Hugging Face's logo

AlekseyKorshuk
/
amazon-reviews-input-output

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
AlekseyKorshuk commited on
Commit
657f216
·
1 Parent(s): 60a1e0b

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +9 -9
  2. eval_results.json +7 -6
  3. train_results.json +3 -3
  4. trainer_state.json +6 -6
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "epoch": 0.99,
3
- "eval_accuracy": 0.003719512195121951,
4
- "eval_loss": 13.134621620178223,
5
- "eval_runtime": 8.1166,
6
  "eval_samples": 100,
7
- "eval_samples_per_second": 12.32,
8
- "eval_steps_per_second": 0.493,
9
- "perplexity": 506166.8414857262,
10
  "train_loss": 1.0375519144919612,
11
- "train_runtime": 119.5105,
12
  "train_samples": 1000,
13
- "train_samples_per_second": 8.367,
14
- "train_steps_per_second": 0.259
15
  }
 
1
  {
2
  "epoch": 0.99,
3
+ "eval_accuracy": 0.08528455284552845,
4
+ "eval_loss": 0.20656633377075195,
5
+ "eval_runtime": 2.2263,
6
  "eval_samples": 100,
7
+ "eval_samples_per_second": 44.917,
8
+ "eval_steps_per_second": 1.797,
9
+ "perplexity": 1.2294492855192867,
10
  "train_loss": 1.0375519144919612,
11
+ "train_runtime": 120.7864,
12
  "train_samples": 1000,
13
+ "train_samples_per_second": 8.279,
14
+ "train_steps_per_second": 0.257
15
  }
eval_results.json CHANGED
@@ -1,9 +1,10 @@
1
  {
2
- "eval_accuracy": 0.003719512195121951,
3
- "eval_loss": 13.134621620178223,
4
- "eval_runtime": 8.1166,
 
5
  "eval_samples": 100,
6
- "eval_samples_per_second": 12.32,
7
- "eval_steps_per_second": 0.493,
8
- "perplexity": 506166.8414857262
9
  }
 
1
  {
2
+ "epoch": 0.99,
3
+ "eval_accuracy": 0.08528455284552845,
4
+ "eval_loss": 0.20656633377075195,
5
+ "eval_runtime": 2.2263,
6
  "eval_samples": 100,
7
+ "eval_samples_per_second": 44.917,
8
+ "eval_steps_per_second": 1.797,
9
+ "perplexity": 1.2294492855192867
10
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.99,
3
  "train_loss": 1.0375519144919612,
4
- "train_runtime": 119.5105,
5
  "train_samples": 1000,
6
- "train_samples_per_second": 8.367,
7
- "train_steps_per_second": 0.259
8
  }
 
1
  {
2
  "epoch": 0.99,
3
  "train_loss": 1.0375519144919612,
4
+ "train_runtime": 120.7864,
5
  "train_samples": 1000,
6
+ "train_samples_per_second": 8.279,
7
+ "train_steps_per_second": 0.257
8
  }
trainer_state.json CHANGED
@@ -23,9 +23,9 @@
23
  "epoch": 0.8,
24
  "eval_accuracy": 0.0851829268292683,
25
  "eval_loss": 0.21037571132183075,
26
- "eval_runtime": 1.8873,
27
- "eval_samples_per_second": 52.986,
28
- "eval_steps_per_second": 2.119,
29
  "step": 25
30
  },
31
  {
@@ -33,9 +33,9 @@
33
  "step": 31,
34
  "total_flos": 938904995758080.0,
35
  "train_loss": 1.0375519144919612,
36
- "train_runtime": 119.5105,
37
- "train_samples_per_second": 8.367,
38
- "train_steps_per_second": 0.259
39
  }
40
  ],
41
  "max_steps": 31,
 
23
  "epoch": 0.8,
24
  "eval_accuracy": 0.0851829268292683,
25
  "eval_loss": 0.21037571132183075,
26
+ "eval_runtime": 2.0103,
27
+ "eval_samples_per_second": 49.743,
28
+ "eval_steps_per_second": 1.99,
29
  "step": 25
30
  },
31
  {
 
33
  "step": 31,
34
  "total_flos": 938904995758080.0,
35
  "train_loss": 1.0375519144919612,
36
+ "train_runtime": 120.7864,
37
+ "train_samples_per_second": 8.279,
38
+ "train_steps_per_second": 0.257
39
  }
40
  ],
41
  "max_steps": 31,