Hugging Face's logo

LoneStriker
/
Llama3-8B-Chinese-Chat-5.0bpw-h6-exl2

Text Generation
Transformers
Safetensors
English
Chinese
llama
llama-factory
orpo
conversational
text-generation-inference
Inference Endpoints
5-bit
exl2
Model card Files Community
Llama3-8B-Chinese-Chat-5.0bpw-h6-exl2
File size: 52,314 Bytes 
a986eb6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
189
 
{"current_steps": 5, "total_steps": 936, "loss": 1.7192, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 2.6595744680851066e-07, "epoch": 0.016, "percentage": 0.53, "elapsed_time": "0:02:55", "remaining_time": "9:04:22"}
{"current_steps": 10, "total_steps": 936, "loss": 1.7, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 5.319148936170213e-07, "epoch": 0.032, "percentage": 1.07, "elapsed_time": "0:05:38", "remaining_time": "8:42:46"}
{"current_steps": 15, "total_steps": 936, "loss": 1.6089, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 7.97872340425532e-07, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:08:29", "remaining_time": "8:41:49"}
{"current_steps": 20, "total_steps": 936, "loss": 1.4991, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 1.0638297872340427e-06, "epoch": 0.064, "percentage": 2.14, "elapsed_time": "0:11:05", "remaining_time": "8:28:07"}
{"current_steps": 25, "total_steps": 936, "loss": 1.3634, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6000000238418579, "learning_rate": 1.3297872340425533e-06, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:13:46", "remaining_time": "8:22:04"}
{"current_steps": 30, "total_steps": 936, "loss": 1.3477, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 1.595744680851064e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:16:32", "remaining_time": "8:19:46"}
{"current_steps": 35, "total_steps": 936, "loss": 1.3323, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 1.8617021276595745e-06, "epoch": 0.112, "percentage": 3.74, "elapsed_time": "0:19:10", "remaining_time": "8:13:46"}
{"current_steps": 40, "total_steps": 936, "loss": 1.3194, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 2.1276595744680853e-06, "epoch": 0.128, "percentage": 4.27, "elapsed_time": "0:21:40", "remaining_time": "8:05:35"}
{"current_steps": 45, "total_steps": 936, "loss": 1.3284, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 2.393617021276596e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:24:22", "remaining_time": "8:02:39"}
{"current_steps": 50, "total_steps": 936, "loss": 1.3627, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 2.6595744680851065e-06, "epoch": 0.16, "percentage": 5.34, "elapsed_time": "0:26:53", "remaining_time": "7:56:38"}
{"current_steps": 55, "total_steps": 936, "loss": 1.2606, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6000000238418579, "learning_rate": 2.9255319148936174e-06, "epoch": 0.176, "percentage": 5.88, "elapsed_time": "0:29:41", "remaining_time": "7:55:30"}
{"current_steps": 60, "total_steps": 936, "loss": 1.3274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.4749999940395355, "learning_rate": 3.191489361702128e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:32:32", "remaining_time": "7:54:59"}
{"current_steps": 65, "total_steps": 936, "loss": 1.2879, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.457446808510639e-06, "epoch": 0.208, "percentage": 6.94, "elapsed_time": "0:35:10", "remaining_time": "7:51:18"}
{"current_steps": 70, "total_steps": 936, "loss": 1.3134, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 3.723404255319149e-06, "epoch": 0.224, "percentage": 7.48, "elapsed_time": "0:37:49", "remaining_time": "7:47:51"}
{"current_steps": 75, "total_steps": 936, "loss": 1.2797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.98936170212766e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:40:30", "remaining_time": "7:45:01"}
{"current_steps": 80, "total_steps": 936, "loss": 1.2678, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 4.255319148936171e-06, "epoch": 0.256, "percentage": 8.55, "elapsed_time": "0:43:10", "remaining_time": "7:42:03"}
{"current_steps": 85, "total_steps": 936, "loss": 1.2615, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6000000238418579, "learning_rate": 4.521276595744681e-06, "epoch": 0.272, "percentage": 9.08, "elapsed_time": "0:45:49", "remaining_time": "7:38:46"}
{"current_steps": 90, "total_steps": 936, "loss": 1.212, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 4.787234042553192e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:48:34", "remaining_time": "7:36:38"}
{"current_steps": 95, "total_steps": 936, "loss": 1.2618, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 4.999982598564682e-06, "epoch": 0.304, "percentage": 10.15, "elapsed_time": "0:51:16", "remaining_time": "7:33:58"}
{"current_steps": 100, "total_steps": 936, "loss": 1.2807, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.999373573764188e-06, "epoch": 0.32, "percentage": 10.68, "elapsed_time": "0:54:01", "remaining_time": "7:31:36"}
{"current_steps": 105, "total_steps": 936, "loss": 1.2805, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.997894719430564e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "0:56:28", "remaining_time": "7:26:54"}
{"current_steps": 110, "total_steps": 936, "loss": 1.2769, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.995546550233241e-06, "epoch": 0.352, "percentage": 11.75, "elapsed_time": "0:59:14", "remaining_time": "7:24:53"}
