Hugging Face's logo

BluebrainAI
/
rotating-head-gp-gpt2-medium-wikitext

Feature Extraction
Transformers
Safetensors
rotating-head-gpt2
Generated from Trainer
custom_code
Model card Files Community
shivanandmn commited on
Commit
958f85b
·
verified ·
1 Parent(s): 7079385

Training in progress, step 11000

Browse files
Files changed (6) hide show
  1. all_results.json +7 -7
  2. eval_results.json +3 -3
  3. model.safetensors +1 -1
  4. train_results.json +4 -4
  5. trainer_state.json +4 -4
  6. training_args.bin +1 -1
all_results.json CHANGED
@@ -4,14 +4,14 @@
4
  "eval_bleu": 0.1323262570770995,
5
  "eval_loss": 3.1777124404907227,
6
  "eval_perplexity": 23.991808041831927,
7
- "eval_runtime": 12.2078,
8
  "eval_samples": 1141,
9
- "eval_samples_per_second": 93.465,
10
- "eval_steps_per_second": 1.474,
11
  "perplexity": 23.991808041831927,
12
  "total_flos": 1.270447321217237e+18,
13
- "train_loss": 0.5092627385828409,
14
- "train_runtime": 3159.8581,
15
- "train_samples_per_second": 216.454,
16
- "train_steps_per_second": 3.384
17
  }
 
4
  "eval_bleu": 0.1323262570770995,
5
  "eval_loss": 3.1777124404907227,
6
  "eval_perplexity": 23.991808041831927,
7
+ "eval_runtime": 25.5919,
8
  "eval_samples": 1141,
9
+ "eval_samples_per_second": 44.584,
10
+ "eval_steps_per_second": 0.703,
11
  "perplexity": 23.991808041831927,
12
  "total_flos": 1.270447321217237e+18,
13
+ "train_loss": 0.0,
14
+ "train_runtime": 0.7883,
15
+ "train_samples_per_second": 867659.215,
16
+ "train_steps_per_second": 13563.597
17
  }
eval_results.json CHANGED
@@ -4,9 +4,9 @@
4
  "eval_bleu": 0.1323262570770995,
5
  "eval_loss": 3.1777124404907227,
6
  "eval_perplexity": 23.991808041831927,
7
- "eval_runtime": 12.2078,
8
  "eval_samples": 1141,
9
- "eval_samples_per_second": 93.465,
10
- "eval_steps_per_second": 1.474,
11
  "perplexity": 23.991808041831927
12
  }
 
4
  "eval_bleu": 0.1323262570770995,
5
  "eval_loss": 3.1777124404907227,
6
  "eval_perplexity": 23.991808041831927,
7
+ "eval_runtime": 25.5919,
8
  "eval_samples": 1141,
9
+ "eval_samples_per_second": 44.584,
10
+ "eval_steps_per_second": 0.703,
11
  "perplexity": 23.991808041831927
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fc50c439ac6b8bc0c1889959ba5ba8a050fe349df08ee581e7eeef2e7f7a658
3
  size 1419374664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe0da93dcf1f16f7de28297ffc4fac8d2e9d36a24b101c6e274cbc013c58b0f
3
  size 1419374664
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 6.0,
3
  "total_flos": 1.270447321217237e+18,
4
- "train_loss": 0.5092627385828409,
5
- "train_runtime": 3159.8581,
6
- "train_samples_per_second": 216.454,
7
- "train_steps_per_second": 3.384
8
  }
 
1
  {
2
  "epoch": 6.0,
3
  "total_flos": 1.270447321217237e+18,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.7883,
6
+ "train_samples_per_second": 867659.215,
7
+ "train_steps_per_second": 13563.597
8
  }
trainer_state.json CHANGED
@@ -985,10 +985,10 @@
985
  "epoch": 6.0,
986
  "step": 10692,
987
  "total_flos": 1.270447321217237e+18,
988
- "train_loss": 0.5092627385828409,
989
- "train_runtime": 3159.8581,
990
- "train_samples_per_second": 216.454,
991
- "train_steps_per_second": 3.384
992
  }
993
  ],
994
  "logging_steps": 100,
 
985
  "epoch": 6.0,
986
  "step": 10692,
987
  "total_flos": 1.270447321217237e+18,
988
+ "train_loss": 0.0,
989
+ "train_runtime": 0.7883,
990
+ "train_samples_per_second": 867659.215,
991
+ "train_steps_per_second": 13563.597
992
  }
993
  ],
994
  "logging_steps": 100,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59200eb8b86a27533dadf7d6faf0a6fa80382d582aa8060a5ac3329ab756818f
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0500a851b586cedd6386f69aa10824a1977591d4bbb5310598cc90b74b59acfc
3
  size 5560