Hugging Face's logo

mamlong34
/
t5_small_race_mutlirc

Transformers
PyTorch
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
2
mamlong34 commited on
Commit
8114f49
·
1 Parent(s): 4d07958

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +8 -8
  2. eval_results.json +6 -5
  3. pytorch_model.bin +1 -1
  4. train_results.json +3 -3
  5. trainer_state.json +15 -15
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.0,
4
- "eval_loss": 6.244291305541992,
5
- "eval_runtime": 107.7226,
6
  "eval_samples": 2985,
7
- "eval_samples_per_second": 27.71,
8
- "eval_steps_per_second": 1.736,
9
  "predict_accuracy": 0.2444,
10
  "predict_loss": 0.7028721570968628,
11
  "predict_runtime": 203.4437,
@@ -13,8 +13,8 @@
13
  "predict_samples_per_second": 24.252,
14
  "predict_steps_per_second": 3.033,
15
  "train_loss": 0.7081544108072917,
16
- "train_runtime": 2765.2923,
17
  "train_samples": 10000,
18
- "train_samples_per_second": 10.849,
19
- "train_steps_per_second": 1.356
20
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.4794,
4
+ "eval_loss": 0.5928728580474854,
5
+ "eval_runtime": 115.0269,
6
  "eval_samples": 2985,
7
+ "eval_samples_per_second": 25.95,
8
+ "eval_steps_per_second": 1.626,
9
  "predict_accuracy": 0.2444,
10
  "predict_loss": 0.7028721570968628,
11
  "predict_runtime": 203.4437,
 
13
  "predict_samples_per_second": 24.252,
14
  "predict_steps_per_second": 3.033,
15
  "train_loss": 0.7081544108072917,
16
+ "train_runtime": 2860.1486,
17
  "train_samples": 10000,
18
+ "train_samples_per_second": 10.489,
19
+ "train_steps_per_second": 1.311
20
  }
eval_results.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "eval_accuracy": 0.0,
3
- "eval_loss": 6.244291305541992,
4
- "eval_runtime": 107.7226,
 
5
  "eval_samples": 2985,
6
- "eval_samples_per_second": 27.71,
7
- "eval_steps_per_second": 1.736
8
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.4794,
4
+ "eval_loss": 0.5928728580474854,
5
+ "eval_runtime": 115.0269,
6
  "eval_samples": 2985,
7
+ "eval_samples_per_second": 25.95,
8
+ "eval_steps_per_second": 1.626
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a69408b2000d0982b70d0dbb16d772101d41e91299a1370f6c54876ac45061
3
  size 242028283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d568637697abb9b9b6fd784a19e6aa35ab7753d138a0c9f2c89f1a5edd20ea3
3
  size 242028283
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 0.7081544108072917,
4
- "train_runtime": 2765.2923,
5
  "train_samples": 10000,
6
- "train_samples_per_second": 10.849,
7
- "train_steps_per_second": 1.356
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 0.7081544108072917,
4
+ "train_runtime": 2860.1486,
5
  "train_samples": 10000,
6
+ "train_samples_per_second": 10.489,
7
+ "train_steps_per_second": 1.311
8
  }
trainer_state.json CHANGED
@@ -21,11 +21,11 @@
21
  },
22
  {
23
  "epoch": 1.0,
24
- "eval_accuracy": 0.2898,
25
  "eval_loss": 0.6522298455238342,
26
- "eval_runtime": 114.6166,
27
- "eval_samples_per_second": 26.043,
28
- "eval_steps_per_second": 1.632,
29
  "step": 1250
30
  },
31
  {
@@ -48,11 +48,11 @@
48
  },
49
  {
50
  "epoch": 2.0,
51
- "eval_accuracy": 0.3481,
52
  "eval_loss": 0.6009056568145752,
53
- "eval_runtime": 115.1828,
54
- "eval_samples_per_second": 25.915,
55
- "eval_steps_per_second": 1.624,
56
  "step": 2500
57
  },
58
  {
@@ -69,11 +69,11 @@
69
  },
70
  {
71
  "epoch": 3.0,
72
- "eval_accuracy": 0.3494,
73
  "eval_loss": 0.5928728580474854,
74
- "eval_runtime": 115.1339,
75
- "eval_samples_per_second": 25.926,
76
- "eval_steps_per_second": 1.624,
77
  "step": 3750
78
  },
79
  {
@@ -81,9 +81,9 @@
81
  "step": 3750,
82
  "total_flos": 4060254044160000.0,
83
  "train_loss": 0.7081544108072917,
84
- "train_runtime": 2765.2923,
85
- "train_samples_per_second": 10.849,
86
- "train_steps_per_second": 1.356
87
  }
88
  ],
89
  "max_steps": 3750,
 
21
  },
22
  {
23
  "epoch": 1.0,
24
+ "eval_accuracy": 0.396,
25
  "eval_loss": 0.6522298455238342,
26
+ "eval_runtime": 115.0329,
27
+ "eval_samples_per_second": 25.949,
28
+ "eval_steps_per_second": 1.626,
29
  "step": 1250
30
  },
31
  {
 
48
  },
49
  {
50
  "epoch": 2.0,
51
+ "eval_accuracy": 0.4693,
52
  "eval_loss": 0.6009056568145752,
53
+ "eval_runtime": 115.9298,
54
+ "eval_samples_per_second": 25.748,
55
+ "eval_steps_per_second": 1.613,
56
  "step": 2500
57
  },
58
  {
 
69
  },
70
  {
71
  "epoch": 3.0,
72
+ "eval_accuracy": 0.4794,
73
  "eval_loss": 0.5928728580474854,
74
+ "eval_runtime": 114.8963,
75
+ "eval_samples_per_second": 25.98,
76
+ "eval_steps_per_second": 1.628,
77
  "step": 3750
78
  },
79
  {
 
81
  "step": 3750,
82
  "total_flos": 4060254044160000.0,
83
  "train_loss": 0.7081544108072917,
84
+ "train_runtime": 2860.1486,
85
+ "train_samples_per_second": 10.489,
86
+ "train_steps_per_second": 1.311
87
  }
88
  ],
89
  "max_steps": 3750,