| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011384479160078426, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002529884257795206, | |
| "eval_loss": 8.741473197937012, | |
| "eval_runtime": 586.1352, | |
| "eval_samples_per_second": 11.359, | |
| "eval_steps_per_second": 1.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007589652773385617, | |
| "grad_norm": 26.1434383392334, | |
| "learning_rate": 3e-05, | |
| "loss": 8.4933, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001264942128897603, | |
| "eval_loss": 5.998294830322266, | |
| "eval_runtime": 591.3249, | |
| "eval_samples_per_second": 11.259, | |
| "eval_steps_per_second": 1.409, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015179305546771235, | |
| "grad_norm": 16.133859634399414, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1644, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002276895832015685, | |
| "grad_norm": 13.156013488769531, | |
| "learning_rate": 9e-05, | |
| "loss": 5.3902, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002529884257795206, | |
| "eval_loss": 4.7294020652771, | |
| "eval_runtime": 591.5744, | |
| "eval_samples_per_second": 11.255, | |
| "eval_steps_per_second": 1.408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003035861109354247, | |
| "grad_norm": 17.320507049560547, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.86, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0037948263866928087, | |
| "grad_norm": 11.7354736328125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.0561, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0037948263866928087, | |
| "eval_loss": 4.001941204071045, | |
| "eval_runtime": 591.4343, | |
| "eval_samples_per_second": 11.257, | |
| "eval_steps_per_second": 1.408, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00455379166403137, | |
| "grad_norm": 10.361626625061035, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 4.1918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005059768515590412, | |
| "eval_loss": 3.7069029808044434, | |
| "eval_runtime": 591.3495, | |
| "eval_samples_per_second": 11.259, | |
| "eval_steps_per_second": 1.409, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005312756941369933, | |
| "grad_norm": 10.757951736450195, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 3.6442, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006071722218708494, | |
| "grad_norm": 9.885283470153809, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 3.736, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006324710644488015, | |
| "eval_loss": 3.5459110736846924, | |
| "eval_runtime": 591.4792, | |
| "eval_samples_per_second": 11.257, | |
| "eval_steps_per_second": 1.408, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006830687496047056, | |
| "grad_norm": 13.528706550598145, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 3.6003, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007589652773385617, | |
| "grad_norm": 10.549182891845703, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6271, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007589652773385617, | |
| "eval_loss": 3.423410415649414, | |
| "eval_runtime": 591.4513, | |
| "eval_samples_per_second": 11.257, | |
| "eval_steps_per_second": 1.408, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008348618050724179, | |
| "grad_norm": 10.609362602233887, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 3.0585, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00885459490228322, | |
| "eval_loss": 3.3249850273132324, | |
| "eval_runtime": 591.8226, | |
| "eval_samples_per_second": 11.25, | |
| "eval_steps_per_second": 1.408, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00910758332806274, | |
| "grad_norm": 9.735877990722656, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 3.5678, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009866548605401303, | |
| "grad_norm": 9.53584098815918, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 3.331, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010119537031180823, | |
| "eval_loss": 3.270254135131836, | |
| "eval_runtime": 591.7633, | |
| "eval_samples_per_second": 11.251, | |
| "eval_steps_per_second": 1.408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010625513882739865, | |
| "grad_norm": 9.458514213562012, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.4146, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011384479160078426, | |
| "grad_norm": 8.75707721710205, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.0878, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011384479160078426, | |
| "eval_loss": 3.243670701980591, | |
| "eval_runtime": 591.8535, | |
| "eval_samples_per_second": 11.249, | |
| "eval_steps_per_second": 1.407, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.034770185781248e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |