Hugging Face's logo

craa
/
100M_low_2000_495

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
craa commited on
Commit
dffbb17
·
verified ·
1 Parent(s): fb5a120

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. all_results.json +7 -7
  3. eval_results.json +3 -3
  4. train_results.json +4 -4
  5. trainer_state.json +0 -0
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 3.2966
20
- - Accuracy: 0.3949
21
 
22
  ## Model description
23
 
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 3.3084
20
+ - Accuracy: 0.3936
21
 
22
  ## Model description
23
 
all_results.json CHANGED
@@ -2,15 +2,15 @@
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.3935781362574578,
4
  "eval_loss": 3.308422088623047,
5
- "eval_runtime": 180.1172,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 99.996,
8
- "eval_steps_per_second": 6.251,
9
  "perplexity": 27.341948244739367,
10
  "total_flos": 7.7681598529536e+17,
11
- "train_loss": 3.46011078748004,
12
- "train_runtime": 80911.2202,
13
  "train_samples": 297298,
14
- "train_samples_per_second": 36.744,
15
- "train_steps_per_second": 1.148
16
  }
 
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.3935781362574578,
4
  "eval_loss": 3.308422088623047,
5
+ "eval_runtime": 181.498,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 99.235,
8
+ "eval_steps_per_second": 6.204,
9
  "perplexity": 27.341948244739367,
10
  "total_flos": 7.7681598529536e+17,
11
+ "train_loss": 3.4552165603473464,
12
+ "train_runtime": 80467.4262,
13
  "train_samples": 297298,
14
+ "train_samples_per_second": 36.946,
15
+ "train_steps_per_second": 1.155
16
  }
eval_results.json CHANGED
@@ -2,9 +2,9 @@
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.3935781362574578,
4
  "eval_loss": 3.308422088623047,
5
- "eval_runtime": 180.1172,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 99.996,
8
- "eval_steps_per_second": 6.251,
9
  "perplexity": 27.341948244739367
10
  }
 
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.3935781362574578,
4
  "eval_loss": 3.308422088623047,
5
+ "eval_runtime": 181.498,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 99.235,
8
+ "eval_steps_per_second": 6.204,
9
  "perplexity": 27.341948244739367
10
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 10.0,
3
  "total_flos": 7.7681598529536e+17,
4
- "train_loss": 3.46011078748004,
5
- "train_runtime": 80911.2202,
6
  "train_samples": 297298,
7
- "train_samples_per_second": 36.744,
8
- "train_steps_per_second": 1.148
9
  }
 
1
  {
2
  "epoch": 10.0,
3
  "total_flos": 7.7681598529536e+17,
4
+ "train_loss": 3.4552165603473464,
5
+ "train_runtime": 80467.4262,
6
  "train_samples": 297298,
7
+ "train_samples_per_second": 36.946,
8
+ "train_steps_per_second": 1.155
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff