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
xet
Community
shivanandmn commited on
Commit
10d55ff
·
verified ·
1 Parent(s): 8ffbf38

Training in progress, step 9000

Browse files
Files changed (6) hide show
  1. all_results.json +6 -6
  2. eval_results.json +3 -3
  3. model.safetensors +1 -1
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
  6. training_args.bin +1 -1
all_results.json CHANGED
@@ -4,14 +4,14 @@
4
  "eval_bleu": 0.13436705184218095,
5
  "eval_loss": 3.19417405128479,
6
  "eval_perplexity": 24.39002046460787,
7
- "eval_runtime": 12.6247,
8
  "eval_samples": 1141,
9
- "eval_samples_per_second": 90.378,
10
- "eval_steps_per_second": 1.426,
11
  "perplexity": 24.39002046460787,
12
  "total_flos": 1.0587061010143642e+18,
13
  "train_loss": 0.0,
14
- "train_runtime": 0.6897,
15
- "train_samples_per_second": 826370.638,
16
- "train_steps_per_second": 12918.158
17
  }
 
4
  "eval_bleu": 0.13436705184218095,
5
  "eval_loss": 3.19417405128479,
6
  "eval_perplexity": 24.39002046460787,
7
+ "eval_runtime": 12.522,
8
  "eval_samples": 1141,
9
+ "eval_samples_per_second": 91.119,
10
+ "eval_steps_per_second": 1.437,
11
  "perplexity": 24.39002046460787,
12
  "total_flos": 1.0587061010143642e+18,
13
  "train_loss": 0.0,
14
+ "train_runtime": 0.6821,
15
+ "train_samples_per_second": 835582.505,
16
+ "train_steps_per_second": 13062.161
17
  }
eval_results.json CHANGED
@@ -4,9 +4,9 @@
4
  "eval_bleu": 0.13436705184218095,
5
  "eval_loss": 3.19417405128479,
6
  "eval_perplexity": 24.39002046460787,
7
- "eval_runtime": 12.6247,
8
  "eval_samples": 1141,
9
- "eval_samples_per_second": 90.378,
10
- "eval_steps_per_second": 1.426,
11
  "perplexity": 24.39002046460787
12
  }
 
4
  "eval_bleu": 0.13436705184218095,
5
  "eval_loss": 3.19417405128479,
6
  "eval_perplexity": 24.39002046460787,
7
+ "eval_runtime": 12.522,
8
  "eval_samples": 1141,
9
+ "eval_samples_per_second": 91.119,
10
+ "eval_steps_per_second": 1.437,
11
  "perplexity": 24.39002046460787
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e7f7422321e9ba44f321f7c1743620f2c8789dffaa00a188f6658f78dd0ebf8
3
  size 1419374664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccffe39a0e2f62c45df5afddc116977ca9e9df4700deb9458a99b1a24fe8aff
3
  size 1419374664
train_results.json CHANGED
@@ -2,7 +2,7 @@
2
  "epoch": 5.0,
3
  "total_flos": 1.0587061010143642e+18,
4
  "train_loss": 0.0,
5
- "train_runtime": 0.6897,
6
- "train_samples_per_second": 826370.638,
7
- "train_steps_per_second": 12918.158
8
  }
 
2
  "epoch": 5.0,
3
  "total_flos": 1.0587061010143642e+18,
4
  "train_loss": 0.0,
5
+ "train_runtime": 0.6821,
6
+ "train_samples_per_second": 835582.505,
7
+ "train_steps_per_second": 13062.161
8
  }
trainer_state.json CHANGED
@@ -823,9 +823,9 @@
823
  "step": 8910,
824
  "total_flos": 1.0587061010143642e+18,
825
  "train_loss": 0.0,
826
- "train_runtime": 0.6897,
827
- "train_samples_per_second": 826370.638,
828
- "train_steps_per_second": 12918.158
829
  }
830
  ],
831
  "logging_steps": 100,
 
823
  "step": 8910,
824
  "total_flos": 1.0587061010143642e+18,
825
  "train_loss": 0.0,
826
+ "train_runtime": 0.6821,
827
+ "train_samples_per_second": 835582.505,
828
+ "train_steps_per_second": 13062.161
829
  }
830
  ],
831
  "logging_steps": 100,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64acc06a54753e3c90d36e5fc570d0909cca6d16e044cd9018ae585d3fb3c51
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d6437c2ee925975d79e817dff86d018d08d52bce678fa75ae1d31d316d4699
3
  size 5560