{"current_steps": 115, "total_steps": 936, "loss": 1.2514, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 4.992329883379755e-06, "epoch": 0.368, "percentage": 12.29, "elapsed_time": "1:01:56", "remaining_time": "7:22:12"}
{"current_steps": 120, "total_steps": 936, "loss": 1.2204, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.988245838331339e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "1:04:28", "remaining_time": "7:18:28"}
{"current_steps": 125, "total_steps": 936, "loss": 1.225, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 4.983295836413337e-06, "epoch": 0.4, "percentage": 13.35, "elapsed_time": "1:07:09", "remaining_time": "7:15:41"}
{"current_steps": 130, "total_steps": 936, "loss": 1.2696, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.977481600320545e-06, "epoch": 0.416, "percentage": 13.89, "elapsed_time": "1:09:46", "remaining_time": "7:12:38"}
{"current_steps": 135, "total_steps": 936, "loss": 1.2562, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.970805153517692e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "1:12:31", "remaining_time": "7:10:16"}
{"current_steps": 140, "total_steps": 936, "loss": 1.2297, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.44999998807907104, "learning_rate": 4.963268819535228e-06, "epoch": 0.448, "percentage": 14.96, "elapsed_time": "1:15:13", "remaining_time": "7:07:39"}
{"current_steps": 145, "total_steps": 936, "loss": 1.1857, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 4.954875221160695e-06, "epoch": 0.464, "percentage": 15.49, "elapsed_time": "1:17:45", "remaining_time": "7:04:11"}
{"current_steps": 150, "total_steps": 936, "loss": 1.2559, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.4749999940395355, "learning_rate": 4.945627279525943e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "1:20:29", "remaining_time": "7:01:46"}
{"current_steps": 155, "total_steps": 936, "loss": 1.2301, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.935528213090526e-06, "epoch": 0.496, "percentage": 16.56, "elapsed_time": "1:23:08", "remaining_time": "6:58:53"}
{"current_steps": 160, "total_steps": 936, "loss": 1.221, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 4.9245815365216115e-06, "epoch": 0.512, "percentage": 17.09, "elapsed_time": "1:25:46", "remaining_time": "6:55:58"}
{"current_steps": 165, "total_steps": 936, "loss": 1.1745, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 4.912791059470815e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "1:28:18", "remaining_time": "6:52:39"}
{"current_steps": 170, "total_steps": 936, "loss": 1.194, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 4.900160885248363e-06, "epoch": 0.544, "percentage": 18.16, "elapsed_time": "1:30:57", "remaining_time": "6:49:49"}
{"current_steps": 175, "total_steps": 936, "loss": 1.2303, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.4749999940395355, "learning_rate": 4.886695409395068e-06, "epoch": 0.56, "percentage": 18.7, "elapsed_time": "1:33:35", "remaining_time": "6:46:58"}
{"current_steps": 180, "total_steps": 936, "loss": 1.2359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 4.872399318152594e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "1:36:02", "remaining_time": "6:43:22"}
{"current_steps": 185, "total_steps": 936, "loss": 1.2299, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 4.857277586832556e-06, "epoch": 0.592, "percentage": 19.76, "elapsed_time": "1:38:35", "remaining_time": "6:40:12"}
{"current_steps": 190, "total_steps": 936, "loss": 1.1951, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.841335478085015e-06, "epoch": 0.608, "percentage": 20.3, "elapsed_time": "1:41:06", "remaining_time": "6:36:59"}
{"current_steps": 195, "total_steps": 936, "loss": 1.2285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.4749999940395355, "learning_rate": 4.824578540066981e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "1:43:41", "remaining_time": "6:34:00"}
{"current_steps": 200, "total_steps": 936, "loss": 1.2092, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.807012604511542e-06, "epoch": 0.64, "percentage": 21.37, "elapsed_time": "1:46:27", "remaining_time": "6:31:45"}
{"current_steps": 205, "total_steps": 936, "loss": 1.1919, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 4.788643784698316e-06, "epoch": 0.656, "percentage": 21.9, "elapsed_time": "1:49:02", "remaining_time": "6:28:49"}
{"current_steps": 210, "total_steps": 936, "loss": 1.2244, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.769478473325908e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "1:51:49", "remaining_time": "6:26:35"}
{"current_steps": 215, "total_steps": 936, "loss": 1.2612, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.7495233402871336e-06, "epoch": 0.688, "percentage": 22.97, "elapsed_time": "1:54:30", "remaining_time": "6:24:01"}
{"current_steps": 220, "total_steps": 936, "loss": 1.1849, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.728785330347771e-06, "epoch": 0.704, "percentage": 23.5, "elapsed_time": "1:57:11", "remaining_time": "6:21:24"}
{"current_steps": 225, "total_steps": 936, "loss": 1.2004, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 4.70727166072964e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "1:59:44", "remaining_time": "6:18:23"}
{"current_steps": 230, "total_steps": 936, "loss": 1.1679, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 4.684989818598887e-06, "epoch": 0.736, "percentage": 24.57, "elapsed_time": "2:02:30", "remaining_time": "6:16:02"}
