| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 50, | |
| "global_step": 147, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 1.0879597663879395, | |
| "learning_rate": 0.00019577464788732396, | |
| "loss": 0.8681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 0.4811602532863617, | |
| "learning_rate": 0.00018169014084507045, | |
| "loss": 0.3276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 0.6136676073074341, | |
| "learning_rate": 0.0001676056338028169, | |
| "loss": 0.3036, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 0.6780334711074829, | |
| "learning_rate": 0.00015352112676056339, | |
| "loss": 0.314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 0.47117260098457336, | |
| "learning_rate": 0.00013943661971830987, | |
| "loss": 0.3115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 0.0781567394733429, | |
| "eval_runtime": 264.3948, | |
| "eval_samples_per_second": 0.567, | |
| "eval_steps_per_second": 0.095, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.5836557745933533, | |
| "learning_rate": 0.00012535211267605635, | |
| "loss": 0.3005, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.7661027312278748, | |
| "learning_rate": 0.00011126760563380282, | |
| "loss": 0.2917, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 0.49967068433761597, | |
| "learning_rate": 9.718309859154931e-05, | |
| "loss": 0.294, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.4809722304344177, | |
| "learning_rate": 8.309859154929578e-05, | |
| "loss": 0.285, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "grad_norm": 0.6247081160545349, | |
| "learning_rate": 6.901408450704226e-05, | |
| "loss": 0.2824, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6802721088435374, | |
| "eval_loss": 0.07400024682283401, | |
| "eval_runtime": 261.0394, | |
| "eval_samples_per_second": 0.575, | |
| "eval_steps_per_second": 0.096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7482993197278912, | |
| "grad_norm": 0.6426054239273071, | |
| "learning_rate": 5.492957746478874e-05, | |
| "loss": 0.2742, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.525353193283081, | |
| "learning_rate": 4.0845070422535214e-05, | |
| "loss": 0.2708, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8843537414965986, | |
| "grad_norm": 0.5583876967430115, | |
| "learning_rate": 2.676056338028169e-05, | |
| "loss": 0.2713, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.6190481185913086, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 0.2684, | |
| "step": 140 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 147, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7908016076781568e+17, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |