Hugging Face's logo

rahulbaburajan
/
gpt-neo-violet-jacobs

Text Generation
Transformers
PyTorch
gpt_neo
Inference Endpoints
Model card Files Community
rahulbaburajan commited on
Commit
37d16e5
•
1 Parent(s): 880f5f0

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +184 -0
trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3794686794281006,
3
+ "best_model_checkpoint": "../saved_models_new/gptNEO_author_VJ_epochs15_lr5e-05/checkpoint-2000",
4
+ "epoch": 14.37125748502994,
5
+ "global_step": 24000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.2,
12
+ "learning_rate": 3.3333333333333335e-05,
13
+ "loss": 1.5146,
14
+ "step": 2000
15
+ },
16
+ {
17
+ "epoch": 1.2,
18
+ "eval_loss": 1.3794686794281006,
19
+ "eval_runtime": 14.6483,
20
+ "eval_samples_per_second": 25.395,
21
+ "eval_steps_per_second": 12.698,
22
+ "step": 2000
23
+ },
24
+ {
25
+ "epoch": 2.4,
26
+ "learning_rate": 4.773242630385488e-05,
27
+ "loss": 1.1782,
28
+ "step": 4000
29
+ },
30
+ {
31
+ "epoch": 2.4,
32
+ "eval_loss": 1.3970938920974731,
33
+ "eval_runtime": 14.6463,
34
+ "eval_samples_per_second": 25.399,
35
+ "eval_steps_per_second": 12.699,
36
+ "step": 4000
37
+ },
38
+ {
39
+ "epoch": 3.59,
40
+ "learning_rate": 4.319727891156463e-05,
41
+ "loss": 1.0049,
42
+ "step": 6000
43
+ },
44
+ {
45
+ "epoch": 3.59,
46
+ "eval_loss": 1.4491934776306152,
47
+ "eval_runtime": 14.6504,
48
+ "eval_samples_per_second": 25.392,
49
+ "eval_steps_per_second": 12.696,
50
+ "step": 6000
51
+ },
52
+ {
53
+ "epoch": 4.79,
54
+ "learning_rate": 3.8662131519274384e-05,
55
+ "loss": 0.8259,
56
+ "step": 8000
57
+ },
58
+ {
59
+ "epoch": 4.79,
60
+ "eval_loss": 1.5493556261062622,
61
+ "eval_runtime": 14.6505,
62
+ "eval_samples_per_second": 25.392,
63
+ "eval_steps_per_second": 12.696,
64
+ "step": 8000
65
+ },
66
+ {
67
+ "epoch": 5.99,
68
+ "learning_rate": 3.412698412698413e-05,
69
+ "loss": 0.6638,
70
+ "step": 10000
71
+ },
72
+ {
73
+ "epoch": 5.99,
74
+ "eval_loss": 1.6542575359344482,
75
+ "eval_runtime": 14.6609,
76
+ "eval_samples_per_second": 25.374,
77
+ "eval_steps_per_second": 12.687,
78
+ "step": 10000
79
+ },
80
+ {
81
+ "epoch": 7.19,
82
+ "learning_rate": 2.959183673469388e-05,
83
+ "loss": 0.4904,
84
+ "step": 12000
85
+ },
86
+ {
87
+ "epoch": 7.19,
88
+ "eval_loss": 1.8380136489868164,
89
+ "eval_runtime": 14.6527,
90
+ "eval_samples_per_second": 25.388,
91
+ "eval_steps_per_second": 12.694,
92
+ "step": 12000
93
+ },
94
+ {
95
+ "epoch": 8.38,
96
+ "learning_rate": 2.5056689342403626e-05,
97
+ "loss": 0.3432,
98
+ "step": 14000
99
+ },
100
+ {
101
+ "epoch": 8.38,
102
+ "eval_loss": 1.9379925727844238,
103
+ "eval_runtime": 14.6501,
104
+ "eval_samples_per_second": 25.392,
105
+ "eval_steps_per_second": 12.696,
106
+ "step": 14000
107
+ },
108
+ {
109
+ "epoch": 9.58,
110
+ "learning_rate": 2.052154195011338e-05,
111
+ "loss": 0.2499,
112
+ "step": 16000
113
+ },
114
+ {
115
+ "epoch": 9.58,
116
+ "eval_loss": 2.04109787940979,
117
+ "eval_runtime": 14.6527,
118
+ "eval_samples_per_second": 25.388,
119
+ "eval_steps_per_second": 12.694,
120
+ "step": 16000
121
+ },
122
+ {
123
+ "epoch": 10.78,
124
+ "learning_rate": 1.5986394557823133e-05,
125
+ "loss": 0.1809,
126
+ "step": 18000
127
+ },
128
+ {
129
+ "epoch": 10.78,
130
+ "eval_loss": 2.1205220222473145,
131
+ "eval_runtime": 14.6526,
132
+ "eval_samples_per_second": 25.388,
133
+ "eval_steps_per_second": 12.694,
134
+ "step": 18000
135
+ },
136
+ {
137
+ "epoch": 11.98,
138
+ "learning_rate": 1.145124716553288e-05,
139
+ "loss": 0.1246,
140
+ "step": 20000
141
+ },
142
+ {
143
+ "epoch": 11.98,
144
+ "eval_loss": 2.1967058181762695,
145
+ "eval_runtime": 14.6441,
146
+ "eval_samples_per_second": 25.403,
147
+ "eval_steps_per_second": 12.701,
148
+ "step": 20000
149
+ },
150
+ {
151
+ "epoch": 13.17,
152
+ "learning_rate": 6.9160997732426305e-06,
153
+ "loss": 0.0824,
154
+ "step": 22000
155
+ },
156
+ {
157
+ "epoch": 13.17,
158
+ "eval_loss": 2.2765705585479736,
159
+ "eval_runtime": 14.6502,
160
+ "eval_samples_per_second": 25.392,
161
+ "eval_steps_per_second": 12.696,
162
+ "step": 22000
163
+ },
164
+ {
165
+ "epoch": 14.37,
166
+ "learning_rate": 2.3809523809523808e-06,
167
+ "loss": 0.0615,
168
+ "step": 24000
169
+ },
170
+ {
171
+ "epoch": 14.37,
172
+ "eval_loss": 2.3161871433258057,
173
+ "eval_runtime": 14.6483,
174
+ "eval_samples_per_second": 25.395,
175
+ "eval_steps_per_second": 12.698,
176
+ "step": 24000
177
+ }
178
+ ],
179
+ "max_steps": 25050,
180
+ "num_train_epochs": 15,
181
+ "total_flos": 6268970336256000.0,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }