Hugging Face's logo

AleBurzio
/
long-t5-base-govreport

Summarization
Transformers
PyTorch
English
longt5
text2text-generation
Generated from Trainer
gov report
long document
Inference Endpoints
Model card Files Community
5
AleBurzio commited on
Commit
25e596b
•
1 Parent(s): c846433

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +15 -9
  2. eval_results.json +10 -9
  3. train_results.json +8 -0
  4. trainer_state.json +10 -1
all_results.json CHANGED
@@ -1,12 +1,18 @@
1
  {
2
- "eval_gen_len": 797.712,
3
- "eval_loss": 1.8528449535369873,
4
- "eval_rouge1": 41.5534,
5
- "eval_rouge2": 12.208,
6
- "eval_rougeL": 18.6433,
7
- "eval_rougeLsum": 37.1885,
8
- "eval_runtime": 880.2631,
 
9
  "eval_samples": 250,
10
- "eval_samples_per_second": 0.284,
11
- "eval_steps_per_second": 0.284
 
 
 
 
 
12
  }
 
1
  {
2
+ "epoch": 13.28,
3
+ "eval_gen_len": 787.34,
4
+ "eval_loss": 1.5448322296142578,
5
+ "eval_rouge1": 57.2303,
6
+ "eval_rouge2": 24.9705,
7
+ "eval_rougeL": 26.8081,
8
+ "eval_rougeLsum": 54.2747,
9
+ "eval_runtime": 853.5909,
10
  "eval_samples": 250,
11
+ "eval_samples_per_second": 0.293,
12
+ "eval_steps_per_second": 0.293,
13
+ "train_loss": 0.0,
14
+ "train_runtime": 2.117,
15
+ "train_samples": 8200,
16
+ "train_samples_per_second": 96836.906,
17
+ "train_steps_per_second": 247.997
18
  }
eval_results.json CHANGED
@@ -1,12 +1,13 @@
1
  {
2
- "eval_gen_len": 797.712,
3
- "eval_loss": 1.8528449535369873,
4
- "eval_rouge1": 41.5534,
5
- "eval_rouge2": 12.208,
6
- "eval_rougeL": 18.6433,
7
- "eval_rougeLsum": 37.1885,
8
- "eval_runtime": 880.2631,
 
9
  "eval_samples": 250,
10
- "eval_samples_per_second": 0.284,
11
- "eval_steps_per_second": 0.284
12
  }
 
1
  {
2
+ "epoch": 13.28,
3
+ "eval_gen_len": 787.34,
4
+ "eval_loss": 1.5448322296142578,
5
+ "eval_rouge1": 57.2303,
6
+ "eval_rouge2": 24.9705,
7
+ "eval_rougeL": 26.8081,
8
+ "eval_rougeLsum": 54.2747,
9
+ "eval_runtime": 853.5909,
10
  "eval_samples": 250,
11
+ "eval_samples_per_second": 0.293,
12
+ "eval_steps_per_second": 0.293
13
  }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 13.28,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 2.117,
5
+ "train_samples": 8200,
6
+ "train_samples_per_second": 96836.906,
7
+ "train_steps_per_second": 247.997
8
+ }
trainer_state.json CHANGED
@@ -5548,9 +5548,18 @@
5548
  "eval_samples_per_second": 0.287,
5549
  "eval_steps_per_second": 0.287,
5550
  "step": 850
 
 
 
 
 
 
 
 
 
5551
  }
5552
  ],
5553
- "max_steps": 1600,
5554
  "num_train_epochs": 25,
5555
  "total_flos": 1.193214367236096e+18,
5556
  "trial_name": null,
 
5548
  "eval_samples_per_second": 0.287,
5549
  "eval_steps_per_second": 0.287,
5550
  "step": 850
5551
+ },
5552
+ {
5553
+ "epoch": 13.28,
5554
+ "step": 850,
5555
+ "total_flos": 1.193214367236096e+18,
5556
+ "train_loss": 0.0,
5557
+ "train_runtime": 2.117,
5558
+ "train_samples_per_second": 96836.906,
5559
+ "train_steps_per_second": 247.997
5560
  }
5561
  ],
5562
+ "max_steps": 525,
5563
  "num_train_epochs": 25,
5564
  "total_flos": 1.193214367236096e+18,
5565
  "trial_name": null,