Hugging Face's logo

Einmalumdiewelt
/
10k_MT5_small_sum-de_GNAD

Summarization
Transformers
PyTorch
German
mt5
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Community
2
Einmalumdiewelt commited on
Commit
dca79fe
•
1 Parent(s): 7ae990f

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +23 -23
  2. eval_results.json +10 -10
  3. generated_predictions.txt +0 -0
  4. predict_results.json +9 -9
  5. train_results.json +5 -5
  6. trainer_state.json +96 -12
all_results.json CHANGED
@@ -1,28 +1,28 @@
1
  {
2
- "epoch": 0.01,
3
- "eval_gen_len": 42.787333333333336,
4
- "eval_loss": 2.5066428184509277,
5
- "eval_rouge1": 23.6554,
6
- "eval_rouge2": 7.5413,
7
- "eval_rougeL": 17.4259,
8
- "eval_rougeLsum": 20.6655,
9
- "eval_runtime": 186.4899,
10
  "eval_samples": 1500,
11
- "eval_samples_per_second": 8.043,
12
- "eval_steps_per_second": 0.804,
13
- "predict_gen_len": 42.516,
14
- "predict_loss": 2.4928014278411865,
15
- "predict_rouge1": 24.233,
16
- "predict_rouge2": 7.7785,
17
- "predict_rougeL": 17.6919,
18
- "predict_rougeLsum": 21.0741,
19
- "predict_runtime": 186.2282,
20
  "predict_samples": 1500,
21
- "predict_samples_per_second": 8.055,
22
- "predict_steps_per_second": 0.805,
23
- "train_loss": 2.8345144271850584,
24
- "train_runtime": 8.6661,
25
  "train_samples": 7000,
26
- "train_samples_per_second": 11.539,
27
- "train_steps_per_second": 1.154
28
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 48.269333333333336,
4
+ "eval_loss": 2.4403438568115234,
5
+ "eval_rouge1": 24.9179,
6
+ "eval_rouge2": 7.8694,
7
+ "eval_rougeL": 18.048,
8
+ "eval_rougeLsum": 21.9371,
9
+ "eval_runtime": 203.3789,
10
  "eval_samples": 1500,
11
+ "eval_samples_per_second": 7.375,
12
+ "eval_steps_per_second": 0.738,
13
+ "predict_gen_len": 48.286,
14
+ "predict_loss": 2.4339749813079834,
15
+ "predict_rouge1": 25.7644,
16
+ "predict_rouge2": 8.257,
17
+ "predict_rougeL": 18.3876,
18
+ "predict_rougeLsum": 22.4801,
19
+ "predict_runtime": 206.6659,
20
  "predict_samples": 1500,
21
+ "predict_samples_per_second": 7.258,
22
+ "predict_steps_per_second": 0.726,
23
+ "train_loss": 2.648989501953125,
24
+ "train_runtime": 4314.4712,
25
  "train_samples": 7000,
26
+ "train_samples_per_second": 16.224,
27
+ "train_steps_per_second": 1.622
28
  }
eval_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 0.01,
3
- "eval_gen_len": 42.787333333333336,
4
- "eval_loss": 2.5066428184509277,
5
- "eval_rouge1": 23.6554,
6
- "eval_rouge2": 7.5413,
7
- "eval_rougeL": 17.4259,
8
- "eval_rougeLsum": 20.6655,
9
- "eval_runtime": 186.4899,
10
  "eval_samples": 1500,
11
- "eval_samples_per_second": 8.043,
12
- "eval_steps_per_second": 0.804
13
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 48.269333333333336,
4
+ "eval_loss": 2.4403438568115234,
5
+ "eval_rouge1": 24.9179,
6
+ "eval_rouge2": 7.8694,
7
+ "eval_rougeL": 18.048,
8
+ "eval_rougeLsum": 21.9371,
9
+ "eval_runtime": 203.3789,
10
  "eval_samples": 1500,
11
+ "eval_samples_per_second": 7.375,
12
+ "eval_steps_per_second": 0.738
13
  }
generated_predictions.txt CHANGED
The diff for this file is too large to render. See raw diff
 
predict_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "predict_gen_len": 42.516,
3
- "predict_loss": 2.4928014278411865,
4
- "predict_rouge1": 24.233,
5
- "predict_rouge2": 7.7785,
6
- "predict_rougeL": 17.6919,
7
- "predict_rougeLsum": 21.0741,
8
- "predict_runtime": 186.2282,
9
  "predict_samples": 1500,
10
- "predict_samples_per_second": 8.055,
11
- "predict_steps_per_second": 0.805
12
  }
 
1
  {
2
+ "predict_gen_len": 48.286,
3
+ "predict_loss": 2.4339749813079834,
4
+ "predict_rouge1": 25.7644,
5
+ "predict_rouge2": 8.257,
6
+ "predict_rougeL": 18.3876,
7
+ "predict_rougeLsum": 22.4801,
8
+ "predict_runtime": 206.6659,
9
  "predict_samples": 1500,
10
+ "predict_samples_per_second": 7.258,
11
+ "predict_steps_per_second": 0.726
12
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.01,
3
- "train_loss": 2.8345144271850584,
4
- "train_runtime": 8.6661,
5
  "train_samples": 7000,
6
- "train_samples_per_second": 11.539,
7
- "train_steps_per_second": 1.154
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.648989501953125,
4
+ "train_runtime": 4314.4712,
5
  "train_samples": 7000,
6
+ "train_samples_per_second": 16.224,
7
+ "train_steps_per_second": 1.622
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,109 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.014285714285714285,
5
- "global_step": 10,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.01,
12
- "step": 10,
13
- "total_flos": 52873081651200.0,
14
- "train_loss": 2.8345144271850584,
15
- "train_runtime": 8.6661,
16
- "train_samples_per_second": 11.539,
17
- "train_steps_per_second": 1.154
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
- "max_steps": 10,
21
- "num_train_epochs": 1,
22
- "total_flos": 52873081651200.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 7000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.71,
12
+ "learning_rate": 4.642857142857143e-05,
13
+ "loss": 2.8035,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.43,
18
+ "learning_rate": 4.2857142857142856e-05,
19
+ "loss": 2.7688,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.14,
24
+ "learning_rate": 3.928571428571429e-05,
25
+ "loss": 2.7244,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.86,
30
+ "learning_rate": 3.571428571428572e-05,
31
+ "loss": 2.7084,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 3.57,
36
+ "learning_rate": 3.2142857142857144e-05,
37
+ "loss": 2.6641,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 4.29,
42
+ "learning_rate": 2.857142857142857e-05,
43
+ "loss": 2.6529,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "learning_rate": 2.5e-05,
49
+ "loss": 2.6412,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 5.71,
54
+ "learning_rate": 2.1428571428571428e-05,
55
+ "loss": 2.6125,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 6.43,
60
+ "learning_rate": 1.785714285714286e-05,
61
+ "loss": 2.6094,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 7.14,
66
+ "learning_rate": 1.4285714285714285e-05,
67
+ "loss": 2.5987,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 7.86,
72
+ "learning_rate": 1.0714285714285714e-05,
73
+ "loss": 2.5816,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 8.57,
78
+ "learning_rate": 7.142857142857143e-06,
79
+ "loss": 2.5776,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 9.29,
84
+ "learning_rate": 3.5714285714285714e-06,
85
+ "loss": 2.5766,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 10.0,
90
+ "learning_rate": 0.0,
91
+ "loss": 2.5662,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 10.0,
96
+ "step": 7000,
97
+ "total_flos": 3.701008317136896e+16,
98
+ "train_loss": 2.648989501953125,
99
+ "train_runtime": 4314.4712,
100
+ "train_samples_per_second": 16.224,
101
+ "train_steps_per_second": 1.622
102
  }
103
  ],
104
+ "max_steps": 7000,
105
+ "num_train_epochs": 10,
106
+ "total_flos": 3.701008317136896e+16,
107
  "trial_name": null,
108
  "trial_params": null
109
  }