| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9996790752964305e-05, | |
| "loss": 0.7636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.991987177050743e-05, | |
| "loss": 2.6172, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9680771188662044e-05, | |
| "loss": 1.5854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9286529995722624e-05, | |
| "loss": 0.6342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8743466161445823e-05, | |
| "loss": 0.4285, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8060282634540053e-05, | |
| "loss": 0.4147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.72479278722912e-05, | |
| "loss": 0.3739, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.631942038446304e-05, | |
| "loss": 0.3636, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.5289640103269626e-05, | |
| "loss": 0.2994, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.4175089922850633e-05, | |
| "loss": 0.2938, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2993631229733584e-05, | |
| "loss": 0.3058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1764197662578087e-05, | |
| "loss": 0.3086, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.0506491688387128e-05, | |
| "loss": 0.3109, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.24066885774754e-06, | |
| "loss": 0.3275, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.987014799113398e-06, | |
| "loss": 0.3047, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 6.7656201285076195e-06, | |
| "loss": 0.2778, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.5960584844236565e-06, | |
| "loss": 0.269, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.497072847626087e-06, | |
| "loss": 0.3077, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.48627517277778e-06, | |
| "loss": 0.3078, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.5798641454908945e-06, | |
| "loss": 0.2905, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.7923655879272395e-06, | |
| "loss": 0.2927, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1363996731159188e-06, | |
| "loss": 0.3442, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.22478678529197e-07, | |
| "loss": 0.2968, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.588385200461307e-07, | |
| "loss": 0.2628, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.1306766081048456e-08, | |
| "loss": 0.2698, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.2914734482765198, | |
| "eval_runtime": 11.0655, | |
| "eval_samples_per_second": 19.882, | |
| "eval_steps_per_second": 0.361, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 124, | |
| "total_flos": 880074424320.0, | |
| "train_loss": 0.4545349882495019, | |
| "train_runtime": 740.5857, | |
| "train_samples_per_second": 2.664, | |
| "train_steps_per_second": 0.167 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 124, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 880074424320.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |