Hugging Face's logo

JulienRPA
/
BERT2BERT_finetuned

Text2Text Generation
Transformers
PyTorch
TensorBoard
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
JulienRPA commited on
Commit
017b9bc
•
1 Parent(s): 74cca0d

Training in progress, step 11000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +39 -3
  6. last-checkpoint/training_args.bin +1 -1
  7. pytorch_model.bin +1 -1
  8. runs/Jun02_07-11-36_8c8a3ec9844a/1685690790.4366324/events.out.tfevents.1685690790.8c8a3ec9844a.3155.1 +3 -0
  9. runs/Jun02_07-11-36_8c8a3ec9844a/events.out.tfevents.1685690790.8c8a3ec9844a.3155.0 +3 -0
  10. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14c9a2e55c4c50b24b29ffda31bbbf8b2ce79105a3817c65ef74a18d2c29ccd0
3
  size 2023671531
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7f2ae7866cbe859e9a83202cb446faa715f7b1a80217fe6e627acfe4157a7a
3
  size 2023671531
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1985db2a12fd26ee3312f17e5b5c9269d139ea9375f805eaa6bedfdbc502aed3
3
  size 1014236857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cc796916aefe4e38a5f73ee609fcf3cd5f4797936a93022e6f5c7a7bf2e8dd
3
  size 1014236857
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:223d17683d85a6b838bf63109231365183224af0ce92c28b1ea819c53db67266
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f52f64e625b9a5d4c4efe5f98776e33220b02b2d0b1d9ac547192bd484b739
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180a76762e48468dc084ebe39054009bb6587d7f0fcb0961ce0eec20c5af2575
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe6ae17ba1adb51797dbf26168b5b12ea8351b1902a73d1e47eeffc8523949e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 256.4102564102564,
5
- "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -366,11 +366,47 @@
366
  "eval_samples_per_second": 3.52,
367
  "eval_steps_per_second": 0.447,
368
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
369
  }
370
  ],
371
  "max_steps": 11700,
372
  "num_train_epochs": 300,
373
- "total_flos": 8083589088527040.0,
374
  "trial_name": null,
375
  "trial_params": null
376
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 282.05128205128204,
5
+ "global_step": 11000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
366
  "eval_samples_per_second": 3.52,
367
  "eval_steps_per_second": 0.447,
368
  "step": 10000
369
+ },
370
+ {
371
+ "epoch": 269.23,
372
+ "learning_rate": 6.206185567010309e-06,
373
+ "loss": 0.045,
374
+ "step": 10500
375
+ },
376
+ {
377
+ "epoch": 269.23,
378
+ "eval_bleu": 95.047,
379
+ "eval_em": 0.1343,
380
+ "eval_gen_len": 58.3213,
381
+ "eval_loss": 0.35046613216400146,
382
+ "eval_rm": 0.307,
383
+ "eval_runtime": 118.1147,
384
+ "eval_samples_per_second": 3.53,
385
+ "eval_steps_per_second": 0.449,
386
+ "step": 10500
387
+ },
388
+ {
389
+ "epoch": 282.05,
390
+ "learning_rate": 3.6288659793814435e-06,
391
+ "loss": 0.0429,
392
+ "step": 11000
393
+ },
394
+ {
395
+ "epoch": 282.05,
396
+ "eval_bleu": 95.2397,
397
+ "eval_em": 0.1391,
398
+ "eval_gen_len": 58.7242,
399
+ "eval_loss": 0.3522409200668335,
400
+ "eval_rm": 0.3046,
401
+ "eval_runtime": 119.4326,
402
+ "eval_samples_per_second": 3.492,
403
+ "eval_steps_per_second": 0.444,
404
+ "step": 11000
405
  }
406
  ],
407
  "max_steps": 11700,
408
  "num_train_epochs": 300,
409
+ "total_flos": 8893000475652480.0,
410
  "trial_name": null,
411
  "trial_params": null
412
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab9cbcd0471e6a26b3d7df9ad7ec2efb4c0f4011d70d40764192f52d388bc55
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f4bc00b89cc61426524602270e52394137beccf4e05eb3ce2d552fad490150
3
  size 4155
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1985db2a12fd26ee3312f17e5b5c9269d139ea9375f805eaa6bedfdbc502aed3
3
  size 1014236857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cc796916aefe4e38a5f73ee609fcf3cd5f4797936a93022e6f5c7a7bf2e8dd
3
  size 1014236857
runs/Jun02_07-11-36_8c8a3ec9844a/1685690790.4366324/events.out.tfevents.1685690790.8c8a3ec9844a.3155.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e957900bb280032b83932ba8f6fe82c20c828a5009ad78163c6c4f4eb4c9ce70
3
+ size 6281
runs/Jun02_07-11-36_8c8a3ec9844a/events.out.tfevents.1685690790.8c8a3ec9844a.3155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:310ed5f8c9724b666625f94c5a1a09d80670fd013a61cbed7bb7887362ed9450
3
+ size 9829
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab9cbcd0471e6a26b3d7df9ad7ec2efb4c0f4011d70d40764192f52d388bc55
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f4bc00b89cc61426524602270e52394137beccf4e05eb3ce2d552fad490150
3
  size 4155