Einmalumdiewelt commited on
Commit
b6e642a
1 Parent(s): fc3fc8c

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +13 -13
  2. eval_results.json +9 -9
  3. train_results.json +4 -4
  4. trainer_state.json +23 -23
all_results.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_gen_len": 53.322,
4
- "eval_loss": 2.0281758308410645,
5
- "eval_rouge1": 28.26,
6
- "eval_rouge2": 9.2063,
7
- "eval_rougeL": 19.7844,
8
- "eval_rougeLsum": 24.388,
9
- "eval_runtime": 249.008,
10
  "eval_samples": 1500,
11
- "eval_samples_per_second": 6.024,
12
- "eval_steps_per_second": 0.755,
13
- "train_loss": 1.9120913609095982,
14
- "train_runtime": 6207.6309,
15
  "train_samples": 7000,
16
- "train_samples_per_second": 11.276,
17
- "train_steps_per_second": 1.41
18
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_gen_len": 54.48733333333333,
4
+ "eval_loss": 2.0228171348571777,
5
+ "eval_rouge1": 28.4344,
6
+ "eval_rouge2": 9.3461,
7
+ "eval_rougeL": 19.7157,
8
+ "eval_rougeLsum": 24.6508,
9
+ "eval_runtime": 254.6251,
10
  "eval_samples": 1500,
11
+ "eval_samples_per_second": 5.891,
12
+ "eval_steps_per_second": 0.738,
13
+ "train_loss": 1.883265816824777,
14
+ "train_runtime": 6265.8424,
15
  "train_samples": 7000,
16
+ "train_samples_per_second": 11.172,
17
+ "train_steps_per_second": 1.396
18
  }
eval_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_gen_len": 53.322,
4
- "eval_loss": 2.0281758308410645,
5
- "eval_rouge1": 28.26,
6
- "eval_rouge2": 9.2063,
7
- "eval_rougeL": 19.7844,
8
- "eval_rougeLsum": 24.388,
9
- "eval_runtime": 249.008,
10
  "eval_samples": 1500,
11
- "eval_samples_per_second": 6.024,
12
- "eval_steps_per_second": 0.755
13
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_gen_len": 54.48733333333333,
4
+ "eval_loss": 2.0228171348571777,
5
+ "eval_rouge1": 28.4344,
6
+ "eval_rouge2": 9.3461,
7
+ "eval_rougeL": 19.7157,
8
+ "eval_rougeLsum": 24.6508,
9
+ "eval_runtime": 254.6251,
10
  "eval_samples": 1500,
11
+ "eval_samples_per_second": 5.891,
12
+ "eval_steps_per_second": 0.738
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "train_loss": 1.9120913609095982,
4
- "train_runtime": 6207.6309,
5
  "train_samples": 7000,
6
- "train_samples_per_second": 11.276,
7
- "train_steps_per_second": 1.41
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "train_loss": 1.883265816824777,
4
+ "train_runtime": 6265.8424,
5
  "train_samples": 7000,
6
+ "train_samples_per_second": 11.172,
7
+ "train_steps_per_second": 1.396
8
  }
trainer_state.json CHANGED
@@ -10,118 +10,118 @@
10
  {
11
  "epoch": 0.57,
12
  "learning_rate": 4.714285714285714e-05,
13
- "loss": 2.1935,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.14,
18
  "learning_rate": 4.428571428571428e-05,
19
- "loss": 2.1618,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 1.71,
24
  "learning_rate": 4.1428571428571437e-05,
25
- "loss": 2.0802,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 2.29,
30
  "learning_rate": 3.857142857142858e-05,
31
- "loss": 2.0405,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 2.86,
36
  "learning_rate": 3.571428571428572e-05,
37
- "loss": 2.0094,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 3.43,
42
  "learning_rate": 3.285714285714286e-05,
43
- "loss": 1.9689,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 4.0,
48
  "learning_rate": 3e-05,
49
- "loss": 1.9429,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 4.57,
54
  "learning_rate": 2.714285714285714e-05,
55
- "loss": 1.888,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 5.14,
60
  "learning_rate": 2.4285714285714288e-05,
61
- "loss": 1.8982,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 5.71,
66
  "learning_rate": 2.1428571428571428e-05,
67
