Hugging Face's logo

BluebrainAI
/
duo-predict-gpt2-medium-wikitext

Feature Extraction
Transformers
Safetensors
duo-predict-gpt2
Generated from Trainer
custom_code
Model card Files Community
shivanandmn commited on
Commit
b1a6d74
·
verified ·
1 Parent(s): 5404364

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. all_results.json +14 -14
  2. eval_results.json +9 -9
  3. model.safetensors +1 -1
  4. train_results.json +5 -5
  5. trainer_state.json +7 -7
  6. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
  "epoch": 5.0,
3
- "eval_accuracy": 0.027886497064579255,
4
- "eval_bleu": 0.0021463467173750564,
5
- "eval_loss": 8.901089668273926,
6
- "eval_perplexity": 7339.967312596559,
7
- "eval_runtime": 2.9365,
8
- "eval_samples": 4,
9
- "eval_samples_per_second": 1.362,
10
- "eval_steps_per_second": 0.341,
11
- "perplexity": 7339.967312596559,
12
- "total_flos": 37111750410240.0,
13
- "train_loss": 19.501985168457033,
14
- "train_runtime": 33.6762,
15
- "train_samples_per_second": 0.594,
16
- "train_steps_per_second": 0.148
17
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_accuracy": 0.02236511042773274,
4
+ "eval_bleu": 0.002799146980613368,
5
+ "eval_loss": 9.125165939331055,
6
+ "eval_perplexity": 9183.52079846965,
7
+ "eval_runtime": 0.3917,
8
+ "eval_samples": 14,
9
+ "eval_samples_per_second": 35.745,
10
+ "eval_steps_per_second": 2.553,
11
+ "perplexity": 9183.52079846965,
12
+ "total_flos": 129891126435840.0,
13
+ "train_loss": 19.52422180175781,
14
+ "train_runtime": 23.5998,
15
+ "train_samples_per_second": 2.966,
16
+ "train_steps_per_second": 0.212
17
  }
eval_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 5.0,
3
- "eval_accuracy": 0.027886497064579255,
4
- "eval_bleu": 0.0021463467173750564,
5
- "eval_loss": 8.901089668273926,
6
- "eval_perplexity": 7339.967312596559,
7
- "eval_runtime": 2.9365,
8
- "eval_samples": 4,
9
- "eval_samples_per_second": 1.362,
10
- "eval_steps_per_second": 0.341,
11
- "perplexity": 7339.967312596559
12
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_accuracy": 0.02236511042773274,
4
+ "eval_bleu": 0.002799146980613368,
5
+ "eval_loss": 9.125165939331055,
6
+ "eval_perplexity": 9183.52079846965,
7
+ "eval_runtime": 0.3917,
8
+ "eval_samples": 14,
9
+ "eval_samples_per_second": 35.745,
10
+ "eval_steps_per_second": 2.553,
11
+ "perplexity": 9183.52079846965
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27bc8eb3b15560df54abe40fea156b75b88024ad128c5613eced7289e6007698
3
  size 1417229824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219976ee5d77df2fc3e00e7db92d57c038d1bb3aea3345229f7edd6b186f3ee0
3
  size 1417229824
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "total_flos": 37111750410240.0,
4
- "train_loss": 19.501985168457033,
5
- "train_runtime": 33.6762,
6
- "train_samples_per_second": 0.594,
7
- "train_steps_per_second": 0.148
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "total_flos": 129891126435840.0,
4
+ "train_loss": 19.52422180175781,
5
+ "train_runtime": 23.5998,
6
+ "train_samples_per_second": 2.966,
7
+ "train_steps_per_second": 0.212
8
  }
trainer_state.json CHANGED
@@ -11,11 +11,11 @@
11
  {
12
  "epoch": 5.0,
13
  "step": 5,
14
- "total_flos": 37111750410240.0,
15
- "train_loss": 19.501985168457033,
16
- "train_runtime": 33.6762,
17
- "train_samples_per_second": 0.594,
18
- "train_steps_per_second": 0.148
19
  }
20
  ],
21
  "logging_steps": 100,
@@ -44,8 +44,8 @@
44
  "attributes": {}
45
  }
46
  },
47
- "total_flos": 37111750410240.0,
48
- "train_batch_size": 8,
49
  "trial_name": null,
50
  "trial_params": null
51
  }
 
11
  {
12
  "epoch": 5.0,
13
  "step": 5,
14
+ "total_flos": 129891126435840.0,
15
+ "train_loss": 19.52422180175781,
16
+ "train_runtime": 23.5998,
17
+ "train_samples_per_second": 2.966,
18
+ "train_steps_per_second": 0.212
19
  }
20
  ],
21
  "logging_steps": 100,
 
44
  "attributes": {}
45
  }
46
  },
47
+ "total_flos": 129891126435840.0,
48
+ "train_batch_size": 64,
49
  "trial_name": null,
50
  "trial_params": null
51
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cbf4e022680dd32fb89b366b15405b4a72821c9a060d5074735c6b62ff171bd
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1fb4d3347c522b6d98e9c675ffe42389ad29aa55352445e19a262742a998195
3
  size 5496