| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-90", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.9794238683127575e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.8971193415637865e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.650205761316873e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.48559670781893e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.403292181069959e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.2386831275720165e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.1563786008230455e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.9917695473251035e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.74485596707819e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.10555555555555556, | |
| "eval_f1_macro": 0.031825795644891124, | |
| "eval_f1_micro": 0.10555555555555556, | |
| "eval_f1_weighted": 0.020156337241764376, | |
| "eval_loss": NaN, | |
| "eval_precision_macro": 0.017592592592592594, | |
| "eval_precision_micro": 0.10555555555555556, | |
| "eval_precision_weighted": 0.011141975308641975, | |
| "eval_recall_macro": 0.16666666666666666, | |
| "eval_recall_micro": 0.10555555555555556, | |
| "eval_recall_weighted": 0.10555555555555556, | |
| "eval_runtime": 50.6187, | |
| "eval_samples_per_second": 3.556, | |
| "eval_steps_per_second": 0.237, | |
| "step": 90 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 5.564124325122048e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |