Hugging Face's logo

balaramas
/
enbnsumm-mT5-XLSumm

Text2Text Generation
Transformers
TensorBoard
Safetensors
English
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
balaramas commited on
Commit
c57c345
•
1 Parent(s): d3d5602

End of training

Browse files
Files changed (4) hide show
  1. README.md +2 -0
  2. all_results.json +4 -4
  3. train_results.json +4 -4
  4. trainer_state.json +8 -8
README.md CHANGED
@@ -1,4 +1,6 @@
1
  ---
 
 
2
  base_model: csebuetnlp/mT5_multilingual_XLSum
3
  tags:
4
  - generated_from_trainer
 
1
  ---
2
+ language:
3
+ - en
4
  base_model: csebuetnlp/mT5_multilingual_XLSum
5
  tags:
6
  - generated_from_trainer
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "train_loss": 4.705486893784153,
4
- "train_runtime": 274.7776,
5
  "train_samples": 11659,
6
- "train_samples_per_second": 212.153,
7
- "train_steps_per_second": 3.33
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "train_loss": 4.84892471396858,
4
+ "train_runtime": 273.84,
5
  "train_samples": 11659,
6
+ "train_samples_per_second": 212.88,
7
+ "train_steps_per_second": 3.341
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "train_loss": 4.705486893784153,
4
- "train_runtime": 274.7776,
5
  "train_samples": 11659,
6
- "train_samples_per_second": 212.153,
7
- "train_steps_per_second": 3.33
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "train_loss": 4.84892471396858,
4
+ "train_runtime": 273.84,
5
  "train_samples": 11659,
6
+ "train_samples_per_second": 212.88,
7
+ "train_steps_per_second": 3.341
8
  }
trainer_state.json CHANGED
@@ -11,18 +11,18 @@
11
  {
12
  "epoch": 2.73,
13
  "grad_norm": NaN,
14
- "learning_rate": 4.989071038251366e-05,
15
- "loss": 8.611,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 5.0,
20
  "step": 915,
21
- "total_flos": 9.163013366795469e+16,
22
- "train_loss": 4.705486893784153,
23
- "train_runtime": 274.7776,
24
- "train_samples_per_second": 212.153,
25
- "train_steps_per_second": 3.33
26
  }
27
  ],
28
  "logging_steps": 500,
@@ -30,7 +30,7 @@
30
  "num_input_tokens_seen": 0,
31
  "num_train_epochs": 5,
32
  "save_steps": 500,
33
- "total_flos": 9.163013366795469e+16,
34
  "train_batch_size": 8,
35
  "trial_name": null,
36
  "trial_params": null
 
11
  {
12
  "epoch": 2.73,
13
  "grad_norm": NaN,
14
+ "learning_rate": 4.9726775956284156e-05,
15
+ "loss": 8.8735,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 5.0,
20
  "step": 915,
21
+ "total_flos": 9.09670937966674e+16,
22
+ "train_loss": 4.84892471396858,
23
+ "train_runtime": 273.84,
24
+ "train_samples_per_second": 212.88,
25
+ "train_steps_per_second": 3.341
26
  }
27
  ],
28
  "logging_steps": 500,
 
30
  "num_input_tokens_seen": 0,
31
  "num_train_epochs": 5,
32
  "save_steps": 500,
33
+ "total_flos": 9.09670937966674e+16,
34
  "train_batch_size": 8,
35
  "trial_name": null,
36
  "trial_params": null