| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 720, | |
| "global_step": 7198, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13892747985551543, | |
| "grad_norm": 0.889398455619812, | |
| "learning_rate": 0.0007907752153375939, | |
| "loss": 0.3895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2000555709919422, | |
| "eval_loss": 0.2990996241569519, | |
| "eval_runtime": 6.0564, | |
| "eval_samples_per_second": 82.558, | |
| "eval_steps_per_second": 5.284, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.27785495971103086, | |
| "grad_norm": 0.5278475880622864, | |
| "learning_rate": 0.0007815133833472261, | |
| "loss": 0.2897, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4001111419838844, | |
| "eval_loss": 0.2636842131614685, | |
| "eval_runtime": 6.0156, | |
| "eval_samples_per_second": 83.118, | |
| "eval_steps_per_second": 5.32, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.41678243956654626, | |
| "grad_norm": 1.208860158920288, | |
| "learning_rate": 0.0007722515513568584, | |
| "loss": 0.2681, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5557099194220617, | |
| "grad_norm": 0.7001394629478455, | |
| "learning_rate": 0.0007629897193664907, | |
| "loss": 0.2536, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6001667129758266, | |
| "eval_loss": 0.25593382120132446, | |
| "eval_runtime": 6.0644, | |
| "eval_samples_per_second": 82.449, | |
| "eval_steps_per_second": 5.277, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.6946373992775771, | |
| "grad_norm": 0.7066700458526611, | |
| "learning_rate": 0.000753727887376123, | |
| "loss": 0.2453, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8002222839677688, | |
| "eval_loss": 0.24263954162597656, | |
| "eval_runtime": 6.2582, | |
| "eval_samples_per_second": 79.896, | |
| "eval_steps_per_second": 5.113, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.8335648791330925, | |
| "grad_norm": 0.8669331073760986, | |
| "learning_rate": 0.000744484579049736, | |
| "loss": 0.2378, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.972492358988608, | |
| "grad_norm": 0.752050518989563, | |
| "learning_rate": 0.0007352412707233491, | |
| "loss": 0.2335, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.000277854959711, | |
| "eval_loss": 0.24230095744132996, | |
| "eval_runtime": 6.2445, | |
| "eval_samples_per_second": 80.07, | |
| "eval_steps_per_second": 5.124, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.1114198388441234, | |
| "grad_norm": 0.5285800695419312, | |
| "learning_rate": 0.0007259794387329814, | |
| "loss": 0.2214, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.2003334259516532, | |
| "eval_loss": 0.23442834615707397, | |
| "eval_runtime": 6.0486, | |
| "eval_samples_per_second": 82.664, | |
| "eval_steps_per_second": 5.291, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 1.2503473186996388, | |
| "grad_norm": 0.7171725630760193, | |
| "learning_rate": 0.0007167176067426138, | |
| "loss": 0.2204, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.3892747985551543, | |
| "grad_norm": 0.6683080792427063, | |
| "learning_rate": 0.000707455774752246, | |
| "loss": 0.217, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4003889969435954, | |
| "eval_loss": 0.2214350551366806, | |
| "eval_runtime": 6.0608, | |
| "eval_samples_per_second": 82.498, | |
| "eval_steps_per_second": 5.28, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 1.5282022784106695, | |
| "grad_norm": 0.8774034380912781, | |
| "learning_rate": 0.0006981939427618783, | |
| "loss": 0.2154, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.6004445679355377, | |
| "eval_loss": 0.2222467064857483, | |
| "eval_runtime": 6.2569, | |
| "eval_samples_per_second": 79.912, | |
| "eval_steps_per_second": 5.114, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 1.667129758266185, | |
| "grad_norm": 0.6040942668914795, | |
| "learning_rate": 0.0006889506344354914, | |
| "loss": 0.2133, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.8005001389274797, | |
| "eval_loss": 0.2248920053243637, | |
| "eval_runtime": 6.2381, | |
| "eval_samples_per_second": 80.153, | |
| "eval_steps_per_second": 5.13, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 1.8060572381217006, | |
| "grad_norm": 0.8217343688011169, | |
| "learning_rate": 0.0006796888024451237, | |
| "loss": 0.2108, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.9449847179772157, | |
| "grad_norm": 0.6363208889961243, | |
| "learning_rate": 0.0006704269704547561, | |
| "loss": 0.2095, | |
| "step": 7000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 43188, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.252742677944074e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |