| { | |
| "best_metric": 0.6125127077102661, | |
| "best_model_checkpoint": "AIStockbot/checkpoint-20", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 14.799009323120117, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 41.67997741699219, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 13.868035316467285, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2359, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 41.22408676147461, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 22.224599838256836, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.8084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 19.105688095092773, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2558, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 29.52898597717285, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.5596, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 44.25790786743164, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.4768, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 41.738868713378906, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.3178, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 19.59181785583496, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.3079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 30.149559020996094, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.8382, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 19.159807205200195, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6248, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 28.319700241088867, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.6566, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 37.52927780151367, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.6355, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 9.751605987548828, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2812, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.6529011726379395, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.1552, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 12.242779731750488, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.3845, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 14.371271133422852, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.6255, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 13.148179054260254, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.2752, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.92774772644043, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8, | |
| "eval_f1_macro": 0.7398550724637681, | |
| "eval_f1_micro": 0.8, | |
| "eval_f1_weighted": 0.8067391304347826, | |
| "eval_loss": 0.6125127077102661, | |
| "eval_precision_macro": 0.7196969696969697, | |
| "eval_precision_micro": 0.8, | |
| "eval_precision_weighted": 0.8204545454545453, | |
| "eval_recall_macro": 0.7777777777777778, | |
| "eval_recall_micro": 0.8, | |
| "eval_recall_weighted": 0.8, | |
| "eval_runtime": 7.8949, | |
| "eval_samples_per_second": 5.067, | |
| "eval_steps_per_second": 0.38, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 10524536709120.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |