End of training
Browse files- README.md +3 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +189 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: facebook/bart-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: summ_screen_fd_blueprint_epoch_10
|
8 |
results: []
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# summ_screen_fd_blueprint_epoch_10
|
15 |
|
16 |
-
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 1.9205
|
19 |
|
|
|
3 |
base_model: facebook/bart-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- learn3r/summ_screen_fd_bp
|
8 |
model-index:
|
9 |
- name: summ_screen_fd_blueprint_epoch_10
|
10 |
results: []
|
|
|
15 |
|
16 |
# summ_screen_fd_blueprint_epoch_10
|
17 |
|
18 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the learn3r/summ_screen_fd_bp dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 1.9205
|
21 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.74,
|
3 |
+
"eval_loss": 1.9205037355422974,
|
4 |
+
"eval_runtime": 2.0094,
|
5 |
+
"eval_samples": 338,
|
6 |
+
"eval_samples_per_second": 168.21,
|
7 |
+
"eval_steps_per_second": 21.4,
|
8 |
+
"train_loss": 2.1082653863089424,
|
9 |
+
"train_runtime": 679.206,
|
10 |
+
"train_samples": 3673,
|
11 |
+
"train_samples_per_second": 54.078,
|
12 |
+
"train_steps_per_second": 0.206
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.74,
|
3 |
+
"eval_loss": 1.9205037355422974,
|
4 |
+
"eval_runtime": 2.0094,
|
5 |
+
"eval_samples": 338,
|
6 |
+
"eval_samples_per_second": 168.21,
|
7 |
+
"eval_steps_per_second": 21.4
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.74,
|
3 |
+
"train_loss": 2.1082653863089424,
|
4 |
+
"train_runtime": 679.206,
|
5 |
+
"train_samples": 3673,
|
6 |
+
"train_samples_per_second": 54.078,
|
7 |
+
"train_steps_per_second": 0.206
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.73913043478261,
|
5 |
+
"global_step": 140,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.7,
|
12 |
+
"learning_rate": 9.285714285714286e-05,
|
13 |
+
"loss": 3.3723,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.97,
|
18 |
+
"eval_loss": 2.261305332183838,
|
19 |
+
"eval_runtime": 1.7879,
|
20 |
+
"eval_samples_per_second": 189.047,
|
21 |
+
"eval_steps_per_second": 24.05,
|
22 |
+
"step": 14
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.39,
|
26 |
+
"learning_rate": 8.642857142857143e-05,
|
27 |
+
"loss": 2.4888,
|
28 |
+
"step": 20
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.95,
|
32 |
+
"eval_loss": 2.087858200073242,
|
33 |
+
"eval_runtime": 1.8469,
|
34 |
+
"eval_samples_per_second": 183.011,
|
35 |
+
"eval_steps_per_second": 23.283,
|
36 |
+
"step": 28
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.09,
|
40 |
+
"learning_rate": 7.928571428571429e-05,
|
41 |
+
"loss": 2.3065,
|
42 |
+
"step": 30
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.78,
|
46 |
+
"learning_rate": 7.214285714285714e-05,
|
47 |
+
"loss": 2.1694,
|
48 |
+
"step": 40
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.99,
|
52 |
+
"eval_loss": 2.0183253288269043,
|
53 |
+
"eval_runtime": 1.7709,
|
54 |
+
"eval_samples_per_second": 190.86,
|
55 |
+
"eval_steps_per_second": 24.281,
|
56 |
+
"step": 43
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.48,
|
60 |
+
"learning_rate": 6.500000000000001e-05,
|
61 |
+
"loss": 2.0846,
|
62 |
+
"step": 50
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.97,
|
66 |
+
"eval_loss": 1.983121395111084,
|
67 |
+
"eval_runtime": 1.724,
|
