| { |
| "best_metric": 0.7899897141616012, |
| "best_model_checkpoint": "/kaggle/working/reels-clf/checkpoint-6258", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 6258, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4793863854266539, |
| "grad_norm": 43369.4140625, |
| "learning_rate": 4.6005113454777885e-05, |
| "loss": 0.2922, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9587727708533078, |
| "grad_norm": 16354.4609375, |
| "learning_rate": 4.2010226909555774e-05, |
| "loss": 0.0957, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9896901036983756, |
| "eval_f1": 0.3894120956863034, |
| "eval_loss": 0.0804702639579773, |
| "eval_runtime": 151.5528, |
| "eval_samples_per_second": 110.08, |
| "eval_steps_per_second": 1.722, |
| "step": 1043 |
| }, |
| { |
| "epoch": 1.4381591562799616, |
| "grad_norm": 592.91064453125, |
| "learning_rate": 3.8015340364333656e-05, |
| "loss": 0.0814, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.9175455417066156, |
| "grad_norm": 63719.01171875, |
| "learning_rate": 3.402045381911154e-05, |
| "loss": 0.074, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9937061679554037, |
| "eval_f1": 0.5246078522111747, |
| "eval_loss": 0.06898169219493866, |
| "eval_runtime": 151.5845, |
| "eval_samples_per_second": 110.057, |
| "eval_steps_per_second": 1.722, |
| "step": 2086 |
| }, |
| { |
| "epoch": 2.396931927133269, |
| "grad_norm": 91346.8984375, |
| "learning_rate": 3.002556727388942e-05, |
| "loss": 0.057, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.876318312559923, |
| "grad_norm": 0.34639281034469604, |
| "learning_rate": 2.6030680728667306e-05, |
| "loss": 0.0565, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9947251693340526, |
| "eval_f1": 0.5763717231704362, |
| "eval_loss": 0.07740658521652222, |
| "eval_runtime": 151.2075, |
| "eval_samples_per_second": 110.332, |
| "eval_steps_per_second": 1.726, |
| "step": 3129 |
| }, |
| { |
| "epoch": 3.3557046979865772, |
| "grad_norm": 0.3635995090007782, |
| "learning_rate": 2.2035794183445192e-05, |
| "loss": 0.0405, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.8350910834132312, |
| "grad_norm": 45141.87109375, |
| "learning_rate": 1.8040907638223074e-05, |
| "loss": 0.0347, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9955044056824313, |
| "eval_f1": 0.6777953957165785, |
| "eval_loss": 0.06517060101032257, |
| "eval_runtime": 152.3821, |
| "eval_samples_per_second": 109.481, |
| "eval_steps_per_second": 1.713, |
| "step": 4172 |
| }, |
| { |
| "epoch": 4.314477468839885, |
| "grad_norm": 0.10806822776794434, |
| "learning_rate": 1.4046021093000961e-05, |
| "loss": 0.0214, |
| "step": 4500 |
| }, |
| { |
| "epoch": 4.793863854266538, |
| "grad_norm": 0.16395215690135956, |
| "learning_rate": 1.0051134547778844e-05, |
| "loss": 0.0269, |
| "step": 5000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9956242881975664, |
| "eval_f1": 0.7422681606882496, |
| "eval_loss": 0.06420310586690903, |
| "eval_runtime": 151.8009, |
| "eval_samples_per_second": 109.901, |
| "eval_steps_per_second": 1.719, |
| "step": 5215 |
| }, |
| { |
| "epoch": 5.273250239693192, |
| "grad_norm": 90.11448669433594, |
| "learning_rate": 6.056248002556728e-06, |
| "loss": 0.0169, |
| "step": 5500 |
| }, |
| { |
| "epoch": 5.752636625119846, |
| "grad_norm": 0.08740052580833435, |
| "learning_rate": 2.0613614573346116e-06, |
| "loss": 0.0213, |
| "step": 6000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9957441707127016, |
| "eval_f1": 0.7899897141616012, |
| "eval_loss": 0.061532892286777496, |
| "eval_runtime": 151.598, |
| "eval_samples_per_second": 110.048, |
| "eval_steps_per_second": 1.722, |
| "step": 6258 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 6258, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.307637757681664e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