- "loss": 1.8509,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 6.29,
72
  "learning_rate": 1.8571428571428572e-05,
73
- "loss": 1.8348,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 6.86,
78
  "learning_rate": 1.5714285714285715e-05,
79
- "loss": 1.8173,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 7.43,
84
  "learning_rate": 1.2857142857142857e-05,
85
- "loss": 1.8017,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 8.0,
90
  "learning_rate": 1e-05,
91
- "loss": 1.7911,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 8.57,
96
  "learning_rate": 7.142857142857143e-06,
97
- "loss": 1.7689,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 9.14,
102
  "learning_rate": 4.285714285714286e-06,
103
- "loss": 1.7795,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 9.71,
108
  "learning_rate": 1.4285714285714286e-06,
109
- "loss": 1.7522,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 10.0,
114
  "step": 8750,
115
- "total_flos": 4.261736610275328e+16,
116
- "train_loss": 1.9120913609095982,
117
- "train_runtime": 6207.6309,
118
- "train_samples_per_second": 11.276,
119
- "train_steps_per_second": 1.41
120
  }
121
  ],
122
  "max_steps": 8750,
123
  "num_train_epochs": 10,
124
- "total_flos": 4.261736610275328e+16,
125
  "trial_name": null,
126
  "trial_params": null
127
  }
 
10
  {
11
  "epoch": 0.57,
12
  "learning_rate": 4.714285714285714e-05,
13
+ "loss": 2.1596,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 1.14,
18
  "learning_rate": 4.428571428571428e-05,
19
+ "loss": 2.1314,
20
  "step": 1000
21
  },
22
  {
23
  "epoch": 1.71,
24
  "learning_rate": 4.1428571428571437e-05,
25
+ "loss": 2.055,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 2.29,
30
  "learning_rate": 3.857142857142858e-05,
31
+ "loss": 2.0122,
32
  "step": 2000
33
  },
34
  {
35
  "epoch": 2.86,
36
  "learning_rate": 3.571428571428572e-05,
37
+ "loss": 1.9833,
38
  "step": 2500
39
  },
40
  {
41
  "epoch": 3.43,
42
  "learning_rate": 3.285714285714286e-05,
43
+ "loss": 1.9181,
44
  "step": 3000
45
  },
46
  {
47
  "epoch": 4.0,
48
  "learning_rate": 3e-05,
49
+ "loss": 1.9276,
50
  "step": 3500
51
  },
52
  {
53
  "epoch": 4.57,
54
  "learning_rate": 2.714285714285714e-05,
55
+ "loss": 1.8599,
56
  "step": 4000
57
  },
58
  {
59
  "epoch": 5.14,
60
  "learning_rate": 2.4285714285714288e-05,
61
+ "loss": 1.8608,
62
  "step": 4500
63
  },
64
  {
65
  "epoch": 5.71,
66
  "learning_rate": 2.1428571428571428e-05,
67
+ "loss": 1.8234,
68
  "step": 5000
69
  },
70
  {
71
  "epoch": 6.29,
72
  "learning_rate": 1.8571428571428572e-05,
73
+ "loss": 1.8171,
74
  "step": 5500
75
  },
76
  {
77
  "epoch": 6.86,
78
  "learning_rate": 1.5714285714285715e-05,
79
+ "loss": 1.7907,
80
  "step": 6000
81
  },
82
  {
83
  "epoch": 7.43,
84
  "learning_rate": 1.2857142857142857e-05,
85
+ "loss": 1.7693,
86
  "step": 6500
87
  },
88
  {
89
  "epoch": 8.0,
90
  "learning_rate": 1e-05,
91
+ "loss": 1.7666,
92
  "step": 7000
93
  },
94
  {
95
  "epoch": 8.57,
96
  "learning_rate": 7.142857142857143e-06,
97
+ "loss": 1.7393,
98
  "step": 7500
99
  },
100
  {
101
  "epoch": 9.14,
102
  "learning_rate": 4.285714285714286e-06,
103
+ "loss": 1.7473,
104
  "step": 8000
105
  },
106
  {
107
  "epoch": 9.71,
108
  "learning_rate": 1.4285714285714286e-06,
109
+ "loss": 1.7235,
110
  "step": 8500
111
  },
112
  {
113
  "epoch": 10.0,
114
  "step": 8750,
115
+ "total_flos": 4.261233268518912e+16,
116
+ "train_loss": 1.883265816824777,
117
+ "train_runtime": 6265.8424,
118
+ "train_samples_per_second": 11.172,
119
+ "train_steps_per_second": 1.396
120
  }
121
  ],
122
  "max_steps": 8750,
123
  "num_train_epochs": 10,
124
+ "total_flos": 4.261233268518912e+16,
125
  "trial_name": null,
126
  "trial_params": null
127
  }