| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009216377502822516, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001843275500564503, | |
| "eval_loss": 10.371973037719727, | |
| "eval_runtime": 19.4745, | |
| "eval_samples_per_second": 469.178, | |
| "eval_steps_per_second": 117.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005529826501693509, | |
| "grad_norm": 0.07208254933357239, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3716, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009216377502822516, | |
| "eval_loss": 10.371664047241211, | |
| "eval_runtime": 19.302, | |
| "eval_samples_per_second": 473.371, | |
| "eval_steps_per_second": 118.382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011059653003387018, | |
| "grad_norm": 0.06621870398521423, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016589479505080527, | |
| "grad_norm": 0.08342023938894272, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018432755005645032, | |
| "eval_loss": 10.370595932006836, | |
| "eval_runtime": 19.265, | |
| "eval_samples_per_second": 474.28, | |
| "eval_steps_per_second": 118.609, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022119306006774036, | |
| "grad_norm": 0.06515509635210037, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.3728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0027649132508467547, | |
| "grad_norm": 0.07225878536701202, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3706, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027649132508467547, | |
| "eval_loss": 10.369028091430664, | |
| "eval_runtime": 19.6179, | |
| "eval_samples_per_second": 465.748, | |
| "eval_steps_per_second": 116.475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033178959010161054, | |
| "grad_norm": 0.07449828833341599, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3691, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0036865510011290063, | |
| "eval_loss": 10.36725902557373, | |
| "eval_runtime": 19.3786, | |
| "eval_samples_per_second": 471.5, | |
| "eval_steps_per_second": 117.914, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038708785511854566, | |
| "grad_norm": 0.08717207610607147, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3667, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004423861201354807, | |
| "grad_norm": 0.12931972742080688, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3669, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004608188751411258, | |
| "eval_loss": 10.365208625793457, | |
| "eval_runtime": 19.5098, | |
| "eval_samples_per_second": 468.329, | |
| "eval_steps_per_second": 117.121, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004976843851524158, | |
| "grad_norm": 0.11614447087049484, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.3667, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0055298265016935095, | |
| "grad_norm": 0.13167273998260498, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0055298265016935095, | |
| "eval_loss": 10.363195419311523, | |
| "eval_runtime": 19.4376, | |
| "eval_samples_per_second": 470.068, | |
| "eval_steps_per_second": 117.556, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006082809151862861, | |
| "grad_norm": 0.1491217315196991, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.3614, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006451464251975761, | |
| "eval_loss": 10.361522674560547, | |
| "eval_runtime": 19.5391, | |
| "eval_samples_per_second": 467.628, | |
| "eval_steps_per_second": 116.945, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006635791802032211, | |
| "grad_norm": 0.14466819167137146, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.364, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007188774452201562, | |
| "grad_norm": 0.17304567992687225, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3644, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007373102002258013, | |
| "eval_loss": 10.36044979095459, | |
| "eval_runtime": 19.359, | |
| "eval_samples_per_second": 471.976, | |
| "eval_steps_per_second": 118.033, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007741757102370913, | |
| "grad_norm": 0.14071166515350342, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3592, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008294739752540263, | |
| "grad_norm": 0.18590952455997467, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3607, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008294739752540263, | |
| "eval_loss": 10.360003471374512, | |
| "eval_runtime": 19.526, | |
| "eval_samples_per_second": 467.94, | |
| "eval_steps_per_second": 117.023, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008847722402709614, | |
| "grad_norm": 0.1559176743030548, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 10.3592, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009216377502822516, | |
| "eval_loss": 10.359918594360352, | |
| "eval_runtime": 19.3944, | |
| "eval_samples_per_second": 471.115, | |
| "eval_steps_per_second": 117.818, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5577533030400.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |