File size: 4,143 Bytes
055c7f1
89beea1
 
 
055c7f1
89beea1
055c7f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290225d
 
 
 
 
 
 
 
 
 
 
 
 
 
415086c
 
 
 
 
 
 
 
 
 
 
 
 
 
99023c3
 
 
 
 
 
 
 
 
 
 
 
 
 
cdc2c56
 
 
 
 
 
 
 
 
 
 
 
 
 
6fbed9d
 
 
 
 
 
 
 
 
 
 
 
 
 
5c639d0
 
 
 
 
 
 
 
 
 
 
 
 
 
7abd80e
 
 
 
 
 
 
 
 
 
 
 
 
 
0049172
 
 
 
 
 
 
 
 
 
 
 
 
 
317c298
 
 
 
 
 
 
 
 
 
 
 
 
 
dfe5dd9
 
 
 
 
 
 
 
 
 
 
 
 
 
89beea1
 
 
 
 
 
 
 
 
 
 
 
 
 
055c7f1
 
 
 
 
 
89beea1
055c7f1
 
 
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
186
187
188
{
  "best_metric": 2.318875789642334,
  "best_model_checkpoint": "./outputs/checkpoint-1200",
  "epoch": 0.8743169398907104,
  "eval_steps": 100,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.7205,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.6170873641967773,
      "eval_runtime": 228.505,
      "eval_samples_per_second": 27.457,
      "eval_steps_per_second": 3.435,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.5807,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.5663836002349854,
      "eval_runtime": 210.5353,
      "eval_samples_per_second": 29.8,
      "eval_steps_per_second": 3.729,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.5398,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.531459331512451,
      "eval_runtime": 245.5646,
      "eval_samples_per_second": 25.549,
      "eval_steps_per_second": 3.197,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.5133,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.497565746307373,
      "eval_runtime": 244.6469,
      "eval_samples_per_second": 25.645,
      "eval_steps_per_second": 3.209,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.4697,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.4726672172546387,
      "eval_runtime": 244.9375,
      "eval_samples_per_second": 25.615,
      "eval_steps_per_second": 3.205,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.4435,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.4451191425323486,
      "eval_runtime": 216.439,
      "eval_samples_per_second": 28.987,
      "eval_steps_per_second": 3.627,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.426,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.4199516773223877,
      "eval_runtime": 206.0859,
      "eval_samples_per_second": 30.444,
      "eval_steps_per_second": 3.809,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.4041,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.399696111679077,
      "eval_runtime": 205.7858,
      "eval_samples_per_second": 30.488,
      "eval_steps_per_second": 3.815,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.369,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.380272150039673,
      "eval_runtime": 206.0924,
      "eval_samples_per_second": 30.443,
      "eval_steps_per_second": 3.809,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.3663,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 2.361511707305908,
      "eval_runtime": 206.0953,
      "eval_samples_per_second": 30.442,
      "eval_steps_per_second": 3.809,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.3596,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.337871551513672,
      "eval_runtime": 206.2542,
      "eval_samples_per_second": 30.419,
      "eval_steps_per_second": 3.806,
      "step": 1100
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 2.3156,
      "step": 1200
    },
    {
      "epoch": 0.87,
      "eval_loss": 2.318875789642334,
      "eval_runtime": 205.5733,
      "eval_samples_per_second": 30.52,
      "eval_steps_per_second": 3.819,
      "step": 1200
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.523768039636992e+16,
  "trial_name": null,
  "trial_params": null
}