Training in progress, epoch 2
Browse files- all_results.json +21 -21
- eval_results.json +9 -9
- generated_predictions.csv +0 -0
- predict_results.json +8 -8
- train_results.json +5 -5
- trainer_state.json +203 -125
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,26 +1,26 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 2.
|
5 |
-
"eval_rouge-1":
|
6 |
-
"eval_rouge-2":
|
7 |
-
"eval_rouge-l":
|
8 |
-
"eval_runtime":
|
9 |
"eval_samples": 450,
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second": 0.
|
12 |
-
"predict_gen_len":
|
13 |
-
"predict_loss": 2.
|
14 |
-
"predict_rouge-1":
|
15 |
-
"predict_rouge-2":
|
16 |
-
"predict_rouge-l":
|
17 |
-
"predict_runtime":
|
18 |
"predict_samples": 417,
|
19 |
-
"predict_samples_per_second":
|
20 |
-
"predict_steps_per_second": 0.
|
21 |
-
"train_loss": 2.
|
22 |
-
"train_runtime":
|
23 |
"train_samples": 5133,
|
24 |
-
"train_samples_per_second":
|
25 |
-
"train_steps_per_second":
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_gen_len": 27.2356,
|
4 |
+
"eval_loss": 2.2613940238952637,
|
5 |
+
"eval_rouge-1": 72.7529,
|
6 |
+
"eval_rouge-2": 64.3941,
|
7 |
+
"eval_rouge-l": 71.5976,
|
8 |
+
"eval_runtime": 129.9628,
|
9 |
"eval_samples": 450,
|
10 |
+
"eval_samples_per_second": 3.463,
|
11 |
+
"eval_steps_per_second": 0.439,
|
12 |
+
"predict_gen_len": 26.4604,
|
13 |
+
"predict_loss": 2.305396795272827,
|
14 |
+
"predict_rouge-1": 73.3028,
|
15 |
+
"predict_rouge-2": 65.6876,
|
16 |
+
"predict_rouge-l": 72.5101,
|
17 |
+
"predict_runtime": 115.003,
|
18 |
"predict_samples": 417,
|
19 |
+
"predict_samples_per_second": 3.626,
|
20 |
+
"predict_steps_per_second": 0.461,
|
21 |
+
"train_loss": 2.047671499282029,
|
22 |
+
"train_runtime": 9522.6649,
|
23 |
"train_samples": 5133,
|
24 |
+
"train_samples_per_second": 26.951,
|
25 |
+
"train_steps_per_second": 3.371
|
26 |
}
|
eval_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 2.
|
5 |
-
"eval_rouge-1":
|
6 |
-
"eval_rouge-2":
|
7 |
-
"eval_rouge-l":
|
8 |
-
"eval_runtime":
|
9 |
"eval_samples": 450,
|
10 |
-
"eval_samples_per_second":
|
11 |
-
"eval_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_gen_len": 27.2356,
|
4 |
+
"eval_loss": 2.2613940238952637,
|
5 |
+
"eval_rouge-1": 72.7529,
|
6 |
+
"eval_rouge-2": 64.3941,
|
7 |
+
"eval_rouge-l": 71.5976,
|
8 |
+
"eval_runtime": 129.9628,
|
9 |
"eval_samples": 450,
|
10 |
+
"eval_samples_per_second": 3.463,
|
11 |
+
"eval_steps_per_second": 0.439
|
12 |
}
|
generated_predictions.csv
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
predict_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"predict_gen_len":
|
3 |
-
"predict_loss": 2.
|
4 |
-
"predict_rouge-1":
|
5 |
-
"predict_rouge-2":
|
6 |
-
"predict_rouge-l":
|
7 |
-
"predict_runtime":
|
8 |
"predict_samples": 417,
|
9 |
-
"predict_samples_per_second":
|
10 |
-
"predict_steps_per_second": 0.
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"predict_gen_len": 26.4604,
|
3 |
+
"predict_loss": 2.305396795272827,
|
4 |
+
"predict_rouge-1": 73.3028,
|
5 |
+
"predict_rouge-2": 65.6876,
|
6 |
+
"predict_rouge-l": 72.5101,
|
7 |
+
"predict_runtime": 115.003,
|
8 |
"predict_samples": 417,
|
9 |
+
"predict_samples_per_second": 3.626,
|
10 |
+
"predict_steps_per_second": 0.461
|
11 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5133,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"train_loss": 2.047671499282029,
|
4 |
+
"train_runtime": 9522.6649,
|
5 |
"train_samples": 5133,
|
6 |
+
"train_samples_per_second": 26.951,
|
7 |
+
"train_steps_per_second": 3.371
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,202 +1,280 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "PEFT/adapters-lib/output/mam/dataset-5100/test/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_gen_len":
|
14 |
-
"eval_loss": 3.
|
15 |
-
"eval_rouge-1":
|
16 |
-
"eval_rouge-2":
|
17 |
-
"eval_rouge-l":
|
18 |
-
"eval_runtime":
|
19 |
-
"eval_samples_per_second":
|
20 |
-
"eval_steps_per_second": 0.
|
21 |
"step": 642
|
22 |
},
|
23 |
{
|
24 |
"epoch": 2.0,
|
25 |
-
"eval_gen_len":
|
26 |
-
"eval_loss": 2.
|
27 |
-
"eval_rouge-1":
|
28 |
-
"eval_rouge-2":
|
29 |
-
"eval_rouge-l":
|
30 |
-
"eval_runtime":
|
31 |
-
"eval_samples_per_second":
|
32 |
-
"eval_steps_per_second": 0.
|
33 |
"step": 1284
|
34 |
},
|
35 |
{
|
36 |
"epoch": 3.0,
|
37 |
-
"eval_gen_len":
|
38 |
-
"eval_loss": 2.
|
39 |
-
"eval_rouge-1":
|
40 |
-
"eval_rouge-2":
|
41 |
-
"eval_rouge-l":
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 0.
|
45 |
"step": 1926
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.0,
|
49 |
-
"eval_gen_len":
|
50 |
-
"eval_loss": 2.
|
51 |
-
"eval_rouge-1":
|
52 |
-
"eval_rouge-2":
|
53 |
-
"eval_rouge-l":
|
54 |
-
"eval_runtime":
|
55 |
-
"eval_samples_per_second":
|
56 |
-
"eval_steps_per_second": 0.
|
57 |
"step": 2568
|
58 |
},
|
59 |
{
|
60 |
"epoch": 5.0,
|
61 |
-
"eval_gen_len":
|
62 |
-
"eval_loss": 2.
|
63 |
-
"eval_rouge-1":
|
64 |
-
"eval_rouge-2":
|
65 |
-
"eval_rouge-l": 52.
|
66 |
-
"eval_runtime":
|
67 |
-
"eval_samples_per_second":
|
68 |
-
"eval_steps_per_second": 0.
|
69 |
"step": 3210
|
70 |
},
|
71 |
{
|
72 |
"epoch": 6.0,
|
73 |
-
"eval_gen_len":
|
74 |
-
"eval_loss": 2.
|
75 |
-
"eval_rouge-1":
|
76 |
-
"eval_rouge-2":
|
77 |
-
"eval_rouge-l":
|
78 |
-
"eval_runtime":
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second": 0.
|
81 |
"step": 3852
|
82 |
},
|
83 |
{
|
84 |
"epoch": 7.0,
|
85 |
-
"eval_gen_len":
|
86 |
-
"eval_loss": 2.
|
87 |
-
"eval_rouge-1":
|
88 |
-
"eval_rouge-2":
|
89 |
-
"eval_rouge-l":
|
90 |
-
"eval_runtime":
|
91 |
-
"eval_samples_per_second":
|
92 |
-
"eval_steps_per_second": 0.
|
93 |
"step": 4494
|
94 |
},
|
95 |
{
|
96 |
"epoch": 7.79,
|
97 |
"learning_rate": 8.715112540192926e-05,
|
98 |
-
"loss": 2.
|
99 |
"step": 5000
|
100 |
},
|
101 |
{
|
102 |
"epoch": 8.0,
|
103 |
-
"eval_gen_len":
|
104 |
-
"eval_loss": 2.
|
105 |
-
"eval_rouge-1":
|
106 |
-
"eval_rouge-2":
|
107 |
-
"eval_rouge-l":
|
108 |
-
"eval_runtime":
|
109 |
-
"eval_samples_per_second":
|
110 |
-
"eval_steps_per_second": 0.
