Hugging Face's logo

zedfum
/
arman-longformer-8k-finetuned-ensani

Summarization
Transformers
PyTorch
Safetensors
Persian
pegasus
text2text-generation
Inference Endpoints
Model card Files Community
2
hofarah commited on
Commit
d6e65de
•
1 Parent(s): 85830c3

Training in progress, step 280

Browse files
Files changed (8) hide show
  1. last-checkpoint/optimizer.pt +2 -2
  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 +62 -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:be720761f0e10b60ecbc47900152f65973bd708bf66af4cbd26d0e647c2fc9ea
3
- size 3544920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d327d6055b26512249f738b530183f923a688879d89aee01c1a7f129ad20292b
3
+ size 3545432
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:279001289160111f69989bdbd63e59b46d9353e04b8efe5c45c0ee36ea822c2b
3
  size 1140034381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e431d6677e21cb70645f73a949e7a206eba6b539e4319051fde1cf766602b528
3
  size 1140034381
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdc259941b88629c38a5d42d50c6190d622a9bb02d68782819b22239cb26f270
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b11dc40821345160db396d3d3b1fc931f4d0a9c790f3c549a309cd06fb1f698
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df343fa90fcddafb2dfc655c399dcd6fb9788397b581ec853a351289fbf07315
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329548916d80d2326c3e9113fcfe22537334086ae18a4696a380e612ee2dcea2
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": 1.9393939393939394,
5
- "global_step": 240,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -360,11 +360,70 @@
360
  "eval_samples_per_second": 0.052,
361
  "eval_steps_per_second": 0.027,
362
  "step": 240
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
363
  }
364
  ],
365
  "max_steps": 369,
366
  "num_train_epochs": 3,
367
- "total_flos": 9365407043420160.0,
368
  "trial_name": null,
369
  "trial_params": null
370
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.268686868686869,
5
+ "global_step": 280,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
360
  "eval_samples_per_second": 0.052,
361
  "eval_steps_per_second": 0.027,
362
  "step": 240
363
+ },
364
+ {
365
+ "epoch": 1.99,
366
+ "learning_rate": 1.707317073170732e-05,
367
+ "loss": 3.4609,
368
+ "step": 245
369
+ },
370
+ {
371
+ "epoch": 2.03,
372
+ "learning_rate": 1.6395663956639568e-05,
373
+ "loss": 3.2715,
374
+ "step": 250
375
+ },
376
+ {
377
+ "epoch": 2.07,
378
+ "learning_rate": 1.5718157181571816e-05,
379
+ "loss": 3.91,
380
+ "step": 255
381
+ },
382
+ {
383
+ "epoch": 2.11,
384
+ "learning_rate": 1.5040650406504067e-05,
385
+ "loss": 3.0947,
386
+ "step": 260
387
+ },
388
+ {
389
+ "epoch": 2.15,
390
+ "learning_rate": 1.4498644986449867e-05,
391
+ "loss": 3.2667,
392
+ "step": 265
393
+ },
394
+ {
395
+ "epoch": 2.19,
396
+ "learning_rate": 1.3821138211382115e-05,
397
+ "loss": 3.5289,
398
+ "step": 270
399
+ },
400
+ {
401
+ "epoch": 2.23,
402
+ "learning_rate": 1.3143631436314363e-05,
403
+ "loss": 3.3016,
404
+ "step": 275
405
+ },
406
+ {
407
+ "epoch": 2.27,
408
+ "learning_rate": 1.2466124661246612e-05,
409
+ "loss": 3.2669,
410
+ "step": 280
411
+ },
412
+ {
413
+ "epoch": 2.27,
414
+ "eval_loss": 3.130876064300537,
415
+ "eval_rouge2_fmeasure": 0.0,
416
+ "eval_rouge2_precision": 0.0,
417
+ "eval_rouge2_recall": 0.0,
418
+ "eval_runtime": 441.1701,
419
+ "eval_samples_per_second": 0.061,
420
+ "eval_steps_per_second": 0.032,
421
+ "step": 280
422
  }
423
  ],
424
  "max_steps": 369,
425
  "num_train_epochs": 3,
426
+ "total_flos": 1.092630821732352e+16,
427
  "trial_name": null,
428
  "trial_params": null
429
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15f8f2ce7bcf861b6b5b78baf6158001d2b18da91cb88a0ef26f2379e4013039
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c123334c6231c04d408abfe6f889d5ad07a522caad9269ed39f2c97c0d20ed
3
  size 4091
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:279001289160111f69989bdbd63e59b46d9353e04b8efe5c45c0ee36ea822c2b
3
  size 1140034381
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e431d6677e21cb70645f73a949e7a206eba6b539e4319051fde1cf766602b528
3
  size 1140034381
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15f8f2ce7bcf861b6b5b78baf6158001d2b18da91cb88a0ef26f2379e4013039
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c123334c6231c04d408abfe6f889d5ad07a522caad9269ed39f2c97c0d20ed
3
  size 4091