| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3766478342749529, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018832391713747645, | |
| "eval_loss": 0.7600103616714478, | |
| "eval_runtime": 7.022, | |
| "eval_samples_per_second": 15.95, | |
| "eval_steps_per_second": 7.975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018832391713747645, | |
| "grad_norm": 0.6724773645401001, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6227, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03766478342749529, | |
| "grad_norm": 0.43917495012283325, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05649717514124294, | |
| "grad_norm": 0.5041059851646423, | |
| "learning_rate": 0.0002, | |
| "loss": 0.465, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07532956685499058, | |
| "grad_norm": 0.5057150721549988, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09416195856873823, | |
| "grad_norm": 0.3785208463668823, | |
| "learning_rate": 0.0002, | |
| "loss": 0.461, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09416195856873823, | |
| "eval_loss": 0.4497997760772705, | |
| "eval_runtime": 5.9882, | |
| "eval_samples_per_second": 18.703, | |
| "eval_steps_per_second": 9.352, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11299435028248588, | |
| "grad_norm": 0.41503942012786865, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3951, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1318267419962335, | |
| "grad_norm": 0.4685976505279541, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4604, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15065913370998116, | |
| "grad_norm": 0.49280235171318054, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4003, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.35098376870155334, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3999, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18832391713747645, | |
| "grad_norm": 0.39404723048210144, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4568, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18832391713747645, | |
| "eval_loss": 0.4238744378089905, | |
| "eval_runtime": 5.972, | |
| "eval_samples_per_second": 18.754, | |
| "eval_steps_per_second": 9.377, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2071563088512241, | |
| "grad_norm": 0.5711905360221863, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4179, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 0.5030353665351868, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4445, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2448210922787194, | |
| "grad_norm": 0.407720685005188, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4066, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.263653483992467, | |
| "grad_norm": 0.41843506693840027, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4076, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2824858757062147, | |
| "grad_norm": 0.6799523234367371, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4233, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2824858757062147, | |
| "eval_loss": 0.41013070940971375, | |
| "eval_runtime": 5.9781, | |
| "eval_samples_per_second": 18.735, | |
| "eval_steps_per_second": 9.368, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "grad_norm": 0.4201280474662781, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4012, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32015065913371, | |
| "grad_norm": 0.47408103942871094, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3687, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 0.41946759819984436, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4167, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3578154425612053, | |
| "grad_norm": 0.43409135937690735, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3949, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "grad_norm": 0.38029003143310547, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4432, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3766478342749529, | |
| "eval_loss": 0.3980959951877594, | |
| "eval_runtime": 5.9981, | |
| "eval_samples_per_second": 18.673, | |
| "eval_steps_per_second": 9.336, | |
| "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": 3.065823967051776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |