diogopaes10 commited on
Commit
1fe725a
β€’
1 Parent(s): cbd6416

Training in progress, step 11500

Browse files
{checkpoint-10500 β†’ checkpoint-11500}/config.json RENAMED
File without changes
{checkpoint-10500 β†’ checkpoint-11500}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80559c1b1bf97ffea5492c8aafd7dec88753955d7295cfbc08b99df5ce302630
3
  size 267028677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65fbc3d7ff6af173ca50cc1b3297ec21fc55033dffeff53b04c5f45964710293
3
  size 267028677
{checkpoint-10500 β†’ checkpoint-11500}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5b915af613925ecdf2955e1a788f57e0f9ed1146924f573e0789a03c9f5d1fb
3
  size 133523761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59529ca11cd16e7f3bbb54ae86a9114f2c52ef602c31399728eb28f1e3d1a68e
3
  size 133523761
{checkpoint-10500 β†’ checkpoint-11500}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89440c8497ea37eb9574fb3a4b717af648034e96d1e784a5ec340222f778f966
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34231bee76a320a6cfd5e6a27db2529c2379830303be0641a6b4deb2835a92cc
3
  size 14575
{checkpoint-10500 β†’ checkpoint-11500}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59eac2cccdc53a2b511c84a4ecc9b55c72027d8de648a98699746a3948afa715
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddd14bf92e9211d27a39f32668b1a30dde045dcc02bdd949826abb0a7d0f1a2
3
  size 627
{checkpoint-10500 β†’ checkpoint-11500}/special_tokens_map.json RENAMED
File without changes
{checkpoint-10500 β†’ checkpoint-11500}/tokenizer.json RENAMED
File without changes
{checkpoint-10500 β†’ checkpoint-11500}/tokenizer_config.json RENAMED
File without changes
{checkpoint-10500 β†’ checkpoint-11500}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.2,
5
- "global_step": 10500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -428,11 +428,63 @@
428
  "eval_system_ram_total": 83.48074722290039,
429
  "eval_system_ram_used": 3.8847808837890625,
430
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
431
  }
432
  ],
433
  "max_steps": 12500,
434
  "num_train_epochs": 5,
435
- "total_flos": 5340484590610176.0,
436
  "trial_name": null,
437
  "trial_params": null
438
  }
 
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,
 
428
  "eval_system_ram_total": 83.48074722290039,
429
  "eval_system_ram_used": 3.8847808837890625,
430
  "step": 10000
431
+ },
432
+ {
433
+ "epoch": 4.25,
434
+ "learning_rate": 3.0064000000000006e-06,
435
+ "loss": 0.6247,
436
+ "step": 10625
437
+ },
438
+ {
439
+ "epoch": 4.25,
440
+ "eval_accuracy": 0.736,
441
+ "eval_disk_space_total": 78.1898422241211,
442
+ "eval_disk_space_used": 26.469379425048828,
443
+ "eval_f1": 0.7332127747065252,
444
+ "eval_gpu_ram_allocated": 0.39348888397216797,
445
+ "eval_gpu_ram_cached": 16.05078125,
446
+ "eval_gpu_ram_total": 39.56402587890625,
447
+ "eval_gpu_utilization": 32,
448
+ "eval_loss": 0.8499526381492615,
449
+ "eval_precision": 0.7324176547179257,
450
+ "eval_recall": 0.736,
451
+ "eval_runtime": 15.3802,
452
+ "eval_samples_per_second": 1300.37,
453
+ "eval_steps_per_second": 40.637,
454
+ "eval_system_ram_total": 83.48074722290039,
455
+ "eval_system_ram_used": 4.0838470458984375,
456
+ "step": 10625
457
+ },
458
+ {
459
+ "epoch": 4.5,
460
+ "learning_rate": 2.0064000000000004e-06,
461
+ "loss": 0.6446,
462
+ "step": 11250
463
+ },
464
+ {
465
+ "epoch": 4.5,
466
+ "eval_accuracy": 0.7358,
467
+ "eval_disk_space_total": 78.1898422241211,
468
+ "eval_disk_space_used": 26.469707489013672,
469
+ "eval_f1": 0.7322672918855475,
470
+ "eval_gpu_ram_allocated": 0.39359617233276367,
471
+ "eval_gpu_ram_cached": 16.05078125,
472
+ "eval_gpu_ram_total": 39.56402587890625,
473
+ "eval_gpu_utilization": 31,
474
+ "eval_loss": 0.8464106321334839,
475
+ "eval_precision": 0.7319786149192336,
476
+ "eval_recall": 0.7358,
477
+ "eval_runtime": 15.2922,
478
+ "eval_samples_per_second": 1307.853,
479
+ "eval_steps_per_second": 40.87,
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
  }
{checkpoint-10500 β†’ checkpoint-11500}/training_args.bin RENAMED
File without changes
{checkpoint-10500 β†’ checkpoint-11500}/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 sha256:6b2d123eec1e3724e36f27638d03c43ed031e88f237dbef0f0139dfab99cb872
3
  size 133523761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59529ca11cd16e7f3bbb54ae86a9114f2c52ef602c31399728eb28f1e3d1a68e
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:f32aec60a58edd33329a0b3ab84d5ac3280b96a5aad80b8e542ed51609be0281
3
- size 23616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a09110f783e2e5350e99889528776802102f16699d8374cb32da164aa43612
3
+ size 24718