| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06668889629876626, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001333777925975325, | |
| "eval_loss": 16.58147430419922, | |
| "eval_runtime": 21.1094, | |
| "eval_samples_per_second": 14.97, | |
| "eval_steps_per_second": 7.485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006668889629876626, | |
| "grad_norm": 19.17524528503418, | |
| "learning_rate": 5e-05, | |
| "loss": 16.444, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013337779259753251, | |
| "grad_norm": 26.007152557373047, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013337779259753251, | |
| "eval_loss": 5.221940040588379, | |
| "eval_runtime": 21.3199, | |
| "eval_samples_per_second": 14.822, | |
| "eval_steps_per_second": 7.411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020006668889629875, | |
| "grad_norm": 14.601143836975098, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6293, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026675558519506502, | |
| "grad_norm": 5.472019195556641, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026675558519506502, | |
| "eval_loss": 0.4065855145454407, | |
| "eval_runtime": 21.3794, | |
| "eval_samples_per_second": 14.781, | |
| "eval_steps_per_second": 7.39, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03334444814938313, | |
| "grad_norm": 10.734155654907227, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04001333777925975, | |
| "grad_norm": 9.736656188964844, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4301, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04001333777925975, | |
| "eval_loss": 0.3173398971557617, | |
| "eval_runtime": 21.5064, | |
| "eval_samples_per_second": 14.693, | |
| "eval_steps_per_second": 7.347, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04668222740913638, | |
| "grad_norm": 7.513450622558594, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2686, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.053351117039013005, | |
| "grad_norm": 9.263309478759766, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3096, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053351117039013005, | |
| "eval_loss": 0.2830474078655243, | |
| "eval_runtime": 21.4653, | |
| "eval_samples_per_second": 14.721, | |
| "eval_steps_per_second": 7.361, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06002000666888963, | |
| "grad_norm": 1.0636922121047974, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3118, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06668889629876626, | |
| "grad_norm": 0.9964779615402222, | |
| "learning_rate": 0.0, | |
| "loss": 0.1974, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06668889629876626, | |
| "eval_loss": 0.2577662765979767, | |
| "eval_runtime": 21.5386, | |
| "eval_samples_per_second": 14.671, | |
| "eval_steps_per_second": 7.336, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |