Hugging Face's logo

indiejoseph
/
mbart-translation-zh-yue

Text2Text Generation
Transformers
PyTorch
Chinese
Yue Chinese
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
2
indiejoseph commited on
Commit
1f92ed0
•
1 Parent(s): 9d9ba26

End of training

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. all_results.json +4 -4
  3. train_results.json +4 -4
  4. trainer_state.json +11 -11
README.md CHANGED
@@ -1,4 +1,7 @@
1
  ---
 
 
 
2
  license: mit
3
  base_model: indiejoseph/mbart-translation-zh-yue
4
  tags:
 
1
  ---
2
+ language:
3
+ - zh
4
+ - yue
5
  license: mit
6
  base_model: indiejoseph/mbart-translation-zh-yue
7
  tags:
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
- "train_loss": 0.23955335338535488,
4
- "train_runtime": 7304.5803,
5
  "train_samples": 100042,
6
- "train_samples_per_second": 54.783,
7
- "train_steps_per_second": 3.424
8
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 0.0376,
5
  "train_samples": 100042,
6
+ "train_samples_per_second": 2660469.321,
7
+ "train_steps_per_second": 166289.305
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
- "train_loss": 0.23955335338535488,
4
- "train_runtime": 7304.5803,
5
  "train_samples": 100042,
6
- "train_samples_per_second": 54.783,
7
- "train_steps_per_second": 3.424
8
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 0.0376,
5
  "train_samples": 100042,
6
+ "train_samples_per_second": 2660469.321,
7
+ "train_steps_per_second": 166289.305
8
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 25012,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -310,19 +310,19 @@
310
  },
311
  {
312
  "epoch": 4.0,
313
- "step": 25012,
314
- "total_flos": 5.323473007568486e+16,
315
- "train_loss": 0.23955335338535488,
316
- "train_runtime": 7304.5803,
317
- "train_samples_per_second": 54.783,
318
- "train_steps_per_second": 3.424
319
  }
320
  ],
321
  "logging_steps": 500,
322
- "max_steps": 25012,
323
- "num_train_epochs": 4,
324
  "save_steps": 500,
325
- "total_flos": 5.323473007568486e+16,
326
  "trial_name": null,
327
  "trial_params": null
328
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.998080921157844,
5
  "eval_steps": 500,
6
+ "global_step": 25000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
310
  },
311
  {
312
  "epoch": 4.0,
313
+ "step": 25000,
314
+ "total_flos": 5.320960491493786e+16,
315
+ "train_loss": 0.0,
316
+ "train_runtime": 0.0376,
317
+ "train_samples_per_second": 2660469.321,
318
+ "train_steps_per_second": 166289.305
319
  }
320
  ],
321
  "logging_steps": 500,
322
+ "max_steps": 6253,
323
+ "num_train_epochs": 1,
324
  "save_steps": 500,
325
+ "total_flos": 5.320960491493786e+16,
326
  "trial_name": null,
327
  "trial_params": null
328
  }