{"current_steps": 235, "total_steps": 936, "loss": 1.1988, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 4.661947558460296e-06, "epoch": 0.752, "percentage": 25.11, "elapsed_time": "2:05:13", "remaining_time": "6:13:31"}
{"current_steps": 240, "total_steps": 936, "loss": 1.2519, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6000000238418579, "learning_rate": 4.63815289945858e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "2:07:55", "remaining_time": "6:11:00"}
{"current_steps": 245, "total_steps": 936, "loss": 1.2055, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.613614122587563e-06, "epoch": 0.784, "percentage": 26.18, "elapsed_time": "2:10:35", "remaining_time": "6:08:18"}
{"current_steps": 250, "total_steps": 936, "loss": 1.1903, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.4749999940395355, "learning_rate": 4.5883397678082385e-06, "epoch": 0.8, "percentage": 26.71, "elapsed_time": "2:13:08", "remaining_time": "6:05:20"}
{"current_steps": 255, "total_steps": 936, "loss": 1.1825, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 4.562338631076703e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "2:15:40", "remaining_time": "6:02:18"}
{"current_steps": 260, "total_steps": 936, "loss": 1.23, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.535619761282989e-06, "epoch": 0.832, "percentage": 27.78, "elapsed_time": "2:18:21", "remaining_time": "5:59:44"}
{"current_steps": 265, "total_steps": 936, "loss": 1.2482, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.508192457101886e-06, "epoch": 0.848, "percentage": 28.31, "elapsed_time": "2:21:00", "remaining_time": "5:57:03"}
{"current_steps": 270, "total_steps": 936, "loss": 1.1889, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 4.480066263756821e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "2:23:36", "remaining_time": "5:54:13"}
{"current_steps": 275, "total_steps": 936, "loss": 1.2078, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.451250969697944e-06, "epoch": 0.88, "percentage": 29.38, "elapsed_time": "2:26:08", "remaining_time": "5:51:17"}
{"current_steps": 280, "total_steps": 936, "loss": 1.1898, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5249999761581421, "learning_rate": 4.42175660319555e-06, "epoch": 0.896, "percentage": 29.91, "elapsed_time": "2:28:42", "remaining_time": "5:48:23"}
{"current_steps": 285, "total_steps": 936, "loss": 1.2078, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.391593428850069e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "2:31:11", "remaining_time": "5:45:21"}
{"current_steps": 290, "total_steps": 936, "loss": 1.2225, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.360771944019767e-06, "epoch": 0.928, "percentage": 30.98, "elapsed_time": "2:33:44", "remaining_time": "5:42:28"}
{"current_steps": 295, "total_steps": 936, "loss": 1.2094, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.5, "learning_rate": 4.329302875167486e-06, "epoch": 0.944, "percentage": 31.52, "elapsed_time": "2:36:22", "remaining_time": "5:39:46"}
{"current_steps": 300, "total_steps": 936, "loss": 1.212, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.550000011920929, "learning_rate": 4.297197174127619e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "2:38:56", "remaining_time": "5:36:56"}
{"current_steps": 305, "total_steps": 936, "loss": 1.2082, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 4.2644660142946685e-06, "epoch": 0.976, "percentage": 32.59, "elapsed_time": "2:41:35", "remaining_time": "5:34:18"}
{"current_steps": 310, "total_steps": 936, "loss": 1.1548, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 4.231120786734689e-06, "epoch": 0.992, "percentage": 33.12, "elapsed_time": "2:44:13", "remaining_time": "5:31:36"}
{"current_steps": 315, "total_steps": 936, "loss": 1.1007, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 4.197173096220983e-06, "epoch": 1.008, "percentage": 33.65, "elapsed_time": "2:47:25", "remaining_time": "5:30:03"}
{"current_steps": 320, "total_steps": 936, "loss": 0.9386, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 4.162634757195418e-06, "epoch": 1.024, "percentage": 34.19, "elapsed_time": "2:50:03", "remaining_time": "5:27:21"}
{"current_steps": 325, "total_steps": 936, "loss": 1.0353, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 4.127517789656772e-06, "epoch": 1.04, "percentage": 34.72, "elapsed_time": "2:52:48", "remaining_time": "5:24:53"}
{"current_steps": 330, "total_steps": 936, "loss": 0.9511, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 4.091834414977556e-06, "epoch": 1.056, "percentage": 35.26, "elapsed_time": "2:55:27", "remaining_time": "5:22:11"}
{"current_steps": 335, "total_steps": 936, "loss": 0.9662, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 4.055597051650731e-06, "epoch": 1.072, "percentage": 35.79, "elapsed_time": "2:58:06", "remaining_time": "5:19:32"}
{"current_steps": 340, "total_steps": 936, "loss": 0.9817, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 4.018818310967843e-06, "epoch": 1.088, "percentage": 36.32, "elapsed_time": "3:00:44", "remaining_time": "5:16:50"}
{"current_steps": 345, "total_steps": 936, "loss": 0.9953, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 3.981510992630055e-06, "epoch": 1.104, "percentage": 36.86, "elapsed_time": "3:03:27", "remaining_time": "5:14:16"}
{"current_steps": 350, "total_steps": 936, "loss": 0.9707, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 3.943688080293607e-06, "epoch": 1.12, "percentage": 37.39, "elapsed_time": "3:05:57", "remaining_time": "5:11:21"}
{"current_steps": 355, "total_steps": 936, "loss": 0.9606, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 3.905362737051252e-06, "epoch": 1.1360000000000001, "percentage": 37.93, "elapsed_time": "3:08:38", "remaining_time": "5:08:44"}
{"current_steps": 360, "total_steps": 936, "loss": 0.9989, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 3.866548300851254e-06, "epoch": 1.152, "percentage": 38.46, "elapsed_time": "3:11:24", "remaining_time": "5:06:15"}
{"current_steps": 365, "total_steps": 936, "loss": 0.9456, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 3.827258279855527e-06, "epoch": 1.168, "percentage": 39.0, "elapsed_time": "3:13:53", "remaining_time": "5:03:18"}
{"current_steps": 370, "total_steps": 936, "loss": 0.9721, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.787506347738538e-06, "epoch": 1.184, "percentage": 39.53, "elapsed_time": "3:16:24", "remaining_time": "5:00:27"}
{"current_steps": 375, "total_steps": 936, "loss": 1.0158, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.747306338928609e-06, "epoch": 1.2, "percentage": 40.06, "elapsed_time": "3:19:04", "remaining_time": "4:57:49"}
{"current_steps": 380, "total_steps": 936, "loss": 0.9464, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 3.706672243793271e-06, "epoch": 1.216, "percentage": 40.6, "elapsed_time": "3:21:40", "remaining_time": "4:55:04"}
{"current_steps": 385, "total_steps": 936, "loss": 0.9478, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 3.665618203770352e-06, "epoch": 1.232, "percentage": 41.13, "elapsed_time": "3:24:16", "remaining_time": "4:52:21"}
{"current_steps": 390, "total_steps": 936, "loss": 0.9435, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 3.6241585064464846e-06, "epoch": 1.248, "percentage": 41.67, "elapsed_time": "3:26:59", "remaining_time": "4:49:46"}
{"current_steps": 395, "total_steps": 936, "loss": 0.9669, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.582307580584759e-06, "epoch": 1.264, "percentage": 42.2, "elapsed_time": "3:29:35", "remaining_time": "4:47:04"}
{"current_steps": 400, "total_steps": 936, "loss": 0.9323, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 3.5400799911032357e-06, "epoch": 1.28, "percentage": 42.74, "elapsed_time": "3:32:16", "remaining_time": "4:44:27"}
{"current_steps": 405, "total_steps": 936, "loss": 0.9978, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.4974904340060756e-06, "epoch": 1.296, "percentage": 43.27, "elapsed_time": "3:35:00", "remaining_time": "4:41:54"}
{"current_steps": 410, "total_steps": 936, "loss": 0.9679, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 3.4545537312690565e-06, "epoch": 1.312, "percentage": 43.8, "elapsed_time": "3:37:37", "remaining_time": "4:39:12"}
{"current_steps": 415, "total_steps": 936, "loss": 0.9274, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 3.4112848256812374e-06, "epoch": 1.328, "percentage": 44.34, "elapsed_time": "3:40:15", "remaining_time": "4:36:30"}
{"current_steps": 420, "total_steps": 936, "loss": 0.9137, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.3676987756445894e-06, "epoch": 1.3439999999999999, "percentage": 44.87, "elapsed_time": "3:43:03", "remaining_time": "4:34:02"}
{"current_steps": 425, "total_steps": 936, "loss": 0.9124, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 3.323810749933381e-06, "epoch": 1.3599999999999999, "percentage": 45.41, "elapsed_time": "3:45:37", "remaining_time": "4:31:17"}
{"current_steps": 430, "total_steps": 936, "loss": 0.9594, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.2796360224151587e-06, "epoch": 1.376, "percentage": 45.94, "elapsed_time": "3:48:16", "remaining_time": "4:28:37"}
{"current_steps": 435, "total_steps": 936, "loss": 0.9259, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 3.235189966735148e-06, "epoch": 1.392, "percentage": 46.47, "elapsed_time": "3:50:44", "remaining_time": "4:25:44"}
{"current_steps": 440, "total_steps": 936, "loss": 0.9667, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.1904880509659397e-06, "epoch": 1.408, "percentage": 47.01, "elapsed_time": "3:53:21", "remaining_time": "4:23:03"}
{"current_steps": 445, "total_steps": 936, "loss": 0.9938, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6000000238418579, "learning_rate": 3.1455458322242943e-06, "epoch": 1.424, "percentage": 47.54, "elapsed_time": "3:55:53", "remaining_time": "4:20:16"}
{"current_steps": 450, "total_steps": 936, "loss": 0.9649, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 3.100378951256981e-06, "epoch": 1.44, "percentage": 48.08, "elapsed_time": "3:58:32", "remaining_time": "4:17:36"}
{"current_steps": 455, "total_steps": 936, "loss": 0.9642, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 3.055003126997495e-06, "epoch": 1.456, "percentage": 48.61, "elapsed_time": "4:01:15", "remaining_time": "4:15:02"}
{"current_steps": 460, "total_steps": 936, "loss": 0.959, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.0094341510955697e-06, "epoch": 1.472, "percentage": 49.15, "elapsed_time": "4:04:03", "remaining_time": "4:12:32"}
{"current_steps": 465, "total_steps": 936, "loss": 0.9591, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.625, "learning_rate": 2.963687882421383e-06, "epoch": 1.488, "percentage": 49.68, "elapsed_time": "4:06:37", "remaining_time": "4:09:48"}
{"current_steps": 470, "total_steps": 936, "loss": 0.9619, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.9177802415463714e-06, "epoch": 1.504, "percentage": 50.21, "elapsed_time": "4:09:16", "remaining_time": "4:07:08"}
