Hugging Face's logo

craa
/
100M_low_2000_634

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
craa commited on
Commit
aaffaf8
·
verified ·
1 Parent(s): ccf6459

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": 0.39387280288921067,
4
- "eval_loss": 3.305699110031128,
5
- "eval_runtime": 179.5166,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 100.331,
8
- "eval_steps_per_second": 6.272,
9
- "perplexity": 27.26759797803971,
10
- "total_flos": 7.7681598529536e+17,
11
- "train_loss": 3.4587742451663783,
12
- "train_runtime": 80154.8404,
13
- "train_samples": 297298,
14
- "train_samples_per_second": 37.09,
15
- "train_steps_per_second": 1.159
16
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.3946354375087805,
4
+ "eval_loss": 3.299715518951416,
5
+ "eval_runtime": 183.1224,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 98.355,
8
+ "eval_steps_per_second": 6.149,
9
+ "perplexity": 27.10492698570954,
10
+ "total_flos": 7.75449427968e+17,
11
+ "train_loss": 3.4498943302123695,
12
+ "train_runtime": 79544.4067,
13
+ "train_samples": 296775,
14
+ "train_samples_per_second": 37.309,
15
+ "train_steps_per_second": 1.166
16
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_accuracy": 0.39387280288921067,
4
- "eval_loss": 3.305699110031128,
5
- "eval_runtime": 179.5166,
6
  "eval_samples": 18011,
7
- "eval_samples_per_second": 100.331,
8
- "eval_steps_per_second": 6.272,
9
- "perplexity": 27.26759797803971
10
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.3946354375087805,
4
+ "eval_loss": 3.299715518951416,
5
+ "eval_runtime": 183.1224,
6
  "eval_samples": 18011,
7
+ "eval_samples_per_second": 98.355,
8
+ "eval_steps_per_second": 6.149,
9
+ "perplexity": 27.10492698570954
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5d4ce95ce8a9cb91d00bd60122c0ffdff7cb2c7f9855cabff67da7e219c68d6
3
  size 503128704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f0c795d62e474da5296b29fa86cb6ef2549c87bdee8a98d18c253175eec040
3
  size 503128704
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 10.0,
3
- "total_flos": 7.7681598529536e+17,
4
- "train_loss": 3.4587742451663783,
5
- "train_runtime": 80154.8404,
6
- "train_samples": 297298,
7
- "train_samples_per_second": 37.09,
8
- "train_steps_per_second": 1.159
9
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "total_flos": 7.75449427968e+17,
4
+ "train_loss": 3.4498943302123695,
5
+ "train_runtime": 79544.4067,
6
+ "train_samples": 296775,
7
+ "train_samples_per_second": 37.309,
8
+ "train_steps_per_second": 1.166
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 sha256:6f70a211759452569c4a583d57df8ecf1cd8848934be54c26401d6bef277c4f7
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cea46ac48e47e917c5082d75f976b7d8ac5df4e115c0cfc62b771f02e97213d
3
  size 5304