Hugging Face's logo

agentlans
/
en-zhtw

Translation
Transformers
Safetensors
English
Chinese
marian
text2text-generation
Generated from Trainer
machine-translation
english
traditional-chinese
transformer
fine-tuned
Model card Files
xet
Community
agentlans commited on
Commit
54d741c
·
verified ·
1 Parent(s): a776c63

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": 1.961527705192566,
4
- "eval_runtime": 77.3959,
5
- "eval_samples": 83311,
6
- "eval_samples_per_second": 1076.426,
7
- "eval_steps_per_second": 134.555,
8
- "num_input_tokens_seen": 225160303,
9
- "total_flos": 5.962942279994573e+16,
10
- "train_loss": 1.8857571468166456,
11
- "train_runtime": 16282.8843,
12
- "train_samples": 333243,
13
- "train_samples_per_second": 204.658,
14
- "train_steps_per_second": 25.583,
15
- "train_tokens_per_second": 13822.702
16
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.0584163665771484,
4
+ "eval_runtime": 189.7324,
5
+ "eval_samples": 199905,
6
+ "eval_samples_per_second": 1053.616,
7
+ "eval_steps_per_second": 131.707,
8
+ "num_input_tokens_seen": 272407288,
9
+ "total_flos": 7.214188795055309e+16,
10
+ "train_loss": 0.0,
11
+ "train_runtime": 0.0544,
12
+ "train_samples": 799616,
13
+ "train_samples_per_second": 73478382.327,
14
+ "train_steps_per_second": 9184797.791,
15
+ "train_tokens_per_second": 5003948262.574
16
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 10.0,
3
- "eval_loss": 1.961527705192566,
4
- "eval_runtime": 77.3959,
5
- "eval_samples": 83311,
6
- "eval_samples_per_second": 1076.426,
7
- "eval_steps_per_second": 134.555,
8
- "num_input_tokens_seen": 225160303
9
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "eval_loss": 1.0584163665771484,
4
+ "eval_runtime": 189.7324,
5
+ "eval_samples": 199905,
6
+ "eval_samples_per_second": 1053.616,
7
+ "eval_steps_per_second": 131.707,
8
+ "num_input_tokens_seen": 272407288
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aac5f96b0d1c2435c122ac11eef69a78fde5924dbd76351f1a233d6c0f28037c
3
  size 309965092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3cface5fdffb425bbbd2773db70102ea5c6163b7a5ce463b7c4025890ae277a
3
  size 309965092
train_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 10.0,
3
- "num_input_tokens_seen": 225160303,
4
- "total_flos": 5.962942279994573e+16,
5
- "train_loss": 1.8857571468166456,
6
- "train_runtime": 16282.8843,
7
- "train_samples": 333243,
8
- "train_samples_per_second": 204.658,
9
- "train_steps_per_second": 25.583,
10
- "train_tokens_per_second": 13822.702
11
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "num_input_tokens_seen": 272407288,
4
+ "total_flos": 7.214188795055309e+16,
5
+ "train_loss": 0.0,
6
+ "train_runtime": 0.0544,
7
+ "train_samples": 799616,
8
+ "train_samples_per_second": 73478382.327,
9
+ "train_steps_per_second": 9184797.791,
10
+ "train_tokens_per_second": 5003948262.574
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 sha256:742b6e553683f5a8be3739142255defff5d894b12172be0396ab15afd216cd8a
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9143c94773d6b03b7764b406548e1c5333b9641259defab981c6cbbd20fb1eb7
3
+ size 5560