Hugging Face's logo

balaramas
/
mt5-hihi

Transformers
Safetensors
mt5
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
balaramas commited on
Commit
3fa0a23
·
verified ·
1 Parent(s): 36745e7

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +15 -9
  2. generated_predictions.txt +0 -0
  3. generation_config.json +0 -1
  4. predict_results.json +9 -9
  5. train_results.json +8 -0
  6. trainer_state.json +114 -0
all_results.json CHANGED
@@ -1,12 +1,18 @@
1
  {
2
- "predict_gen_len": 52.7633955448525,
3
- "predict_loss": 3.9636030197143555,
4
- "predict_rouge1": 0.1906,
5
- "predict_rouge2": 0.0401,
6
- "predict_rougeL": 0.1886,
7
- "predict_rougeLsum": 0.1886,
8
- "predict_runtime": 234.4913,
 
9
  "predict_samples": 1661,
10
- "predict_samples_per_second": 7.083,
11
- "predict_steps_per_second": 0.222
 
 
 
 
 
12
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "predict_gen_len": 114.25285972305839,
4
+ "predict_loss": 1.9146976470947266,
5
+ "predict_rouge1": 5.2479,
6
+ "predict_rouge2": 1.8139,
7
+ "predict_rougeL": 5.1695,
8
+ "predict_rougeLsum": 5.1641,
9
+ "predict_runtime": 670.5406,
10
  "predict_samples": 1661,
11
+ "predict_samples_per_second": 2.477,
12
+ "predict_steps_per_second": 1.239,
13
+ "train_loss": 1.3815043066249624,
14
+ "train_runtime": 3193.6495,
15
+ "train_samples": 14964,
16
+ "train_samples_per_second": 4.686,
17
+ "train_steps_per_second": 2.343
18
  }
generated_predictions.txt CHANGED
The diff for this file is too large to render. See raw diff
 
generation_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_from_model_config": true,
3
  "decoder_start_token_id": 250021,
4
  "eos_token_id": 1,
5
  "length_penalty": 0.6,
 
1
  {
 
2
  "decoder_start_token_id": 250021,
3
  "eos_token_id": 1,
4
  "length_penalty": 0.6,
predict_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "predict_gen_len": 52.7633955448525,
3
- "predict_loss": 3.9636030197143555,
4
- "predict_rouge1": 0.1906,
5
- "predict_rouge2": 0.0401,
6
- "predict_rougeL": 0.1886,
7
- "predict_rougeLsum": 0.1886,
8
- "predict_runtime": 234.4913,
9
  "predict_samples": 1661,
10
- "predict_samples_per_second": 7.083,
11
- "predict_steps_per_second": 0.222
12
  }
 
1
  {
2
+ "predict_gen_len": 114.25285972305839,
3
+ "predict_loss": 1.9146976470947266,
4
+ "predict_rouge1": 5.2479,
5
+ "predict_rouge2": 1.8139,
6
+ "predict_rougeL": 5.1695,
7
+ "predict_rougeLsum": 5.1641,
8
+ "predict_runtime": 670.5406,
9
  "predict_samples": 1661,
10
+ "predict_samples_per_second": 2.477,
11
+ "predict_steps_per_second": 1.239
12
  }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.3815043066249624,
4
+ "train_runtime": 3193.6495,
5
+ "train_samples": 14964,
6
+ "train_samples_per_second": 4.686,
7
+ "train_steps_per_second": 2.343
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7482,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07,
13
+ "learning_rate": 4.665864742047581e-05,
14
+ "loss": 1.7562,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.13,
19
+ "learning_rate": 4.331729484095162e-05,
20
+ "loss": 1.526,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.2,
25
+ "learning_rate": 3.997594226142743e-05,
26
+ "loss": 1.4549,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.27,
31
+ "learning_rate": 3.663458968190324e-05,
32
+ "loss": 1.434,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.33,
37
+ "learning_rate": 3.3293237102379046e-05,
38
+ "loss": 1.3931,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.4,
43
+ "learning_rate": 2.995188452285485e-05,
44
+ "loss": 1.3762,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.47,
49
+ "learning_rate": 2.6610531943330663e-05,
50
+ "loss": 1.3459,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.53,
55
+ "learning_rate": 2.326917936380647e-05,
56
+ "loss": 1.314,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.6,
61
+ "learning_rate": 1.9927826784282277e-05,
62
+ "loss": 1.3203,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.67,
67
+ "learning_rate": 1.658647420475809e-05,
68
+ "loss": 1.3109,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.74,
73
+ "learning_rate": 1.3245121625233894e-05,
74
+ "loss": 1.3052,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.8,
79
+ "learning_rate": 9.903769045709705e-06,
80
+ "loss": 1.2921,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.87,
85
+ "learning_rate": 6.562416466185513e-06,
86
+ "loss": 1.2959,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.94,
91
+ "learning_rate": 3.2210638866613206e-06,
92
+ "loss": 1.2986,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "step": 7482,
98
+ "total_flos": 2.662634158119936e+16,
99
+ "train_loss": 1.3815043066249624,
100
+ "train_runtime": 3193.6495,
101
+ "train_samples_per_second": 4.686,
102
+ "train_steps_per_second": 2.343
103
+ }
104
+ ],
105
+ "logging_steps": 500,
106
+ "max_steps": 7482,
107
+ "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 1,
109
+ "save_steps": 500,
110
+ "total_flos": 2.662634158119936e+16,
111
+ "train_batch_size": 2,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }