diogopaes10 commited on
Commit
cd6047c
β€’
1 Parent(s): 6ae55e7

Training in progress, step 12500

Browse files
{checkpoint-11500 β†’ checkpoint-12500}/config.json RENAMED
File without changes
{checkpoint-11500 β†’ checkpoint-12500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65fbc3d7ff6af173ca50cc1b3297ec21fc55033dffeff53b04c5f45964710293
3
  size 267028677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89abca1d6cacb633e4403dc53e0cdc1d284e1b84592b501d3f79626753ba3457
3
  size 267028677
{checkpoint-11500 β†’ checkpoint-12500}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59529ca11cd16e7f3bbb54ae86a9114f2c52ef602c31399728eb28f1e3d1a68e
3
  size 133523761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b4c0a712dff96e0473aeb3857c38177bf768f38bb7b857a8eb2705c05d922a
3
  size 133523761
{checkpoint-11500 β†’ checkpoint-12500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34231bee76a320a6cfd5e6a27db2529c2379830303be0641a6b4deb2835a92cc
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef826e9fbe5adfb12188e69aca966a61172da1b2ea910613beab436b85220ac
3
  size 14575
{checkpoint-11500 β†’ checkpoint-12500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ddd14bf92e9211d27a39f32668b1a30dde045dcc02bdd949826abb0a7d0f1a2
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dc4ba56ead8bf6047d71926b107227b1dbd8295e34c75548e1702143a342558
3
  size 627
{checkpoint-11500 β†’ checkpoint-12500}/special_tokens_map.json RENAMED
File without changes
{checkpoint-11500 β†’ checkpoint-12500}/tokenizer.json RENAMED
File without changes
{checkpoint-11500 β†’ checkpoint-12500}/tokenizer_config.json RENAMED
File without changes
{checkpoint-11500 β†’ checkpoint-12500}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.6,
5
- "global_step": 11500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -480,11 +480,63 @@
480
  "eval_system_ram_total": 83.48074722290039,
481
  "eval_system_ram_used": 3.8687171936035156,
482
  "step": 11250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
483
  }
484
  ],
485
  "max_steps": 12500,
486
  "num_train_epochs": 5,
487
- "total_flos": 5846801588057472.0,
488
  "trial_name": null,
489
  "trial_params": null
490
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 12500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
480
  "eval_system_ram_total": 83.48074722290039,
481
  "eval_system_ram_used": 3.8687171936035156,
482
  "step": 11250
483
+ },
484
+ {
485
+ "epoch": 4.75,
486
+ "learning_rate": 1.0064e-06,
487
+ "loss": 0.6355,
488
+ "step": 11875
489
+ },
490
+ {
491
+ "epoch": 4.75,
492
+ "eval_accuracy": 0.73495,
493
+ "eval_disk_space_total": 78.1898422241211,
494
+ "eval_disk_space_used": 26.470008850097656,
495
+ "eval_f1": 0.7311394674076037,
496
+ "eval_gpu_ram_allocated": 0.39347314834594727,
497
+ "eval_gpu_ram_cached": 16.05078125,
498
+ "eval_gpu_ram_total": 39.56402587890625,
499
+ "eval_gpu_utilization": 30,
500
+ "eval_loss": 0.850346565246582,
501
+ "eval_precision": 0.7308376671248696,
502
+ "eval_recall": 0.73495,
503
+ "eval_runtime": 15.2775,
504
+ "eval_samples_per_second": 1309.111,
505
+ "eval_steps_per_second": 40.91,
506
+ "eval_system_ram_total": 83.48074722290039,
507
+ "eval_system_ram_used": 3.8853225708007812,
508
+ "step": 11875
509
+ },
510
+ {
511
+ "epoch": 5.0,
512
+ "learning_rate": 6.400000000000001e-09,
513
+ "loss": 0.6396,
514
+ "step": 12500
515
+ },
516
+ {
517
+ "epoch": 5.0,
518
+ "eval_accuracy": 0.73565,
519
+ "eval_disk_space_total": 78.1898422241211,
520
+ "eval_disk_space_used": 26.47040557861328,
521
+ "eval_f1": 0.732235722379434,
522
+ "eval_gpu_ram_allocated": 0.3934931755065918,
523
+ "eval_gpu_ram_cached": 16.05078125,
524
+ "eval_gpu_ram_total": 39.56402587890625,
525
+ "eval_gpu_utilization": 33,
526
+ "eval_loss": 0.8507665991783142,
527
+ "eval_precision": 0.7317733808462167,
528
+ "eval_recall": 0.73565,
529
+ "eval_runtime": 15.2926,
530
+ "eval_samples_per_second": 1307.826,
531
+ "eval_steps_per_second": 40.87,
532
+ "eval_system_ram_total": 83.48074722290039,
533
+ "eval_system_ram_used": 3.8995018005371094,
534
+ "step": 12500
535
  }
536
  ],
537
  "max_steps": 12500,
538
  "num_train_epochs": 5,
539
+ "total_flos": 6360760919761920.0,
540
  "trial_name": null,
541
  "trial_params": null
542
  }
{checkpoint-11500 β†’ checkpoint-12500}/training_args.bin RENAMED
File without changes
{checkpoint-11500 β†’ checkpoint-12500}/vocab.txt RENAMED
File without changes
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f464404bbabf4ffc076175dc0dd64bed9ebbae82e692e4cc0d024912d83b0bf7
3
  size 133523761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b4c0a712dff96e0473aeb3857c38177bf768f38bb7b857a8eb2705c05d922a
3
  size 133523761
runs/Jul23_01-08-06_df8adf32a670/events.out.tfevents.1690074496.df8adf32a670.1420.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb8b338480dce9596ce62d102b2c3b4e900091413645f35902e9c12c0c481491
3
- size 25820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dbc2d39c4c64c3b5480bd01b1771b4f4940fe7f8922458f8cf510bf6c94e960
3
+ size 26922