Hugging Face's logo

k4black
/
t5-small-e-snli-generation-explanation_only-selected-b64

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
k4black commited on
Commit
5d7f951
•
1 Parent(s): 49068d5

Training in progress, step 46000

Browse files
Files changed (8) 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 +25 -3
  6. last-checkpoint/training_args.bin +1 -1
  7. pytorch_model.bin +1 -1
  8. 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 sha256:9034c84f18778333e1872d7331a8eb09431219f8d95aaae7c99eed6f46650ed0
3
  size 839109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f467fec01f2ecd24f52bfa098e50bf53953c7035b798dfdb0dac553bec346045
3
  size 839109
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb856baf7d31eafc5114ccc9c02965a7416c0e2e314749860a91bd70633ae99
3
  size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0508343bba57f00f2ca018de766048993e2b7c4aae1704ba38e2c828e97e3d
3
  size 242071641
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb1c65f67599992edc6f37f768bc31665429f6b717770ba716c87e900565cdd9
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af866b29da241a8cd7b954d873b727f4d541f4639d8d988e1afe762150c82db7
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfe9cd4b1870cc08c52a01526a50912b784c0d634c7d848108e06294afd36be5
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7f7dbcc6af1af2997ab49eaf245404b3ca605cb402cb0c5a0a5319ced2d65e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 1.718157410621643,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-42000",
4
- "epoch": 5.125815470643057,
5
- "global_step": 44000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -490,11 +490,33 @@
490
  "eval_samples_per_second": 79.956,
491
  "eval_steps_per_second": 1.251,
492
  "step": 44000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
493
  }
494
  ],
495
  "max_steps": 85840,
496
  "num_train_epochs": 10,
497
- "total_flos": 4.392879598111949e+16,
498
  "trial_name": null,
499
  "trial_params": null
500
  }
 
1
  {
2
  "best_metric": 1.718157410621643,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-42000",
4
+ "epoch": 5.358807082945014,
5
+ "global_step": 46000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
490
  "eval_samples_per_second": 79.956,
491
  "eval_steps_per_second": 1.251,
492
  "step": 44000
493
+ },
494
+ {
495
+ "epoch": 5.36,
496
+ "learning_rate": 0.0004885466228478932,
497
+ "loss": 1.1271,
498
+ "step": 46000
499
+ },
500
+ {
501
+ "epoch": 5.36,
502
+ "eval_accuracy": null,
503
+ "eval_bertscore_f1": 0.9343265120005904,
504
+ "eval_bleu": 0.4107679859085796,
505
+ "eval_f1": null,
506
+ "eval_loss": 1.7594177722930908,
507
+ "eval_rouge1": 0.6214337711077422,
508
+ "eval_rouge2": 0.415499095864183,
509
+ "eval_rougeL": 0.5634811122039034,
510
+ "eval_rougeLsum": 0.565609388415719,
511
+ "eval_runtime": 148.0927,
512
+ "eval_samples_per_second": 66.458,
513
+ "eval_steps_per_second": 1.04,
514
+ "step": 46000
515
  }
516
  ],
517
  "max_steps": 85840,
518
  "num_train_epochs": 10,
519
+ "total_flos": 4.593569496652186e+16,
520
  "trial_name": null,
521
  "trial_params": null
522
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a67f68b1ac5c574955a71eda994dfb70c89ed57dafcee072ff2097b6000781
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56934fb9396918bcbb21c649a8cf3c6543e3a8003906e7f5545a3b9b1261fd6c
3
  size 3899
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb856baf7d31eafc5114ccc9c02965a7416c0e2e314749860a91bd70633ae99
3
  size 242071641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0508343bba57f00f2ca018de766048993e2b7c4aae1704ba38e2c828e97e3d
3
  size 242071641
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a67f68b1ac5c574955a71eda994dfb70c89ed57dafcee072ff2097b6000781
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56934fb9396918bcbb21c649a8cf3c6543e3a8003906e7f5545a3b9b1261fd6c
3
  size 3899