|
111 |
"step": 5136
|
112 |
},
|
113 |
{
|
114 |
"epoch": 9.0,
|
115 |
-
"eval_gen_len":
|
116 |
-
"eval_loss": 2.
|
117 |
-
"eval_rouge-1":
|
118 |
-
"eval_rouge-2":
|
119 |
-
"eval_rouge-l":
|
120 |
-
"eval_runtime":
|
121 |
-
"eval_samples_per_second":
|
122 |
-
"eval_steps_per_second": 0.
|
123 |
"step": 5778
|
124 |
},
|
125 |
{
|
126 |
"epoch": 10.0,
|
127 |
-
"eval_gen_len":
|
128 |
-
"eval_loss": 2.
|
129 |
-
"eval_rouge-1":
|
130 |
-
"eval_rouge-2":
|
131 |
-
"eval_rouge-l":
|
132 |
-
"eval_runtime":
|
133 |
-
"eval_samples_per_second":
|
134 |
-
"eval_steps_per_second": 0.
|
135 |
"step": 6420
|
136 |
},
|
137 |
{
|
138 |
"epoch": 11.0,
|
139 |
-
"eval_gen_len":
|
140 |
-
"eval_loss": 2.
|
141 |
-
"eval_rouge-1":
|
142 |
-
"eval_rouge-2":
|
143 |
-
"eval_rouge-l":
|
144 |
-
"eval_runtime":
|
145 |
-
"eval_samples_per_second":
|
146 |
-
"eval_steps_per_second": 0.
|
147 |
"step": 7062
|
148 |
},
|
149 |
{
|
150 |
"epoch": 12.0,
|
151 |
-
"eval_gen_len":
|
152 |
-
"eval_loss": 2.
|
153 |
-
"eval_rouge-1":
|
154 |
-
"eval_rouge-2":
|
155 |
-
"eval_rouge-l":
|
156 |
-
"eval_runtime":
|
157 |
-
"eval_samples_per_second":
|
158 |
-
"eval_steps_per_second": 0.
|
159 |
"step": 7704
|
160 |
},
|
161 |
{
|
162 |
"epoch": 13.0,
|
163 |
-
"eval_gen_len":
|
164 |
-
"eval_loss": 2.
|
165 |
-
"eval_rouge-1":
|
166 |
-
"eval_rouge-2":
|
167 |
-
"eval_rouge-l":
|
168 |
-
"eval_runtime":
|
169 |
-
"eval_samples_per_second":
|
170 |
-
"eval_steps_per_second": 0.
|
171 |
"step": 8346
|
172 |
},
|
173 |
{
|
174 |
"epoch": 14.0,
|
175 |
-
"eval_gen_len":
|
176 |
-
"eval_loss": 2.
|
177 |
-
"eval_rouge-1":
|
178 |
-
"eval_rouge-2":
|
179 |
-
"eval_rouge-l":
|
180 |
-
"eval_runtime":
|
181 |
-
"eval_samples_per_second":
|
182 |
-
"eval_steps_per_second": 0.
