| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004024934469035676, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.012467234517838e-05, | |
| "eval_loss": 2.1559741497039795, | |
| "eval_runtime": 857.823, | |
| "eval_samples_per_second": 24.391, | |
| "eval_steps_per_second": 12.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002012467234517838, | |
| "grad_norm": 6.170618534088135, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4469, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004024934469035676, | |
| "grad_norm": 1.0294487476348877, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006037401703553514, | |
| "grad_norm": 0.6725739240646362, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008049868938071352, | |
| "grad_norm": 1.0152796506881714, | |
| "learning_rate": 0.0002, | |
| "loss": 1.29, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001006233617258919, | |
| "grad_norm": 0.8606889843940735, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001006233617258919, | |
| "eval_loss": 1.4589308500289917, | |
| "eval_runtime": 858.7739, | |
| "eval_samples_per_second": 24.364, | |
| "eval_steps_per_second": 12.182, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0012074803407107028, | |
| "grad_norm": 0.7305423021316528, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2205, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0014087270641624865, | |
| "grad_norm": 1.4533841609954834, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2138, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0016099737876142705, | |
| "grad_norm": 1.0131192207336426, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3712, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0018112205110660542, | |
| "grad_norm": 0.9000447988510132, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1396, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.002012467234517838, | |
| "grad_norm": 1.9898265600204468, | |
| "learning_rate": 0.0002, | |
| "loss": 1.229, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002012467234517838, | |
| "eval_loss": 1.4349274635314941, | |
| "eval_runtime": 858.4486, | |
| "eval_samples_per_second": 24.373, | |
| "eval_steps_per_second": 12.187, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002213713957969622, | |
| "grad_norm": 1.271390676498413, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3306, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0024149606814214057, | |
| "grad_norm": 0.9250841736793518, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1564, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0026162074048731894, | |
| "grad_norm": 1.0612225532531738, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2448, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.002817454128324973, | |
| "grad_norm": 0.643467366695404, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1702, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.003018700851776757, | |
| "grad_norm": 1.3284869194030762, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2826, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003018700851776757, | |
| "eval_loss": 1.407882809638977, | |
| "eval_runtime": 858.6574, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 12.184, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003219947575228541, | |
| "grad_norm": 1.3226466178894043, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3085, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0034211942986803246, | |
| "grad_norm": 1.9192092418670654, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1933, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0036224410221321083, | |
| "grad_norm": 1.0368775129318237, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2231, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.003823687745583892, | |
| "grad_norm": 1.5248116254806519, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2734, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004024934469035676, | |
| "grad_norm": 0.9554014801979065, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1498, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004024934469035676, | |
| "eval_loss": 1.397660255432129, | |
| "eval_runtime": 858.6574, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 12.184, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.68217396985856e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |