| { | |
| "best_metric": 0.10429740697145462, | |
| "best_model_checkpoint": "./classifier/checkpoint-40", | |
| "epoch": 1.2903225806451613, | |
| "eval_steps": 10, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 1.5601885318756104, | |
| "learning_rate": 9.35483870967742e-05, | |
| "loss": 0.1631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "eval_accuracy": 0.9565217391304348, | |
| "eval_f1": 0.8979591836734694, | |
| "eval_loss": 0.15750479698181152, | |
| "eval_precision": 0.9705882352941176, | |
| "eval_recall": 0.8354430379746836, | |
| "eval_runtime": 0.9626, | |
| "eval_samples_per_second": 358.397, | |
| "eval_steps_per_second": 6.233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 3.452174663543701, | |
| "learning_rate": 8.709677419354839e-05, | |
| "loss": 0.0953, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "eval_accuracy": 0.9710144927536232, | |
| "eval_f1": 0.9375, | |
| "eval_loss": 0.11482395976781845, | |
| "eval_precision": 0.9259259259259259, | |
| "eval_recall": 0.9493670886075949, | |
| "eval_runtime": 0.6977, | |
| "eval_samples_per_second": 494.448, | |
| "eval_steps_per_second": 8.599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 4.141051769256592, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.0984, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "eval_accuracy": 0.9710144927536232, | |
| "eval_f1": 0.935064935064935, | |
| "eval_loss": 0.11602061241865158, | |
| "eval_precision": 0.96, | |
| "eval_recall": 0.9113924050632911, | |
| "eval_runtime": 0.8289, | |
| "eval_samples_per_second": 416.231, | |
| "eval_steps_per_second": 7.239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.5622131824493408, | |
| "learning_rate": 7.419354838709677e-05, | |
| "loss": 0.0316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "eval_accuracy": 0.9826086956521739, | |
| "eval_f1": 0.9620253164556962, | |
| "eval_loss": 0.10429740697145462, | |
| "eval_precision": 0.9620253164556962, | |
| "eval_recall": 0.9620253164556962, | |
| "eval_runtime": 0.6866, | |
| "eval_samples_per_second": 502.488, | |
| "eval_steps_per_second": 8.739, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 155, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 455444722939380.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |