Hugging Face's logo

navjordj
/
snl-summarization

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
navjordj commited on
Commit
0ac986c
•
1 Parent(s): 3a13582

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +15 -5
  2. generated_predictions.txt +0 -0
  3. generation_config.json +0 -1
  4. predict_results.json +12 -0
  5. train_results.json +5 -5
  6. trainer_state.json +26 -14
all_results.json CHANGED
@@ -1,8 +1,18 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 2.9761986998923713,
4
- "train_runtime": 1278.1344,
 
 
 
 
 
 
 
 
 
 
5
  "train_samples": 11044,
6
- "train_samples_per_second": 25.922,
7
- "train_steps_per_second": 0.406
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "predict_gen_len": 45.68034889687019,
4
+ "predict_loss": 2.10367488861084,
5
+ "predict_rouge1": 31.8781,
6
+ "predict_rouge2": 14.0329,
7
+ "predict_rougeL": 27.5321,
8
+ "predict_rougeLsum": 29.6372,
9
+ "predict_runtime": 175.8488,
10
+ "predict_samples": 1949,
11
+ "predict_samples_per_second": 11.083,
12
+ "predict_steps_per_second": 0.347,
13
+ "train_loss": 2.6604936368203576,
14
+ "train_runtime": 4208.1526,
15
  "train_samples": 11044,
16
+ "train_samples_per_second": 26.244,
17
+ "train_steps_per_second": 0.411
18
  }
generated_predictions.txt ADDED
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": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
 
1
  {
 
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
predict_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_gen_len": 45.68034889687019,
3
+ "predict_loss": 2.10367488861084,
4
+ "predict_rouge1": 31.8781,
5
+ "predict_rouge2": 14.0329,
6
+ "predict_rougeL": 27.5321,
7
+ "predict_rougeLsum": 29.6372,
8
+ "predict_runtime": 175.8488,
9
+ "predict_samples": 1949,
10
+ "predict_samples_per_second": 11.083,
11
+ "predict_steps_per_second": 0.347
12
+ }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 2.9761986998923713,
4
- "train_runtime": 1278.1344,
5
  "train_samples": 11044,
6
- "train_samples_per_second": 25.922,
7
- "train_steps_per_second": 0.406
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.6604936368203576,
4
+ "train_runtime": 4208.1526,
5
  "train_samples": 11044,
6
+ "train_samples_per_second": 26.244,
7
+ "train_steps_per_second": 0.411
8
  }
trainer_state.json CHANGED
@@ -1,31 +1,43 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.0,
5
- "global_step": 519,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 2.89,
12
- "learning_rate": 1.8304431599229288e-06,
13
- "loss": 2.984,
14
  "step": 500
15
  },
16
  {
17
- "epoch": 3.0,
18
- "step": 519,
19
- "total_flos": 7.945359287176397e+16,
20
- "train_loss": 2.9761986998923713,
21
- "train_runtime": 1278.1344,
22
- "train_samples_per_second": 25.922,
23
- "train_steps_per_second": 0.406
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
- "max_steps": 519,
27
- "num_train_epochs": 3,
28
- "total_flos": 7.945359287176397e+16,
29
  "trial_name": null,
30
  "trial_params": null
31
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 1730,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 2.89,
12
+ "learning_rate": 3.554913294797688e-05,
13
+ "loss": 2.962,
14
  "step": 500
15
  },
16
  {
17
+ "epoch": 5.78,
18
+ "learning_rate": 2.1098265895953757e-05,
19
+ "loss": 2.596,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 8.67,
24
+ "learning_rate": 6.647398843930635e-06,
25
+ "loss": 2.5038,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 10.0,
30
+ "step": 1730,
31
+ "total_flos": 2.648315673797714e+17,
32
+ "train_loss": 2.6604936368203576,
33
+ "train_runtime": 4208.1526,
34
+ "train_samples_per_second": 26.244,
35
+ "train_steps_per_second": 0.411
36
  }
37
  ],
38
+ "max_steps": 1730,
39
+ "num_train_epochs": 10,
40
+ "total_flos": 2.648315673797714e+17,
41
  "trial_name": null,
42
  "trial_params": null
43
  }