Hugging Face's logo

AlekseyKorshuk
/
6.7b-ri-reproduce-4-gpu

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
text-generation-inference
Model card Files Community
10
AlekseyKorshuk commited on
Commit
1f2302f
·
1 Parent(s): 7cbae14

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +172 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 1.1160404185454051,
4
+ "train_runtime": 51742.5542,
5
+ "train_samples": 189,
6
+ "train_samples_per_second": 0.037,
7
+ "train_steps_per_second": 0.009
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 1.1160404185454051,
4
+ "train_runtime": 51742.5542,
5
+ "train_samples": 189,
6
+ "train_samples_per_second": 0.037,
7
+ "train_steps_per_second": 0.009
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 480,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 9e-07,
13
+ "loss": 3.1382,
14
+ "perplexity": 23.062317304193936,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "learning_rate": 9e-07,
20
+ "loss": 2.6614,
21
+ "perplexity": 14.316317920319525,
22
+ "step": 48
23
+ },
24
+ {
25
+ "epoch": 1.0,
26
+ "eval_runtime": 0.0024,
27
+ "eval_samples_per_second": 0.0,
28
+ "eval_steps_per_second": 0.0,
29
+ "step": 48
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "learning_rate": 9e-07,
34
+ "loss": 2.1364,
35
+ "perplexity": 8.468894663745782,
36
+ "step": 96
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_runtime": 0.0028,
41
+ "eval_samples_per_second": 0.0,
42
+ "eval_steps_per_second": 0.0,
43
+ "step": 96
44
+ },
45
+ {
46
+ "epoch": 3.0,
47
+ "learning_rate": 9e-07,
48
+ "loss": 1.7242,
49
+ "perplexity": 5.608032808397292,
50
+ "step": 144
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_runtime": 0.002,
55
+ "eval_samples_per_second": 0.0,
56
+ "eval_steps_per_second": 0.0,
57
+ "step": 144
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "learning_rate": 9e-07,
62
+ "loss": 1.3783,
63
+ "perplexity": 3.96815003520746,
64
+ "step": 192
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_runtime": 0.0023,
69
+ "eval_samples_per_second": 0.0,
70
+ "eval_steps_per_second": 0.0,
71
+ "step": 192
72
+ },
73
+ {
74
+ "epoch": 5.0,
75
+ "learning_rate": 9e-07,
76
+ "loss": 1.0366,
77
+ "perplexity": 2.819614010859592,
78
+ "step": 240
79
+ },
80
+ {
81
+ "epoch": 5.0,
82
+ "eval_runtime": 0.0021,
83
+ "eval_samples_per_second": 0.0,
84
+ "eval_steps_per_second": 0.0,
85
+ "step": 240
86
+ },
87
+ {
88
+ "epoch": 6.0,
89
+ "learning_rate": 9e-07,
90
+ "loss": 0.7703,
91
+ "perplexity": 2.1604142808602513,
92
+ "step": 288
93
+ },
94
+ {
95
+ "epoch": 6.0,
96
+ "eval_runtime": 0.0032,
97
+ "eval_samples_per_second": 0.0,
98
+ "eval_steps_per_second": 0.0,
99
+ "step": 288
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "learning_rate": 9e-07,
104
+ "loss": 0.5576,
105
+ "perplexity": 1.7464759242010608,
106
+ "step": 336
107
+ },
108
+ {
109
+ "epoch": 7.0,
110
+ "eval_runtime": 0.0025,
111
+ "eval_samples_per_second": 0.0,
112
+ "eval_steps_per_second": 0.0,
113
+ "step": 336
114
+ },
115
+ {
116
+ "epoch": 8.0,
117
+ "learning_rate": 9e-07,
118
+ "loss": 0.4029,
119
+ "perplexity": 1.4961572684557012,
120
+ "step": 384
121
+ },
122
+ {
123
+ "epoch": 8.0,
124
+ "eval_runtime": 0.0025,
125
+ "eval_samples_per_second": 0.0,
126
+ "eval_steps_per_second": 0.0,
127
+ "step": 384
128
+ },
129
+ {
130
+ "epoch": 9.0,
131
+ "learning_rate": 9e-07,
132
+ "loss": 0.2827,
133
+ "perplexity": 1.3267070899823727,
134
+ "step": 432
135
+ },
136
+ {
137
+ "epoch": 9.0,
138
+ "eval_runtime": 0.0019,
139
+ "eval_samples_per_second": 0.0,
140
+ "eval_steps_per_second": 0.0,
141
+ "step": 432
142
+ },
143
+ {
144
+ "epoch": 10.0,
145
+ "learning_rate": 9e-07,
146
+ "loss": 0.2,
147
+ "perplexity": 1.2214027581601699,
148
+ "step": 480
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "eval_runtime": 0.0023,
153
+ "eval_samples_per_second": 0.0,
154
+ "eval_steps_per_second": 0.0,
155
+ "step": 480
156
+ },
157
+ {
158
+ "epoch": 10.0,
159
+ "step": 480,
160
+ "total_flos": 5019068989440.0,
161
+ "train_loss": 1.1160404185454051,
162
+ "train_runtime": 51742.5542,
163
+ "train_samples_per_second": 0.037,
164
+ "train_steps_per_second": 0.009
165
+ }
166
+ ],
167
+ "max_steps": 480,
168
+ "num_train_epochs": 10,
169
+ "total_flos": 5019068989440.0,
170
+ "trial_name": null,
171
+ "trial_params": null
172
+ }