Hugging Face's logo

mpapucci
/
it5-multitask-classification-topic-age-gender-tag-it

Text2Text Generation
Transformers
PyTorch
Italian
t5
Text Classification
Inference Endpoints
text-generation-inference
Model card Files Community
1
mpapucci commited on
Commit
ed02c05
•
1 Parent(s): f87158e

re-trained mutlitask model to align it with the singletask ones

Browse files
Files changed (5) hide show
  1. all_results.json +4 -4
  2. pytorch_model.bin +0 -3
  3. train_results.json +4 -4
  4. trainer_state.json +6 -6
  5. training_args.bin +0 -0
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 1.0506418329673728e+16,
4
- "train_loss": 1.2171453878437424,
5
- "train_runtime": 2739.982,
6
  "train_samples": 32526,
7
- "train_samples_per_second": 23.742,
8
- "train_steps_per_second": 2.968
9
  }
 
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 1.0506418329673728e+16,
4
+ "train_loss": 1.2627147819042441,
5
+ "train_runtime": 2692.7589,
6
  "train_samples": 32526,
7
+ "train_samples_per_second": 24.158,
8
+ "train_steps_per_second": 3.02
9
  }
pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3eaa0d748919f005e35eacce9d318c2c877d5927c80de9aa517279ea615dfbb
3
- size 990253005
 
 
 
 
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 1.0506418329673728e+16,
4
- "train_loss": 1.2171453878437424,
5
- "train_runtime": 2739.982,
6
  "train_samples": 32526,
7
- "train_samples_per_second": 23.742,
8
- "train_steps_per_second": 2.968
9
  }
 
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 1.0506418329673728e+16,
4
+ "train_loss": 1.2627147819042441,
5
+ "train_runtime": 2692.7589,
6
  "train_samples": 32526,
7
+ "train_samples_per_second": 24.158,
8
+ "train_steps_per_second": 3.02
9
  }
trainer_state.json CHANGED
@@ -10,23 +10,23 @@
10
  {
11
  "epoch": 1.0,
12
  "learning_rate": 5e-06,
13
- "loss": 2.0403,
14
  "step": 4066
15
  },
16
  {
17
  "epoch": 2.0,
18
  "learning_rate": 0.0,
19
- "loss": 0.394,
20
  "step": 8132
21
  },
22
  {
23
  "epoch": 2.0,
24
  "step": 8132,
25
  "total_flos": 1.0506418329673728e+16,
26
- "train_loss": 1.2171453878437424,
27
- "train_runtime": 2739.982,
28
- "train_samples_per_second": 23.742,
29
- "train_steps_per_second": 2.968
30
  }
31
  ],
32
  "max_steps": 8132,
 
10
  {
11
  "epoch": 1.0,
12
  "learning_rate": 5e-06,
13
+ "loss": 2.1304,
14
  "step": 4066
15
  },
16
  {
17
  "epoch": 2.0,
18
  "learning_rate": 0.0,
19
+ "loss": 0.395,
20
  "step": 8132
21
  },
22
  {
23
  "epoch": 2.0,
24
  "step": 8132,
25
  "total_flos": 1.0506418329673728e+16,
26
+ "train_loss": 1.2627147819042441,
27
+ "train_runtime": 2692.7589,
28
+ "train_samples_per_second": 24.158,
29
+ "train_steps_per_second": 3.02
30
  }
31
  ],
32
  "max_steps": 8132,
training_args.bin CHANGED
Binary files a/training_args.bin and b/training_args.bin differ