Hugging Face's logo

agentlans
/
zhtw-en

Translation
Transformers
Safetensors
English
Chinese
marian
text2text-generation
Generated from Trainer
Model card Files
xet
Community
agentlans commited on
Commit
b7e2702
·
verified ·
1 Parent(s): 1d96d64

Upload 13 files

Browse files
Files changed (6) hide show
  1. all_results.json +14 -14
  2. eval_results.json +7 -7
  3. model.safetensors +1 -1
  4. train_results.json +9 -9
  5. trainer_state.json +0 -0
  6. training_args.bin +2 -2
all_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "epoch": 10.0,
3
- "eval_loss": 1.8425856828689575,
4
- "eval_runtime": 78.2516,
5
- "eval_samples": 83311,
6
- "eval_samples_per_second": 1064.656,
7
- "eval_steps_per_second": 133.084,
8
- "num_input_tokens_seen": 224864981,
9
- "total_flos": 5.955121238645146e+16,
10
- "train_loss": 1.7257680629754402,
11
- "train_runtime": 16392.488,
12
- "train_samples": 333243,
13
- "train_samples_per_second": 203.29,
14
- "train_steps_per_second": 25.412,
15
- "train_tokens_per_second": 13715.035
16
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.9877662062644958,
4
+ "eval_runtime": 191.8575,
5
+ "eval_samples": 199905,
6
+ "eval_samples_per_second": 1041.945,
7
+ "eval_steps_per_second": 130.248,
8
+ "num_input_tokens_seen": 270444104,
9
+ "total_flos": 7.16219760157655e+16,
10
+ "train_loss": 0.8578685343122414,
11
+ "train_runtime": 15819.1918,
12
+ "train_samples": 799616,
13
+ "train_samples_per_second": 252.736,
14
+ "train_steps_per_second": 31.592,
15
+ "train_tokens_per_second": 17096.35
16
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 10.0,
3
- "eval_loss": 1.8425856828689575,
4
- "eval_runtime": 78.2516,
5
- "eval_samples": 83311,
6
- "eval_samples_per_second": 1064.656,
7
- "eval_steps_per_second": 133.084,
8
- "num_input_tokens_seen": 224864981
9
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.9877662062644958,
4
+ "eval_runtime": 191.8575,
5
+ "eval_samples": 199905,
6
+ "eval_samples_per_second": 1041.945,
7
+ "eval_steps_per_second": 130.248,
8
+ "num_input_tokens_seen": 270444104
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f64d3422f29320e25c3147ccad3fd8c2ff33f21c304ce3fef5ad0635cb65a1b
3
  size 309965092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2698bb7b6baef60d957fc165adb6fe41d9c331e3c9f8636a06b445e14ccde26
3
  size 309965092
train_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 10.0,
3
- "num_input_tokens_seen": 224864981,
4
- "total_flos": 5.955121238645146e+16,
5
- "train_loss": 1.7257680629754402,
6
- "train_runtime": 16392.488,
7
- "train_samples": 333243,
8
- "train_samples_per_second": 203.29,
9
- "train_steps_per_second": 25.412,
10
- "train_tokens_per_second": 13715.035
11
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "num_input_tokens_seen": 270444104,
4
+ "total_flos": 7.16219760157655e+16,
5
+ "train_loss": 0.8578685343122414,
6
+ "train_runtime": 15819.1918,
7
+ "train_samples": 799616,
8
+ "train_samples_per_second": 252.736,
9
+ "train_steps_per_second": 31.592,
10
+ "train_tokens_per_second": 17096.35
11
  }
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:e21d4704e53ce765ad8089f6ad1256599250b602615c481e5a598d83131099ba
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd88c026fb1afd3024d926e8768bbb2f364125b062859865bf66ce94ac883e1
3
+ size 5560