Hugging Face's logo

craa
/
100M_low_1000_6910

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
craa commited on
Commit
5ed5e1d
·
verified ·
1 Parent(s): c655658

Training in progress, step 10000

Browse files
Files changed (6) hide show
  1. all_results.json +12 -12
  2. eval_results.json +6 -6
  3. model.safetensors +1 -1
  4. train_results.json +6 -6
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_accuracy": 0.3932824917497146,
4
- "eval_loss": 3.3091650009155273,
5
- "eval_runtime": 184.8493,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 97.436,
8
- "eval_steps_per_second": 6.091,
9
- "perplexity": 27.3622684613255,
10
- "total_flos": 7.7681859821568e+17,
11
- "train_loss": 3.468291573590681,
12
- "train_runtime": 80362.6457,
13
- "train_samples": 297299,
14
- "train_samples_per_second": 36.995,
15
- "train_steps_per_second": 1.156
16
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.3945585112642079,
4
+ "eval_loss": 3.3003323078155518,
5
+ "eval_runtime": 183.9415,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.917,
8
+ "eval_steps_per_second": 6.122,
9
+ "perplexity": 27.1216501596411,
10
+ "total_flos": 7.75449427968e+17,
11
+ "train_loss": 3.4540262829556942,
12
+ "train_runtime": 79697.0382,
13
+ "train_samples": 296775,
14
+ "train_samples_per_second": 37.238,
15
+ "train_steps_per_second": 1.164
16
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_accuracy": 0.3932824917497146,
4
- "eval_loss": 3.3091650009155273,
5
- "eval_runtime": 184.8493,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 97.436,
8
- "eval_steps_per_second": 6.091,
9
- "perplexity": 27.3622684613255
10
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.3945585112642079,
4
+ "eval_loss": 3.3003323078155518,
5
+ "eval_runtime": 183.9415,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 97.917,
8
+ "eval_steps_per_second": 6.122,
9
+ "perplexity": 27.1216501596411
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ba445d5f7bde0bdc1450a61d9dc6d9911dd68570309d06b0e848348c074bba5
3
  size 503128704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8cbe6c7ebe3b4d9f3b05c1cba622f285527d797b137af3778eeece3685aee08
3
  size 503128704
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 10.0,
3
- "total_flos": 7.7681859821568e+17,
4
- "train_loss": 3.468291573590681,
5
- "train_runtime": 80362.6457,
6
- "train_samples": 297299,
7
- "train_samples_per_second": 36.995,
8
- "train_steps_per_second": 1.156
9
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "total_flos": 7.75449427968e+17,
4
+ "train_loss": 3.4540262829556942,
5
+ "train_runtime": 79697.0382,
6
+ "train_samples": 296775,
7
+ "train_samples_per_second": 37.238,
8
+ "train_steps_per_second": 1.164
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f812bd3f0270a8ded86620a14962545283d1ba25bb404bbc09c145e1c4b17dc
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
3
  size 5304