| { |
| "best_global_step": 305, |
| "best_metric": 0.7205882352941176, |
| "best_model_checkpoint": "/content/agri-utilization-classifier/transformer/checkpoint-305", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 305, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08196721311475409, |
| "grad_norm": 3.737260103225708, |
| "learning_rate": 3.157894736842105e-06, |
| "loss": 0.5265155029296875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.16393442622950818, |
| "grad_norm": 3.5834667682647705, |
| "learning_rate": 6.447368421052632e-06, |
| "loss": 0.46113067626953125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2459016393442623, |
| "grad_norm": 4.713325500488281, |
| "learning_rate": 9.736842105263159e-06, |
| "loss": 0.36277122497558595, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 5.049388885498047, |
| "learning_rate": 1.3026315789473684e-05, |
| "loss": 0.2863706398010254, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "grad_norm": 3.5716683864593506, |
| "learning_rate": 1.6315789473684213e-05, |
| "loss": 0.30932790756225587, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.4918032786885246, |
| "grad_norm": 3.1771602630615234, |
| "learning_rate": 1.960526315789474e-05, |
| "loss": 0.34346282958984375, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5737704918032787, |
| "grad_norm": 13.294544219970703, |
| "learning_rate": 1.9679533867443555e-05, |
| "loss": 0.2966791343688965, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 4.51957893371582, |
| "learning_rate": 1.9315367807720323e-05, |
| "loss": 0.3470170211791992, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7377049180327869, |
| "grad_norm": 2.978902816772461, |
| "learning_rate": 1.8951201747997088e-05, |
| "loss": 0.33052406311035154, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.819672131147541, |
| "grad_norm": 3.3191263675689697, |
| "learning_rate": 1.8587035688273852e-05, |
| "loss": 0.21728967666625976, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9016393442622951, |
| "grad_norm": 3.7143661975860596, |
| "learning_rate": 1.822286962855062e-05, |
| "loss": 0.23666904449462892, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 1.896660566329956, |
| "learning_rate": 1.7858703568827385e-05, |
| "loss": 0.21057628631591796, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9611451942740287, |
| "eval_f1": 0.7205882352941176, |
| "eval_loss": 0.1562921404838562, |
| "eval_precision": 0.8596491228070176, |
| "eval_recall": 0.620253164556962, |
| "eval_roc_auc": 0.9517677869925796, |
| "eval_runtime": 3.9768, |
| "eval_samples_per_second": 245.924, |
| "eval_steps_per_second": 7.795, |
| "step": 305 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1525, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 641596308495360.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
