Baselhany commited on
Commit
4bf1dc1
·
verified ·
1 Parent(s): 2ec4056

Training in progress, step 16578, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f53dbd7245e348dee415a2c3edb732728f914a9235424eb142a38b0fcdb4922b
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6fe5823dfdfa0755102c0eb6bc2e20653f20acc9d8c12b2a794fe6e3aaf193
3
  size 290403936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c4ef6c5232b5ee02ac43851b59bab6c09b948ea11cd09d00c3480bccc004904
3
  size 574811514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2054e9edbc564f8fc2b480dd761a14114f25a3409569e10e474e5ef6b53cf40c
3
  size 574811514
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:575455a76dde8fe52d7ea4902f127e1ac96a955301198cd8f9f854c6f6b225c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca0c14548c719bd1dc6b14340ff0cda7af14cb7800c6ddca9bb7602ae76e724
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1e137e6d7eb503a22b6951a72d7291375278d1d1c16a253949aea8f67d5e881
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde6e5d2db511c993b2eaa11f1389bc72ef762a7921595905540728ea4683973
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.473509293967616,
3
  "best_model_checkpoint": "./Whisper_base_fine_tune_Quran/checkpoint-13600",
4
- "epoch": 5.790664013026959,
5
  "eval_steps": 800,
6
- "global_step": 16000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -2447,6 +2447,83 @@
2447
  "eval_steps_per_second": 0.159,
2448
  "eval_wer": 11.635815589133207,
2449
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2450
  }
2451
  ],
2452
  "logging_steps": 50,
@@ -2461,12 +2538,12 @@
2461
  "should_evaluate": false,
2462
  "should_log": false,
2463
  "should_save": true,
2464
- "should_training_stop": false
2465
  },
2466
  "attributes": {}
2467
  }
2468
  },
2469
- "total_flos": 6.641663606784e+19,
2470
  "train_batch_size": 16,
2471
  "trial_name": null,
2472
  "trial_params": null
 
1
  {
2
  "best_metric": 11.473509293967616,
3
  "best_model_checkpoint": "./Whisper_base_fine_tune_Quran/checkpoint-13600",
4
+ "epoch": 5.999819070019902,
5
  "eval_steps": 800,
6
+ "global_step": 16578,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
2447
  "eval_steps_per_second": 0.159,
2448
  "eval_wer": 11.635815589133207,
2449
  "step": 16000
2450
+ },
2451
+ {
2452
+ "epoch": 5.808757011036729,
2453
+ "grad_norm": 444.3935852050781,
2454
+ "learning_rate": 2.6586324318237375e-07,
2455
+ "loss": 0.0008,
2456
+ "step": 16050
2457
+ },
2458
+ {
2459
+ "epoch": 5.826850009046499,
2460
+ "grad_norm": 8292.3271484375,
2461
+ "learning_rate": 2.179293688860995e-07,
2462
+ "loss": 0.0008,
2463
+ "step": 16100
2464
+ },
2465
+ {
2466
+ "epoch": 5.844943007056269,
2467
+ "grad_norm": 14908.7646484375,
2468
+ "learning_rate": 1.7474715294875654e-07,
2469
+ "loss": 0.0005,
2470
+ "step": 16150
2471
+ },
2472
+ {
2473
+ "epoch": 5.863036005066039,
2474
+ "grad_norm": 7871.6640625,
2475
+ "learning_rate": 1.363207170779035e-07,
2476
+ "loss": 0.0005,
2477
+ "step": 16200
2478
+ },
2479
+ {
2480
+ "epoch": 5.881129003075809,
2481
+ "grad_norm": 12875.3583984375,
2482
+ "learning_rate": 1.026537290457541e-07,
2483
+ "loss": 0.0006,
2484
+ "step": 16250
2485
+ },
2486
+ {
2487
+ "epoch": 5.89922200108558,
2488
+ "grad_norm": 405.7221984863281,
2489
+ "learning_rate": 7.374940233906836e-08,
2490
+ "loss": 0.0006,
2491
+ "step": 16300
2492
+ },
2493
+ {
2494
+ "epoch": 5.91731499909535,
2495
+ "grad_norm": 11683.8515625,
2496
+ "learning_rate": 4.9610495852453476e-08,
2497
+ "loss": 0.0008,
2498
+ "step": 16350
2499
+ },
2500
+ {
2501
+ "epoch": 5.93540799710512,
2502
+ "grad_norm": 29532.91796875,
2503
+ "learning_rate": 3.023931362498566e-08,
2504
+ "loss": 0.0007,
2505
+ "step": 16400
2506
+ },
2507
+ {
2508
+ "epoch": 5.95350099511489,
2509
+ "grad_norm": 11724.4853515625,
2510
+ "learning_rate": 1.563770462034708e-08,
2511
+ "loss": 0.0006,
2512
+ "step": 16450
2513
+ },
2514
+ {
2515
+ "epoch": 5.971593993124661,
2516
+ "grad_norm": 15493.84765625,
2517
+ "learning_rate": 5.80706255029484e-09,
2518
+ "loss": 0.0007,
2519
+ "step": 16500
2520
+ },
2521
+ {
2522
+ "epoch": 5.989686991134431,
2523
+ "grad_norm": 20287.396484375,
2524
+ "learning_rate": 7.483257416562861e-10,
2525
+ "loss": 0.0005,
2526
+ "step": 16550
2527
  }
2528
  ],
2529
  "logging_steps": 50,
 
2538
  "should_evaluate": false,
2539
  "should_log": false,
2540
  "should_save": true,
2541
+ "should_training_stop": true
2542
  },
2543
  "attributes": {}
2544
  }
2545
  },
2546
+ "total_flos": 6.881593704579072e+19,
2547
  "train_batch_size": 16,
2548
  "trial_name": null,
2549
  "trial_params": null