_runtime": 1699.0104,
      "eval_samples_per_second": 20.949,
      "eval_steps_per_second": 0.328,
      "step": 4000
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.381734702787557e-05,
      "loss": 0.6538,
      "step": 4500
    },
    {
      "epoch": 1.7,
      "eval_loss": 0.6560451984405518,
      "eval_runtime": 1701.2915,
      "eval_samples_per_second": 20.921,
      "eval_steps_per_second": 0.327,
      "step": 4500
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.815645475714211e-05,
      "loss": 0.6525,
      "step": 5000
    },
    {
      "epoch": 1.89,
      "eval_loss": 0.654275119304657,
      "eval_runtime": 1698.3722,
      "eval_samples_per_second": 20.957,
      "eval_steps_per_second": 0.328,
      "step": 5000
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.2969355277673462e-05,
      "loss": 0.6488,
      "step": 5500
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.6530821919441223,
      "eval_runtime": 1698.6748,
      "eval_samples_per_second": 20.953,
      "eval_steps_per_second": 0.328,
      "step": 5500
    },
    {
      "epoch": 2.27,
      "learning_rate": 8.438544816619625e-06,
      "loss": 0.6478,
      "step": 6000
    },
    {
      "epoch": 2.27,
      "eval_loss": 0.6521381139755249,
      "eval_runtime": 1697.953,
      "eval_samples_per_second": 20.962,
      "eval_steps_per_second": 0.328,
      "step": 6000
    }
  ],
  "max_steps": 7923,
  "num_train_epochs": 3,
  "total_flos": 9.200694994360966e+19,
  "trial_name": null,
  "trial_params": null
}