spacemanidol commited on
Commit
5c8ea99
1 Parent(s): 2510a15

Upload 13 files

Browse files
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
  metrics:
7
  - rouge
8
  model-index:
9
- - name: small-3-6-t
10
  results:
11
  - task:
12
  name: Summarization
@@ -26,9 +26,9 @@ model-index:
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
  should probably proofread and complete it, then remove this comment. -->
28
 
29
- # small-3-6-t
30
 
31
- This model is a fine-tuned version of [asy/cnndm/small-3-6](https://huggingface.co/asy/cnndm/small-3-6) on the cnn_dailymail 3.0.0 dataset.
32
  It achieves the following results on the evaluation set:
33
  - Loss: 1.7320
34
  - Rouge1: 38.5733
 
6
  metrics:
7
  - rouge
8
  model-index:
9
+ - name: small-3-6
10
  results:
11
  - task:
12
  name: Summarization
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
  should probably proofread and complete it, then remove this comment. -->
28
 
29
+ # small-3-6
30
 
31
+ This model is a fine-tuned version of [cnn/small-3-6/](https://huggingface.co/cnn/small-3-6/) on the cnn_dailymail 3.0.0 dataset.
32
  It achieves the following results on the evaluation set:
33
  - Loss: 1.7320
34
  - Rouge1: 38.5733
all_results.json CHANGED
@@ -6,13 +6,13 @@
6
  "eval_rouge2": 16.7984,
7
  "eval_rougeL": 27.1527,
8
  "eval_rougeLsum": 35.793,
9
- "eval_runtime": 2928.1869,
10
  "eval_samples": 13368,
11
- "eval_samples_per_second": 4.565,
12
- "eval_steps_per_second": 1.141,
13
  "train_loss": 2.001928689168385,
14
- "train_runtime": 25325.5133,
15
  "train_samples": 287113,
16
- "train_samples_per_second": 34.011,
17
- "train_steps_per_second": 0.531
18
  }
 
6
  "eval_rouge2": 16.7984,
7
  "eval_rougeL": 27.1527,
8
  "eval_rougeLsum": 35.793,
9
+ "eval_runtime": 2973.3751,
10
  "eval_samples": 13368,
11
+ "eval_samples_per_second": 4.496,
12
+ "eval_steps_per_second": 1.124,
13
  "train_loss": 2.001928689168385,
14
+ "train_runtime": 26117.7064,
15
  "train_samples": 287113,
16
+ "train_samples_per_second": 32.979,
17
+ "train_steps_per_second": 0.515
18
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "asy/cnndm/small-3-6",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "cnn/small-3-6/",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
eval_results.json CHANGED
@@ -6,8 +6,8 @@
6
  "eval_rouge2": 16.7984,
7
  "eval_rougeL": 27.1527,
8
  "eval_rougeLsum": 35.793,
9
- "eval_runtime": 2928.1869,
10
  "eval_samples": 13368,
11
- "eval_samples_per_second": 4.565,
12
- "eval_steps_per_second": 1.141
13
  }
 
6
  "eval_rouge2": 16.7984,
7
  "eval_rougeL": 27.1527,
8
  "eval_rougeLsum": 35.793,
9
+ "eval_runtime": 2973.3751,
10
  "eval_samples": 13368,
11
+ "eval_samples_per_second": 4.496,
12
+ "eval_steps_per_second": 1.124
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 2.001928689168385,
4
- "train_runtime": 25325.5133,
5
  "train_samples": 287113,
6
- "train_samples_per_second": 34.011,
7
- "train_steps_per_second": 0.531
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 2.001928689168385,
4
+ "train_runtime": 26117.7064,
5
  "train_samples": 287113,
6
+ "train_samples_per_second": 32.979,
7
+ "train_steps_per_second": 0.515
8
  }
trainer_state.json CHANGED
@@ -168,9 +168,9 @@
168
  "step": 13458,
169
  "total_flos": 2.6528666710694707e+17,
170
  "train_loss": 2.001928689168385,
171
- "train_runtime": 25325.5133,
172
- "train_samples_per_second": 34.011,
173
- "train_steps_per_second": 0.531
174
  }
175
  ],
176
  "max_steps": 13458,
 
168
  "step": 13458,
169
  "total_flos": 2.6528666710694707e+17,
170
  "train_loss": 2.001928689168385,
171
+ "train_runtime": 26117.7064,
172
+ "train_samples_per_second": 32.979,
173
+ "train_steps_per_second": 0.515
174
  }
175
  ],
176
  "max_steps": 13458,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff6efff05f8b72c2c4429a0e63741b1467364c7b7696f5db62baa8fe7fa92408
3
- size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5127cd381db677f1037d8ced9dd631ca715106159ded7ad6f265c1c84840ab31
3
+ size 3707