{"current_steps": 475, "total_steps": 936, "loss": 0.9498, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 2.871727205202563e-06, "epoch": 1.52, "percentage": 50.75, "elapsed_time": "4:11:51", "remaining_time": "4:04:26"}
{"current_steps": 480, "total_steps": 936, "loss": 0.9629, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 2.825544800722376e-06, "epoch": 1.536, "percentage": 51.28, "elapsed_time": "4:14:27", "remaining_time": "4:01:43"}
{"current_steps": 485, "total_steps": 936, "loss": 0.9485, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.7792491004607984e-06, "epoch": 1.552, "percentage": 51.82, "elapsed_time": "4:16:58", "remaining_time": "3:58:57"}
{"current_steps": 490, "total_steps": 936, "loss": 0.9529, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.732856216201906e-06, "epoch": 1.568, "percentage": 52.35, "elapsed_time": "4:19:34", "remaining_time": "3:56:15"}
{"current_steps": 495, "total_steps": 936, "loss": 0.9733, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 2.6863822935516546e-06, "epoch": 1.584, "percentage": 52.88, "elapsed_time": "4:22:20", "remaining_time": "3:53:43"}
{"current_steps": 500, "total_steps": 936, "loss": 0.9562, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.639843506318899e-06, "epoch": 1.6, "percentage": 53.42, "elapsed_time": "4:25:01", "remaining_time": "3:51:06"}
{"current_steps": 505, "total_steps": 936, "loss": 0.9531, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 2.593256050886603e-06, "epoch": 1.616, "percentage": 53.95, "elapsed_time": "4:27:37", "remaining_time": "3:48:24"}
{"current_steps": 510, "total_steps": 936, "loss": 0.949, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 2.5466361405751914e-06, "epoch": 1.6320000000000001, "percentage": 54.49, "elapsed_time": "4:30:26", "remaining_time": "3:45:53"}
{"current_steps": 515, "total_steps": 936, "loss": 0.9795, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 2.5e-06, "epoch": 1.6480000000000001, "percentage": 55.02, "elapsed_time": "4:33:07", "remaining_time": "3:43:16"}
{"current_steps": 520, "total_steps": 936, "loss": 0.9221, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 2.4533638594248094e-06, "epoch": 1.6640000000000001, "percentage": 55.56, "elapsed_time": "4:35:45", "remaining_time": "3:40:36"}
{"current_steps": 525, "total_steps": 936, "loss": 0.9773, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 2.406743949113397e-06, "epoch": 1.6800000000000002, "percentage": 56.09, "elapsed_time": "4:38:13", "remaining_time": "3:37:48"}
{"current_steps": 530, "total_steps": 936, "loss": 0.9491, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 2.360156493681102e-06, "epoch": 1.696, "percentage": 56.62, "elapsed_time": "4:40:51", "remaining_time": "3:35:08"}
{"current_steps": 535, "total_steps": 936, "loss": 0.9586, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.3136177064483462e-06, "epoch": 1.712, "percentage": 57.16, "elapsed_time": "4:43:35", "remaining_time": "3:32:33"}
{"current_steps": 540, "total_steps": 936, "loss": 0.8999, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 2.2671437837980943e-06, "epoch": 1.728, "percentage": 57.69, "elapsed_time": "4:46:16", "remaining_time": "3:29:55"}
{"current_steps": 545, "total_steps": 936, "loss": 0.9613, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 2.2207508995392024e-06, "epoch": 1.744, "percentage": 58.23, "elapsed_time": "4:49:03", "remaining_time": "3:27:22"}
{"current_steps": 550, "total_steps": 936, "loss": 0.9815, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 2.1744551992776247e-06, "epoch": 1.76, "percentage": 58.76, "elapsed_time": "4:51:31", "remaining_time": "3:24:35"}
{"current_steps": 555, "total_steps": 936, "loss": 0.9807, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 2.1282727947974373e-06, "epoch": 1.776, "percentage": 59.29, "elapsed_time": "4:54:08", "remaining_time": "3:21:55"}
{"current_steps": 560, "total_steps": 936, "loss": 0.9808, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 2.082219758453629e-06, "epoch": 1.792, "percentage": 59.83, "elapsed_time": "4:56:46", "remaining_time": "3:19:15"}
{"current_steps": 565, "total_steps": 936, "loss": 0.9573, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 2.036312117578617e-06, "epoch": 1.808, "percentage": 60.36, "elapsed_time": "4:59:22", "remaining_time": "3:16:34"}
{"current_steps": 570, "total_steps": 936, "loss": 0.9561, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 1.990565848904431e-06, "epoch": 1.8239999999999998, "percentage": 60.9, "elapsed_time": "5:01:59", "remaining_time": "3:13:54"}
{"current_steps": 575, "total_steps": 936, "loss": 0.9946, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.574999988079071, "learning_rate": 1.9449968730025055e-06, "epoch": 1.8399999999999999, "percentage": 61.43, "elapsed_time": "5:04:44", "remaining_time": "3:11:19"}
{"current_steps": 580, "total_steps": 936, "loss": 0.9332, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 1.899621048743019e-06, "epoch": 1.8559999999999999, "percentage": 61.97, "elapsed_time": "5:07:21", "remaining_time": "3:08:39"}
{"current_steps": 585, "total_steps": 936, "loss": 0.9053, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 1.854454167775706e-06, "epoch": 1.8719999999999999, "percentage": 62.5, "elapsed_time": "5:10:00", "remaining_time": "3:06:00"}
{"current_steps": 590, "total_steps": 936, "loss": 0.9753, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 1.8095119490340618e-06, "epoch": 1.888, "percentage": 63.03, "elapsed_time": "5:12:40", "remaining_time": "3:03:21"}