|
183 |
"step": 8988
|
184 |
},
|
185 |
{
|
186 |
-
"epoch":
|
187 |
-
"
|
188 |
-
"
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
}
|
194 |
],
|
195 |
"logging_steps": 5000,
|
196 |
"max_steps": 32100,
|
197 |
"num_train_epochs": 50,
|
198 |
"save_steps": 500,
|
199 |
-
"total_flos":
|
200 |
"trial_name": null,
|
201 |
"trial_params": null
|
202 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.2613940238952637,
|
3 |
+
"best_model_checkpoint": "PEFT/adapters-lib/output/mam/dataset-5100/test/checkpoint-9630",
|
4 |
+
"epoch": 20.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12840,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_gen_len": 27.1578,
|
14 |
+
"eval_loss": 3.0984482765197754,
|
15 |
+
"eval_rouge-1": 35.9221,
|
16 |
+
"eval_rouge-2": 20.801,
|
17 |
+
"eval_rouge-l": 33.0593,
|
18 |
+
"eval_runtime": 132.8327,
|
19 |
+
"eval_samples_per_second": 3.388,
|
20 |
+
"eval_steps_per_second": 0.429,
|
21 |
"step": 642
|
22 |
},
|
23 |
{
|
24 |
"epoch": 2.0,
|
25 |
+
"eval_gen_len": 23.6511,
|
26 |
+
"eval_loss": 2.8489246368408203,
|
27 |
+
"eval_rouge-1": 39.2966,
|
28 |
+
"eval_rouge-2": 22.654,
|
29 |
+
"eval_rouge-l": 37.1498,
|
30 |
+
"eval_runtime": 117.4318,
|
31 |
+
"eval_samples_per_second": 3.832,
|
32 |
+
"eval_steps_per_second": 0.485,
|
33 |
"step": 1284
|
34 |
},
|
35 |
{
|
36 |
"epoch": 3.0,
|
37 |
+
"eval_gen_len": 26.7267,
|
38 |
+
"eval_loss": 2.5933380126953125,
|
39 |
+
"eval_rouge-1": 47.1185,
|
40 |
+
"eval_rouge-2": 30.2869,
|
41 |
+
"eval_rouge-l": 44.1491,
|
42 |
+
"eval_runtime": 135.6918,
|
43 |
+
"eval_samples_per_second": 3.316,
|
44 |
+
"eval_steps_per_second": 0.42,
|
45 |
"step": 1926
|
46 |
},
|
47 |
{
|
48 |
"epoch": 4.0,
|
49 |
+
"eval_gen_len": 25.22,
|
50 |
+
"eval_loss": 2.476445198059082,
|
51 |
+
"eval_rouge-1": 50.0244,
|
52 |
+
"eval_rouge-2": 34.9212,
|
53 |
+
"eval_rouge-l": 48.057,
|
54 |
+
"eval_runtime": 123.2916,
|
55 |
+
"eval_samples_per_second": 3.65,
|
56 |
+
"eval_steps_per_second": 0.462,
|
57 |
"step": 2568
|
58 |
},
|
59 |
{
|
60 |
"epoch": 5.0,
|
61 |
+
"eval_gen_len": 26.6533,
|
62 |
+
"eval_loss": 2.412160873413086,
|
63 |
+
"eval_rouge-1": 54.5479,
|
64 |
+
"eval_rouge-2": 40.7397,
|
65 |
+
"eval_rouge-l": 52.5031,
|
66 |
+
"eval_runtime": 131.3008,
|
67 |
+
"eval_samples_per_second": 3.427,
|
68 |
+
"eval_steps_per_second": 0.434,
|
69 |
"step": 3210
|
70 |
},
|
71 |
{
|
72 |
"epoch": 6.0,
|
73 |
+
"eval_gen_len": 26.2667,
|
74 |
+
"eval_loss": 2.342738151550293,
|
75 |
+
"eval_rouge-1": 57.6653,
|
76 |
+
"eval_rouge-2": 44.2728,
|
77 |
+
"eval_rouge-l": 55.9363,
|
78 |
+
"eval_runtime": 127.5752,
|
79 |
+
"eval_samples_per_second": 3.527,
|
80 |
+
"eval_steps_per_second": 0.447,
|
81 |
"step": 3852
|
82 |
},
|
83 |
{
|
84 |
"epoch": 7.0,
|
85 |
+
"eval_gen_len": 26.1711,
|
86 |
+
"eval_loss": 2.3344807624816895,
|
87 |
+
"eval_rouge-1": 62.4422,
|
88 |
+
"eval_rouge-2": 50.3255,
|
89 |
+
"eval_rouge-l": 60.7065,
|
90 |
+
"eval_runtime": 127.1935,
|
91 |
+
"eval_samples_per_second": 3.538,
|
92 |
+
"eval_steps_per_second": 0.448,
|
93 |
"step": 4494
|
94 |
},
|
95 |
{
|
96 |
"epoch": 7.79,
|
97 |
"learning_rate": 8.715112540192926e-05,
|
98 |
+
"loss": 2.5283,
|
99 |
"step": 5000
|
100 |
},
|
101 |
{
|
102 |
"epoch": 8.0,
|
103 |
+
"eval_gen_len": 26.3044,
|
104 |
+
"eval_loss": 2.3082587718963623,
|
105 |
+
"eval_rouge-1": 65.6385,
|
106 |
+
"eval_rouge-2": 55.386,
|
107 |
+
"eval_rouge-l": 64.2792,
|
108 |
+
"eval_runtime": 129.227,
|
109 |
+
"eval_samples_per_second": 3.482,
|
110 |
+
"eval_steps_per_second": 0.441,
|
111 |
"step": 5136
|
112 |
},
|
113 |
{
|
114 |
"epoch": 9.0,
|
115 |
+
"eval_gen_len": 26.0844,
|
116 |
+
"eval_loss": 2.288771390914917,
|
117 |
+
"eval_rouge-1": 69.2728,
|
118 |
+
"eval_rouge-2": 59.5819,
|
119 |
+
"eval_rouge-l": 68.0772,
|
120 |
+
"eval_runtime": 127.02,
|
121 |
+
"eval_samples_per_second": 3.543,
|
122 |
+
"eval_steps_per_second": 0.449,
|
123 |
"step": 5778
|
124 |
},
|
125 |
{
|
126 |
"epoch": 10.0,
|
127 |
+
"eval_gen_len": 26.5111,
|
128 |
+
"eval_loss": 2.2961621284484863,
|
129 |
+
"eval_rouge-1": 69.5351,
|
130 |
+
"eval_rouge-2": 60.4728,
|
131 |
+
"eval_rouge-l": 68.5563,
|
132 |
+
"eval_runtime": 128.3845,
|
133 |
+
"eval_samples_per_second": 3.505,
|
134 |
+
"eval_steps_per_second": 0.444,
|
135 |
"step": 6420
|
136 |
},
|
137 |
{
|
138 |
"epoch": 11.0,
|
139 |
+
"eval_gen_len": 26.4467,
|
140 |
+
"eval_loss": 2.294877052307129,
|
141 |
+
"eval_rouge-1": 71.1387,
|
142 |
+
"eval_rouge-2": 62.2653,
|
143 |
+
"eval_rouge-l": 69.9201,
|
144 |
+
"eval_runtime": 125.5037,
|
145 |
+
"eval_samples_per_second": 3.586,
|
146 |
+
"eval_steps_per_second": 0.454,
|
147 |
"step": 7062
|
148 |
},
|
149 |
{
|
150 |
"epoch": 12.0,
|
151 |
+
"eval_gen_len": 26.3911,
|
152 |
+
"eval_loss": 2.270343065261841,
|
153 |
+
"eval_rouge-1": 72.6498,
|
154 |
+
"eval_rouge-2": 63.8234,
|
155 |
+
"eval_rouge-l": 71.505,
|
156 |
+
"eval_runtime": 128.4901,
|
157 |
+
"eval_samples_per_second": 3.502,
|
158 |
+
"eval_steps_per_second": 0.444,
|
159 |
"step": 7704
|
160 |
},
|
161 |
{
|
162 |
"epoch": 13.0,
|
163 |
+
"eval_gen_len": 26.3556,
|
164 |
+
"eval_loss": 2.2668042182922363,
|
165 |
+
"eval_rouge-1": 73.2494,
|
166 |
+
"eval_rouge-2": 65.1934,
|
167 |
+
"eval_rouge-l": 72.2586,
|
168 |
+
"eval_runtime": 125.8233,
|
169 |
+
"eval_samples_per_second": 3.576,
|
170 |
+
"eval_steps_per_second": 0.453,
|
171 |
"step": 8346
|
172 |
},
|
173 |
{
|
174 |
"epoch": 14.0,
|
175 |
+
"eval_gen_len": 26.5333,
|
176 |
+
"eval_loss": 2.267202854156494,
|
177 |
+
"eval_rouge-1": 73.2228,
|
178 |
+
"eval_rouge-2": 64.7993,
|
179 |
+
"eval_rouge-l": 71.9902,
|
180 |
+
"eval_runtime": 128.1385,
|
181 |
+
"eval_samples_per_second": 3.512,
|
182 |
+
"eval_steps_per_second": 0.445,
|
183 |
"step": 8988
|
184 |
},
|
185 |
{
|
186 |
+
"epoch": 15.0,
|
187 |
+
"eval_gen_len": 27.2356,
|
188 |
+
"eval_loss": 2.2613940238952637,
|
189 |
+
"eval_rouge-1": 72.7529,
|
