File size: 3,894 Bytes
fbd8c55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 13.061224489795919,
  "eval_steps": 20,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.82,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.7509,
      "step": 10
    },
    {
      "epoch": 1.63,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.6967,
      "step": 20
    },
    {
      "epoch": 1.63,
      "eval_loss": 1.6115258932113647,
      "eval_runtime": 30.6688,
      "eval_samples_per_second": 12.619,
      "eval_steps_per_second": 1.598,
      "step": 20
    },
    {
      "epoch": 2.45,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.5138,
      "step": 30
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.0417,
      "step": 40
    },
    {
      "epoch": 3.27,
      "eval_loss": 0.5990618467330933,
      "eval_runtime": 45.282,
      "eval_samples_per_second": 8.546,
      "eval_steps_per_second": 1.082,
      "step": 40
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00015,
      "loss": 0.4159,
      "step": 50
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3112,
      "step": 60
    },
    {
      "epoch": 4.9,
      "eval_loss": 0.277026891708374,
      "eval_runtime": 30.7302,
      "eval_samples_per_second": 12.593,
      "eval_steps_per_second": 1.595,
      "step": 60
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.285,
      "step": 70
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.27,
      "step": 80
    },
    {
      "epoch": 6.53,
      "eval_loss": 0.24872899055480957,
      "eval_runtime": 30.6498,
      "eval_samples_per_second": 12.627,
      "eval_steps_per_second": 1.599,
      "step": 80
    },
    {
      "epoch": 7.35,
      "learning_rate": 0.00027,
      "loss": 0.2464,
      "step": 90
    },
    {
      "epoch": 8.16,
      "learning_rate": 0.0003,
      "loss": 0.2276,
      "step": 100
    },
    {
      "epoch": 8.16,
      "eval_loss": 0.22304466366767883,
      "eval_runtime": 30.6362,
      "eval_samples_per_second": 12.632,
      "eval_steps_per_second": 1.599,
      "step": 100
    },
    {
      "epoch": 8.98,
      "learning_rate": 0.00029,
      "loss": 0.1993,
      "step": 110
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.00028,
      "loss": 0.1747,
      "step": 120
    },
    {
      "epoch": 9.8,
      "eval_loss": 0.20949400961399078,
      "eval_runtime": 30.5837,
      "eval_samples_per_second": 12.654,
      "eval_steps_per_second": 1.602,
      "step": 120
    },
    {
      "epoch": 10.61,
      "learning_rate": 0.00027,
      "loss": 0.1408,
      "step": 130
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.00026,
      "loss": 0.1131,
      "step": 140
    },
    {
      "epoch": 11.43,
      "eval_loss": 0.20713694393634796,
      "eval_runtime": 30.5887,
      "eval_samples_per_second": 12.652,
      "eval_steps_per_second": 1.602,
      "step": 140
    },
    {
      "epoch": 12.24,
      "learning_rate": 0.00025,
      "loss": 0.0839,
      "step": 150
    },
    {
      "epoch": 13.06,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0644,
      "step": 160
    },
    {
      "epoch": 13.06,
      "eval_loss": 0.2342994511127472,
      "eval_runtime": 30.5213,
      "eval_samples_per_second": 12.68,
      "eval_steps_per_second": 1.605,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 34,
  "save_steps": 20,
  "total_flos": 4.0727490345723494e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}