polejowska commited on
Commit
9492956
1 Parent(s): 3445883

End of training

Browse files
Files changed (3) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +8 -158
  3. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50ef054b6d9eb9370c99f2fbbadc603558f06e784b594a87d0b2ee908340990
3
  size 312421626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b2b14b353679762fa1d51f3d7674cf2e9ac4ea26d4c031cfc705cdc5801845
3
  size 312421626
trainer_state.json CHANGED
@@ -1,165 +1,15 @@
1
  {
2
- "best_metric": 1.7242921590805054,
3
- "best_model_checkpoint": "detr-r101-cd45rb-8ah-12l\\checkpoint-46060",
4
- "epoch": 10.0,
5
- "global_step": 46060,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "learning_rate": 9.00238818931828e-06,
13
- "loss": 3.0401,
14
- "step": 4606
15
- },
16
- {
17
- "epoch": 1.0,
18
- "eval_loss": 2.163705587387085,
19
- "eval_runtime": 222.5701,
20
- "eval_samples_per_second": 8.002,
21
- "eval_steps_per_second": 1.002,
22
- "step": 4606
23
- },
24
- {
25
- "epoch": 2.0,
26
- "learning_rate": 8.002822405557968e-06,
27
- "loss": 2.7151,
28
- "step": 9212
29
- },
30
- {
31
- "epoch": 2.0,
32
- "eval_loss": 2.06657338142395,
33
- "eval_runtime": 222.3447,
34
- "eval_samples_per_second": 8.01,
35
- "eval_steps_per_second": 1.003,
36
- "step": 9212
37
- },
38
- {
39
- "epoch": 3.0,
40
- "learning_rate": 7.003039513677812e-06,
41
- "loss": 2.6021,
42
- "step": 13818
43
- },
44
- {
45
- "epoch": 3.0,
46
- "eval_loss": 1.986824870109558,
47
- "eval_runtime": 226.29,
48
- "eval_samples_per_second": 7.87,
49
- "eval_steps_per_second": 0.985,
50
- "step": 13818
51
- },
52
- {
53
- "epoch": 4.0,
54
- "learning_rate": 6.003473729917499e-06,
55
- "loss": 2.5221,
56
- "step": 18424
57
- },
58
- {
59
- "epoch": 4.0,
60
- "eval_loss": 1.8957558870315552,
61
- "eval_runtime": 219.599,
62
- "eval_samples_per_second": 8.11,
63
- "eval_steps_per_second": 1.015,
64
- "step": 18424
65
- },
66
- {
67
- "epoch": 5.0,
68
- "learning_rate": 5.003907946157187e-06,
69
- "loss": 2.4541,
70
- "step": 23030
71
- },
72
- {
73
- "epoch": 5.0,
74
- "eval_loss": 1.8809998035430908,
75
- "eval_runtime": 222.9944,
76
- "eval_samples_per_second": 7.987,
77
- "eval_steps_per_second": 1.0,
78
- "step": 23030
79
- },
80
- {
81
- "epoch": 6.0,
82
- "learning_rate": 4.0041250542770305e-06,
83
- "loss": 2.4155,
84
- "step": 27636
85
- },
86
- {
87
- "epoch": 6.0,
88
- "eval_loss": 1.8369228839874268,
89
- "eval_runtime": 220.1885,
90
- "eval_samples_per_second": 8.089,
91
- "eval_steps_per_second": 1.013,
92
- "step": 27636
93
- },
94
- {
95
- "epoch": 7.0,
96
- "learning_rate": 3.0047763786365614e-06,
97
- "loss": 2.3531,
98
- "step": 32242
99
- },
100
- {
101
- "epoch": 7.0,
102
- "eval_loss": 1.8039908409118652,
103
- "eval_runtime": 225.4193,
104
- "eval_samples_per_second": 7.901,
105
- "eval_steps_per_second": 0.989,
106
- "step": 32242
107
- },
108
- {
109
- "epoch": 8.0,
110
- "learning_rate": 2.004993486756405e-06,
111
- "loss": 2.31,
112
- "step": 36848
113
- },
114
- {
115
- "epoch": 8.0,
116
- "eval_loss": 1.797875165939331,
117
- "eval_runtime": 219.4975,
118
- "eval_samples_per_second": 8.114,
119
- "eval_steps_per_second": 1.016,
120
- "step": 36848
121
- },
122
- {
123
- "epoch": 9.0,
124
- "learning_rate": 1.0054277029960922e-06,
125
- "loss": 2.2841,
126
- "step": 41454
127
- },
128
- {
129
- "epoch": 9.0,
130
- "eval_loss": 1.7520661354064941,
131
- "eval_runtime": 222.6235,
132
- "eval_samples_per_second": 8.0,
133
- "eval_steps_per_second": 1.002,
134
- "step": 41454
135
- },
136
- {
137
- "epoch": 10.0,
138
- "learning_rate": 5.644811115935737e-09,
139
- "loss": 2.2555,
140
- "step": 46060
141
- },
142
- {
143
- "epoch": 10.0,
144
- "eval_loss": 1.7242921590805054,
145
- "eval_runtime": 220.3572,
146
- "eval_samples_per_second": 8.082,
147
- "eval_steps_per_second": 1.012,
148
- "step": 46060
149
- },
150
- {
151
- "epoch": 10.0,
152
- "step": 46060,
153
- "total_flos": 1.650708094793472e+20,
154
- "train_loss": 2.4951736483323383,
155
- "train_runtime": 37556.3075,
156
- "train_samples_per_second": 4.905,
157
- "train_steps_per_second": 1.226
158
- }
159
- ],
160
- "max_steps": 46060,
161
- "num_train_epochs": 10,
162
- "total_flos": 1.650708094793472e+20,
163
  "trial_name": null,
164
  "trial_params": null
165
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": null,
5
+ "global_step": 0,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 0,
11
+ "num_train_epochs": 0,
12
+ "total_flos": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  "trial_name": null,
14
  "trial_params": null
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc9dcbfd112ca4f5aaa6f788a7d81929234664d3a7bb0f84e6abf9d3457810ae
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15d3a01aaf39a92184d567cac94bb10a33edec5dbcaf68971253978afcdf2ac
3
  size 3579