{"current_steps": 595, "total_steps": 936, "loss": 0.9771, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 1.764810033264852e-06, "epoch": 1.904, "percentage": 63.57, "elapsed_time": "5:15:16", "remaining_time": "3:00:41"}
{"current_steps": 600, "total_steps": 936, "loss": 0.9631, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.675000011920929, "learning_rate": 1.7203639775848423e-06, "epoch": 1.92, "percentage": 64.1, "elapsed_time": "5:17:50", "remaining_time": "2:57:59"}
{"current_steps": 605, "total_steps": 936, "loss": 0.9786, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 1.6761892500666195e-06, "epoch": 1.936, "percentage": 64.64, "elapsed_time": "5:20:33", "remaining_time": "2:55:22"}
{"current_steps": 610, "total_steps": 936, "loss": 0.9546, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 1.632301224355411e-06, "epoch": 1.952, "percentage": 65.17, "elapsed_time": "5:23:04", "remaining_time": "2:52:39"}
{"current_steps": 615, "total_steps": 936, "loss": 0.9811, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.699999988079071, "learning_rate": 1.5887151743187634e-06, "epoch": 1.968, "percentage": 65.71, "elapsed_time": "5:25:37", "remaining_time": "2:49:57"}
{"current_steps": 620, "total_steps": 936, "loss": 0.9563, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 1.5454462687309445e-06, "epoch": 1.984, "percentage": 66.24, "elapsed_time": "5:28:09", "remaining_time": "2:47:15"}
{"current_steps": 625, "total_steps": 936, "loss": 0.8898, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 1.502509565993925e-06, "epoch": 2.0, "percentage": 66.77, "elapsed_time": "5:30:45", "remaining_time": "2:44:35"}
{"current_steps": 630, "total_steps": 936, "loss": 0.8054, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 1.4599200088967652e-06, "epoch": 2.016, "percentage": 67.31, "elapsed_time": "5:34:22", "remaining_time": "2:42:24"}
{"current_steps": 635, "total_steps": 936, "loss": 0.8194, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 1.4176924194152405e-06, "epoch": 2.032, "percentage": 67.84, "elapsed_time": "5:36:55", "remaining_time": "2:39:42"}
{"current_steps": 640, "total_steps": 936, "loss": 0.7991, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 1.3758414935535147e-06, "epoch": 2.048, "percentage": 68.38, "elapsed_time": "5:39:36", "remaining_time": "2:37:03"}
{"current_steps": 645, "total_steps": 936, "loss": 0.8219, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 1.3343817962296485e-06, "epoch": 2.064, "percentage": 68.91, "elapsed_time": "5:42:18", "remaining_time": "2:34:25"}
{"current_steps": 650, "total_steps": 936, "loss": 0.7579, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8999999761581421, "learning_rate": 1.293327756206729e-06, "epoch": 2.08, "percentage": 69.44, "elapsed_time": "5:44:59", "remaining_time": "2:31:47"}
{"current_steps": 655, "total_steps": 936, "loss": 0.7865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 1.252693661071391e-06, "epoch": 2.096, "percentage": 69.98, "elapsed_time": "5:47:35", "remaining_time": "2:29:07"}
{"current_steps": 660, "total_steps": 936, "loss": 0.7903, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 1.2124936522614622e-06, "epoch": 2.112, "percentage": 70.51, "elapsed_time": "5:50:12", "remaining_time": "2:26:27"}
{"current_steps": 665, "total_steps": 936, "loss": 0.797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 1.1727417201444735e-06, "epoch": 2.128, "percentage": 71.05, "elapsed_time": "5:52:52", "remaining_time": "2:23:48"}
{"current_steps": 670, "total_steps": 936, "loss": 0.7863, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8999999761581421, "learning_rate": 1.1334516991487473e-06, "epoch": 2.144, "percentage": 71.58, "elapsed_time": "5:55:32", "remaining_time": "2:21:09"}
{"current_steps": 675, "total_steps": 936, "loss": 0.7675, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 1.094637262948749e-06, "epoch": 2.16, "percentage": 72.12, "elapsed_time": "5:58:13", "remaining_time": "2:18:30"}
{"current_steps": 680, "total_steps": 936, "loss": 0.7969, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 1.0563119197063934e-06, "epoch": 2.176, "percentage": 72.65, "elapsed_time": "6:00:49", "remaining_time": "2:15:50"}
{"current_steps": 685, "total_steps": 936, "loss": 0.804, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 1.018489007369945e-06, "epoch": 2.192, "percentage": 73.18, "elapsed_time": "6:03:22", "remaining_time": "2:13:08"}
{"current_steps": 690, "total_steps": 936, "loss": 0.7751, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 9.81181689032158e-07, "epoch": 2.208, "percentage": 73.72, "elapsed_time": "6:06:00", "remaining_time": "2:10:29"}
{"current_steps": 695, "total_steps": 936, "loss": 0.7732, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 9.444029483492703e-07, "epoch": 2.224, "percentage": 74.25, "elapsed_time": "6:08:38", "remaining_time": "2:07:49"}
{"current_steps": 700, "total_steps": 936, "loss": 0.7583, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 9.081655850224449e-07, "epoch": 2.24, "percentage": 74.79, "elapsed_time": "6:11:13", "remaining_time": "2:05:09"}
{"current_steps": 705, "total_steps": 936, "loss": 0.7482, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 8.724822103432282e-07, "epoch": 2.2560000000000002, "percentage": 75.32, "elapsed_time": "6:13:57", "remaining_time": "2:02:31"}
{"current_steps": 710, "total_steps": 936, "loss": 0.7722, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.949999988079071, "learning_rate": 8.373652428045831e-07, "epoch": 2.2720000000000002, "percentage": 75.85, "elapsed_time": "6:16:38", "remaining_time": "1:59:53"}
