Hugging Face's logo

navjordj
/
flan-t5-small_en-no

Text2Text Generation
Transformers
PyTorch
English
Norwegian
t5
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
2
navjordj commited on
Commit
fc36c55
•
1 Parent(s): 3fc6933

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +6 -6
  2. eval_results.json +2 -2
  3. train_results.json +4 -4
  4. trainer_state.json +4 -4
all_results.json CHANGED
@@ -3,13 +3,13 @@
3
  "eval_bleu": 10.9236,
4
  "eval_gen_len": 79.2493,
5
  "eval_loss": 1.7087136507034302,
6
- "eval_runtime": 177.7595,
7
  "eval_samples": 12422,
8
- "eval_samples_per_second": 69.881,
9
  "eval_steps_per_second": 0.551,
10
- "train_loss": 2.27133990001286,
11
- "train_runtime": 2909.2317,
12
  "train_samples": 62107,
13
- "train_samples_per_second": 213.482,
14
- "train_steps_per_second": 0.835
15
  }
 
3
  "eval_bleu": 10.9236,
4
  "eval_gen_len": 79.2493,
5
  "eval_loss": 1.7087136507034302,
6
+ "eval_runtime": 178.0196,
7
  "eval_samples": 12422,
8
+ "eval_samples_per_second": 69.779,
9
  "eval_steps_per_second": 0.551,
10
+ "train_loss": 0.35158030819991,
11
+ "train_runtime": 504.822,
12
  "train_samples": 62107,
13
+ "train_samples_per_second": 1230.275,
14
+ "train_steps_per_second": 4.814
15
  }
eval_results.json CHANGED
@@ -3,8 +3,8 @@
3
  "eval_bleu": 10.9236,
4
  "eval_gen_len": 79.2493,
5
  "eval_loss": 1.7087136507034302,
6
- "eval_runtime": 177.7595,
7
  "eval_samples": 12422,
8
- "eval_samples_per_second": 69.881,
9
  "eval_steps_per_second": 0.551
10
  }
 
3
  "eval_bleu": 10.9236,
4
  "eval_gen_len": 79.2493,
5
  "eval_loss": 1.7087136507034302,
6
+ "eval_runtime": 178.0196,
7
  "eval_samples": 12422,
8
+ "eval_samples_per_second": 69.779,
9
  "eval_steps_per_second": 0.551
10
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "train_loss": 2.27133990001286,
4
- "train_runtime": 2909.2317,
5
  "train_samples": 62107,
6
- "train_samples_per_second": 213.482,
7
- "train_steps_per_second": 0.835
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "train_loss": 0.35158030819991,
4
+ "train_runtime": 504.822,
5
  "train_samples": 62107,
6
+ "train_samples_per_second": 1230.275,
7
+ "train_steps_per_second": 4.814
8
  }
trainer_state.json CHANGED
@@ -35,10 +35,10 @@
35
  "epoch": 10.0,
36
  "step": 2430,
37
  "total_flos": 2.2677509529759744e+16,
38
- "train_loss": 2.27133990001286,
39
- "train_runtime": 2909.2317,
40
- "train_samples_per_second": 213.482,
41
- "train_steps_per_second": 0.835
42
  }
43
  ],
44
  "max_steps": 2430,
 
35
  "epoch": 10.0,
36
  "step": 2430,
37
  "total_flos": 2.2677509529759744e+16,
38
+ "train_loss": 0.35158030819991,
39
+ "train_runtime": 504.822,
40
+ "train_samples_per_second": 1230.275,
41
+ "train_steps_per_second": 4.814
42
  }
43
  ],
44
  "max_steps": 2430,