68 |
+
"eval_samples_per_second": 196.056,
|
69 |
+
"eval_steps_per_second": 24.942,
|
70 |
+
"step": 57
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 4.17,
|
74 |
+
"learning_rate": 5.785714285714287e-05,
|
75 |
+
"loss": 2.026,
|
76 |
+
"step": 60
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.87,
|
80 |
+
"learning_rate": 5.0714285714285716e-05,
|
81 |
+
"loss": 1.9812,
|
82 |
+
"step": 70
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 4.94,
|
86 |
+
"eval_loss": 1.9576869010925293,
|
87 |
+
"eval_runtime": 2.058,
|
88 |
+
"eval_samples_per_second": 164.239,
|
89 |
+
"eval_steps_per_second": 20.894,
|
90 |
+
"step": 71
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 5.57,
|
94 |
+
"learning_rate": 4.3571428571428576e-05,
|
95 |
+
"loss": 1.9352,
|
96 |
+
"step": 80
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 5.98,
|
100 |
+
"eval_loss": 1.9370218515396118,
|
101 |
+
"eval_runtime": 1.7855,
|
102 |
+
"eval_samples_per_second": 189.305,
|
103 |
+
"eval_steps_per_second": 24.083,
|
104 |
+
"step": 86
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.26,
|
108 |
+
"learning_rate": 3.642857142857143e-05,
|
109 |
+
"loss": 1.9164,
|
110 |
+
"step": 90
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.96,
|
114 |
+
"learning_rate": 2.9285714285714288e-05,
|
115 |
+
"loss": 1.8822,
|
116 |
+
"step": 100
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 6.96,
|
120 |
+
"eval_loss": 1.9341849088668823,
|
121 |
+
"eval_runtime": 1.8263,
|
122 |
+
"eval_samples_per_second": 185.074,
|
123 |
+
"eval_steps_per_second": 23.545,
|
124 |
+
"step": 100
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 7.65,
|
128 |
+
"learning_rate": 2.214285714285714e-05,
|
129 |
+
"loss": 1.853,
|
130 |
+
"step": 110
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 8.0,
|
134 |
+
"eval_loss": 1.9238194227218628,
|
135 |
+
"eval_runtime": 1.8358,
|
136 |
+
"eval_samples_per_second": 184.114,
|
137 |
+
"eval_steps_per_second": 23.423,
|
138 |
+
"step": 115
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 8.35,
|
142 |
+
"learning_rate": 1.5e-05,
|
143 |
+
"loss": 1.8446,
|
144 |
+
"step": 120
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 8.97,
|
148 |
+
"eval_loss": 1.9229856729507446,
|
149 |
+
"eval_runtime": 1.8246,
|
150 |
+
"eval_samples_per_second": 185.25,
|
151 |
+
"eval_steps_per_second": 23.567,
|
152 |
+
"step": 129
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 9.04,
|
156 |
+
"learning_rate": 7.857142857142858e-06,
|
157 |
+
"loss": 1.8343,
|
158 |
+
"step": 130
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 9.74,
|
162 |
+
"learning_rate": 7.142857142857143e-07,
|
163 |
+
"loss": 1.8211,
|
164 |
+
"step": 140
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 9.74,
|
168 |
+
"eval_loss": 1.9205037355422974,
|
169 |
+
"eval_runtime": 1.9363,
|
170 |
+
"eval_samples_per_second": 174.556,
|
171 |
+
"eval_steps_per_second": 22.207,
|
172 |
+
"step": 140
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 9.74,
|
176 |
+
"step": 140,
|
177 |
+
"total_flos": 2.181454126645248e+16,
|
178 |
+
"train_loss": 2.1082653863089424,
|
179 |
+
"train_runtime": 679.206,
|
180 |
+
"train_samples_per_second": 54.078,
|
181 |
+
"train_steps_per_second": 0.206
|
182 |
+
}
|
183 |
+
],
|
184 |
+
"max_steps": 140,
|
185 |
+
"num_train_epochs": 10,
|
186 |
+
"total_flos": 2.181454126645248e+16,
|
187 |
+
"trial_name": null,
|
188 |
+
"trial_params": null
|
189 |
+
}
|