{"current_steps": 715, "total_steps": 936, "loss": 0.7688, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 8.028269037790171e-07, "epoch": 2.288, "percentage": 76.39, "elapsed_time": "6:19:16", "remaining_time": "1:57:13"}
{"current_steps": 720, "total_steps": 936, "loss": 0.7621, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 7.688792132653111e-07, "epoch": 2.304, "percentage": 76.92, "elapsed_time": "6:21:53", "remaining_time": "1:54:34"}
{"current_steps": 725, "total_steps": 936, "loss": 0.7714, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 7.355339857053318e-07, "epoch": 2.32, "percentage": 77.46, "elapsed_time": "6:24:19", "remaining_time": "1:51:51"}
{"current_steps": 730, "total_steps": 936, "loss": 0.7932, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 7.028028258723818e-07, "epoch": 2.336, "percentage": 77.99, "elapsed_time": "6:27:05", "remaining_time": "1:49:14"}
{"current_steps": 735, "total_steps": 936, "loss": 0.776, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 6.706971248325151e-07, "epoch": 2.352, "percentage": 78.53, "elapsed_time": "6:29:48", "remaining_time": "1:46:35"}
{"current_steps": 740, "total_steps": 936, "loss": 0.7637, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 6.392280559802341e-07, "epoch": 2.368, "percentage": 79.06, "elapsed_time": "6:32:37", "remaining_time": "1:43:59"}
{"current_steps": 745, "total_steps": 936, "loss": 0.7279, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.925000011920929, "learning_rate": 6.084065711499326e-07, "epoch": 2.384, "percentage": 79.59, "elapsed_time": "6:35:19", "remaining_time": "1:41:21"}
{"current_steps": 750, "total_steps": 936, "loss": 0.7662, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 5.782433968044495e-07, "epoch": 2.4, "percentage": 80.13, "elapsed_time": "6:38:13", "remaining_time": "1:38:45"}
{"current_steps": 755, "total_steps": 936, "loss": 0.7806, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 5.487490303020576e-07, "epoch": 2.416, "percentage": 80.66, "elapsed_time": "6:40:45", "remaining_time": "1:36:04"}
{"current_steps": 760, "total_steps": 936, "loss": 0.7998, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 5.199337362431792e-07, "epoch": 2.432, "percentage": 81.2, "elapsed_time": "6:43:31", "remaining_time": "1:33:26"}
{"current_steps": 765, "total_steps": 936, "loss": 0.7519, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7250000238418579, "learning_rate": 4.918075428981148e-07, "epoch": 2.448, "percentage": 81.73, "elapsed_time": "6:46:14", "remaining_time": "1:30:48"}
{"current_steps": 770, "total_steps": 936, "loss": 0.7689, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 4.643802387170118e-07, "epoch": 2.464, "percentage": 82.26, "elapsed_time": "6:48:48", "remaining_time": "1:28:07"}
{"current_steps": 775, "total_steps": 936, "loss": 0.7588, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 4.376613689232978e-07, "epoch": 2.48, "percentage": 82.8, "elapsed_time": "6:51:28", "remaining_time": "1:25:28"}
{"current_steps": 780, "total_steps": 936, "loss": 0.7523, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 4.1166023219176176e-07, "epoch": 2.496, "percentage": 83.33, "elapsed_time": "6:54:02", "remaining_time": "1:22:48"}
{"current_steps": 785, "total_steps": 936, "loss": 0.7563, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.925000011920929, "learning_rate": 3.863858774124385e-07, "epoch": 2.512, "percentage": 83.87, "elapsed_time": "6:56:32", "remaining_time": "1:20:07"}
{"current_steps": 790, "total_steps": 936, "loss": 0.7382, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.618471005414215e-07, "epoch": 2.528, "percentage": 84.4, "elapsed_time": "6:59:00", "remaining_time": "1:17:26"}
{"current_steps": 795, "total_steps": 936, "loss": 0.7742, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.75, "learning_rate": 3.380524415397049e-07, "epoch": 2.544, "percentage": 84.94, "elapsed_time": "7:01:37", "remaining_time": "1:14:46"}
{"current_steps": 800, "total_steps": 936, "loss": 0.7785, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 3.150101814011136e-07, "epoch": 2.56, "percentage": 85.47, "elapsed_time": "7:04:21", "remaining_time": "1:12:08"}
{"current_steps": 805, "total_steps": 936, "loss": 0.7977, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 2.927283392703606e-07, "epoch": 2.576, "percentage": 86.0, "elapsed_time": "7:07:04", "remaining_time": "1:09:29"}
{"current_steps": 810, "total_steps": 936, "loss": 0.7552, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 2.712146696522305e-07, "epoch": 2.592, "percentage": 86.54, "elapsed_time": "7:09:40", "remaining_time": "1:06:50"}
{"current_steps": 815, "total_steps": 936, "loss": 0.7575, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 2.504766597128666e-07, "epoch": 2.608, "percentage": 87.07, "elapsed_time": "7:12:16", "remaining_time": "1:04:10"}
{"current_steps": 820, "total_steps": 936, "loss": 0.7752, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 2.3052152667409289e-07, "epoch": 2.624, "percentage": 87.61, "elapsed_time": "7:14:49", "remaining_time": "1:01:30"}
{"current_steps": 825, "total_steps": 936, "loss": 0.7935, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 2.1135621530168488e-07, "epoch": 2.64, "percentage": 88.14, "elapsed_time": "7:17:29", "remaining_time": "0:58:51"}
