diogopaes10 commited on
Commit
6ae55e7
β€’
1 Parent(s): 1fe725a

Training in progress, step 12000

Browse files
{checkpoint-11000 β†’ checkpoint-12000}/config.json RENAMED
File without changes
{checkpoint-11000 β†’ checkpoint-12000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7121353f67016220d0ba6e07bd91a440d339f7e5ae43637ec5df1821dca53d0
3
  size 267028677
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dbf8bfdaff0d358c50ba58b2e37e228971d18c40ded342ff3414bc23c55625
3
  size 267028677
{checkpoint-11000 β†’ checkpoint-12000}/pytorch_model.bin RENAMED
@@ -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:f464404bbabf4ffc076175dc0dd64bed9ebbae82e692e4cc0d024912d83b0bf7
3
  size 133523761
{checkpoint-11000 β†’ checkpoint-12000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f611266503706b42390c0157b3936fc5fd122440ae086d8d5ee5411a8edfeafa
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e99597d92b26233312419b8d7606c8fbe7f7558947be013db496307a49ea89f
3
  size 14575
{checkpoint-11000 β†’ checkpoint-12000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91ff66b19ca53b4aad8b20e30491f86f0e0556ec5ed0d4287237a1e66d619793
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8b6ab7544af193bb6ba46a2bee0e0abe8937e6b54f5dea5a487ee681ff4d17
3
  size 627
{checkpoint-11000 β†’ checkpoint-12000}/special_tokens_map.json RENAMED
File without changes
{checkpoint-11000 β†’ checkpoint-12000}/tokenizer.json RENAMED
File without changes
{checkpoint-11000 β†’ checkpoint-12000}/tokenizer_config.json RENAMED
File without changes
{checkpoint-11000 β†’ checkpoint-12000}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.4,
5
- "global_step": 11000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -454,11 +454,63 @@
454
  "eval_system_ram_total": 83.48074722290039,
455
  "eval_system_ram_used": 4.0838470458984375,
456
  "step": 10625
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457
  }
458
  ],
459
  "max_steps": 12500,
460
  "num_train_epochs": 5,
461
- "total_flos": 5590392214928640.0,
462
  "trial_name": null,
463
  "trial_params": null
464
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.8,
5
+ "global_step": 12000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
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
+ "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
  "max_steps": 12500,
512
  "num_train_epochs": 5,
513
+ "total_flos": 6101292142348032.0,
514
  "trial_name": null,
515
  "trial_params": null
516
  }
{checkpoint-11000 β†’ checkpoint-12000}/training_args.bin RENAMED
File without changes
{checkpoint-11000 β†’ checkpoint-12000}/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 sha256:59529ca11cd16e7f3bbb54ae86a9114f2c52ef602c31399728eb28f1e3d1a68e
3
  size 133523761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f464404bbabf4ffc076175dc0dd64bed9ebbae82e692e4cc0d024912d83b0bf7
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 sha256:39a09110f783e2e5350e99889528776802102f16699d8374cb32da164aa43612
3
- size 24718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8b338480dce9596ce62d102b2c3b4e900091413645f35902e9c12c0c481491
3
+ size 25820