190 |
+
"eval_rouge-2": 64.3941,
|
191 |
+
"eval_rouge-l": 71.5976,
|
192 |
+
"eval_runtime": 129.55,
|
193 |
+
"eval_samples_per_second": 3.474,
|
194 |
+
"eval_steps_per_second": 0.44,
|
195 |
+
"step": 9630
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 15.58,
|
199 |
+
"learning_rate": 7.109003215434083e-05,
|
200 |
+
"loss": 1.7733,
|
201 |
+
"step": 10000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 16.0,
|
205 |
+
"eval_gen_len": 26.5311,
|
206 |
+
"eval_loss": 2.2660067081451416,
|
207 |
+
"eval_rouge-1": 73.5002,
|
208 |
+
"eval_rouge-2": 65.0894,
|
209 |
+
"eval_rouge-l": 72.2767,
|
210 |
+
"eval_runtime": 129.1203,
|
211 |
+
"eval_samples_per_second": 3.485,
|
212 |
+
"eval_steps_per_second": 0.441,
|
213 |
+
"step": 10272
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 17.0,
|
217 |
+
"eval_gen_len": 26.4089,
|
218 |
+
"eval_loss": 2.2624781131744385,
|
219 |
+
"eval_rouge-1": 73.9016,
|
220 |
+
"eval_rouge-2": 66.1357,
|
221 |
+
"eval_rouge-l": 72.7275,
|
222 |
+
"eval_runtime": 125.6051,
|
223 |
+
"eval_samples_per_second": 3.583,
|
224 |
+
"eval_steps_per_second": 0.454,
|
225 |
+
"step": 10914
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 18.0,
|
229 |
+
"eval_gen_len": 26.0111,
|
230 |
+
"eval_loss": 2.2674496173858643,
|
231 |
+
"eval_rouge-1": 74.1365,
|
232 |
+
"eval_rouge-2": 66.7011,
|
233 |
+
"eval_rouge-l": 73.0304,
|
234 |
+
"eval_runtime": 123.8827,
|
235 |
+
"eval_samples_per_second": 3.632,
|
236 |
+
"eval_steps_per_second": 0.46,
|
237 |
+
"step": 11556
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 19.0,
|
241 |
+
"eval_gen_len": 26.7356,
|
242 |
+
"eval_loss": 2.264456033706665,
|
243 |
+
"eval_rouge-1": 74.1459,
|
244 |
+
"eval_rouge-2": 66.8989,
|
245 |
+
"eval_rouge-l": 73.1443,
|
246 |
+
"eval_runtime": 128.4694,
|
247 |
+
"eval_samples_per_second": 3.503,
|
248 |
+
"eval_steps_per_second": 0.444,
|
249 |
+
"step": 12198
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 20.0,
|
253 |
+
"eval_gen_len": 26.5311,
|
254 |
+
"eval_loss": 2.2706127166748047,
|
255 |
+
"eval_rouge-1": 74.3728,
|
256 |
+
"eval_rouge-2": 66.4207,
|
257 |
+
"eval_rouge-l": 73.2288,
|
258 |
+
"eval_runtime": 125.0151,
|
259 |
+
"eval_samples_per_second": 3.6,
|
260 |
+
"eval_steps_per_second": 0.456,
|
261 |
+
"step": 12840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 20.0,
|
265 |
+
"step": 12840,
|
266 |
+
"total_flos": 3.46468539506688e+16,
|
267 |
+
"train_loss": 2.047671499282029,
|
268 |
+
"train_runtime": 9522.6649,
|
269 |
+
"train_samples_per_second": 26.951,
|
270 |
+
"train_steps_per_second": 3.371
|
271 |
}
|
272 |
],
|
273 |
"logging_steps": 5000,
|
274 |
"max_steps": 32100,
|
275 |
"num_train_epochs": 50,
|
276 |
"save_steps": 500,
|
277 |
+
"total_flos": 3.46468539506688e+16,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
280 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a95829ca88d043b246dcabe92dff664cfa4ccae9daef7724eeb0be2f31e5b5b5
|
3 |
size 4792
|