{"current_steps": 830, "total_steps": 936, "loss": 0.8091, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 1.9298739548845813e-07, "epoch": 2.656, "percentage": 88.68, "elapsed_time": "7:20:03", "remaining_time": "0:56:12"}
{"current_steps": 835, "total_steps": 936, "loss": 0.7636, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 1.7542145993301896e-07, "epoch": 2.672, "percentage": 89.21, "elapsed_time": "7:22:41", "remaining_time": "0:53:32"}
{"current_steps": 840, "total_steps": 936, "loss": 0.7742, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 1.5866452191498488e-07, "epoch": 2.6879999999999997, "percentage": 89.74, "elapsed_time": "7:25:11", "remaining_time": "0:50:52"}
{"current_steps": 845, "total_steps": 936, "loss": 0.7386, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.925000011920929, "learning_rate": 1.4272241316744456e-07, "epoch": 2.7039999999999997, "percentage": 90.28, "elapsed_time": "7:27:46", "remaining_time": "0:48:13"}
{"current_steps": 850, "total_steps": 936, "loss": 0.711, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.9750000238418579, "learning_rate": 1.2760068184740597e-07, "epoch": 2.7199999999999998, "percentage": 90.81, "elapsed_time": "7:30:20", "remaining_time": "0:45:33"}
{"current_steps": 855, "total_steps": 936, "loss": 0.7165, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 1.133045906049321e-07, "epoch": 2.7359999999999998, "percentage": 91.35, "elapsed_time": "7:33:02", "remaining_time": "0:42:55"}
{"current_steps": 860, "total_steps": 936, "loss": 0.7491, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.925000011920929, "learning_rate": 9.983911475163727e-08, "epoch": 2.752, "percentage": 91.88, "elapsed_time": "7:35:34", "remaining_time": "0:40:15"}
{"current_steps": 865, "total_steps": 936, "loss": 0.7404, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 8.720894052918566e-08, "epoch": 2.768, "percentage": 92.41, "elapsed_time": "7:38:07", "remaining_time": "0:37:36"}
{"current_steps": 870, "total_steps": 936, "loss": 0.7496, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 7.541846347838915e-08, "epoch": 2.784, "percentage": 92.95, "elapsed_time": "7:40:42", "remaining_time": "0:34:57"}
{"current_steps": 875, "total_steps": 936, "loss": 0.7865, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8999999761581421, "learning_rate": 6.447178690947492e-08, "epoch": 2.8, "percentage": 93.48, "elapsed_time": "7:43:10", "remaining_time": "0:32:17"}
{"current_steps": 880, "total_steps": 936, "loss": 0.7529, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.925000011920929, "learning_rate": 5.437272047405712e-08, "epoch": 2.816, "percentage": 94.02, "elapsed_time": "7:45:49", "remaining_time": "0:29:38"}
{"current_steps": 885, "total_steps": 936, "loss": 0.8151, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.800000011920929, "learning_rate": 4.512477883930527e-08, "epoch": 2.832, "percentage": 94.55, "elapsed_time": "7:48:29", "remaining_time": "0:26:59"}
{"current_steps": 890, "total_steps": 936, "loss": 0.7505, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 3.673118046477159e-08, "epoch": 2.848, "percentage": 95.09, "elapsed_time": "7:51:12", "remaining_time": "0:24:21"}
{"current_steps": 895, "total_steps": 936, "loss": 0.7622, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 2.9194846482308026e-08, "epoch": 2.864, "percentage": 95.62, "elapsed_time": "7:53:51", "remaining_time": "0:21:42"}
{"current_steps": 900, "total_steps": 936, "loss": 0.766, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 2.251839967945535e-08, "epoch": 2.88, "percentage": 96.15, "elapsed_time": "7:56:39", "remaining_time": "0:19:03"}
{"current_steps": 905, "total_steps": 936, "loss": 0.8119, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 1.6704163586663825e-08, "epoch": 2.896, "percentage": 96.69, "elapsed_time": "7:59:15", "remaining_time": "0:16:24"}
{"current_steps": 910, "total_steps": 936, "loss": 0.7818, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 1.1754161668660612e-08, "epoch": 2.912, "percentage": 97.22, "elapsed_time": "8:01:53", "remaining_time": "0:13:46"}
{"current_steps": 915, "total_steps": 936, "loss": 0.7862, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.824999988079071, "learning_rate": 7.670116620245304e-09, "epoch": 2.928, "percentage": 97.76, "elapsed_time": "8:04:39", "remaining_time": "0:11:07"}
{"current_steps": 920, "total_steps": 936, "loss": 0.7435, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.875, "learning_rate": 4.453449766758933e-09, "epoch": 2.944, "percentage": 98.29, "elapsed_time": "8:07:28", "remaining_time": "0:08:28"}
{"current_steps": 925, "total_steps": 936, "loss": 0.787, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.6499999761581421, "learning_rate": 2.1052805694365964e-09, "epoch": 2.96, "percentage": 98.82, "elapsed_time": "8:10:12", "remaining_time": "0:05:49"}
{"current_steps": 930, "total_steps": 936, "loss": 0.7539, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.7749999761581421, "learning_rate": 6.264262358129936e-10, "epoch": 2.976, "percentage": 99.36, "elapsed_time": "8:12:59", "remaining_time": "0:03:10"}
{"current_steps": 935, "total_steps": 936, "loss": 0.7977, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": 0.8500000238418579, "learning_rate": 1.7401435318531444e-11, "epoch": 2.992, "percentage": 99.89, "elapsed_time": "8:15:39", "remaining_time": "0:00:31"}
{"current_steps": 936, "total_steps": 936, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.9952, "percentage": 100.0, "elapsed_time": "8:16:10", "remaining_time": "0:00:00"}