| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03678499172337686, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007356998344675372, | |
| "eval_loss": 5.8742570877075195, | |
| "eval_runtime": 70.8587, | |
| "eval_samples_per_second": 8.087, | |
| "eval_steps_per_second": 4.05, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036784991723376862, | |
| "grad_norm": 4.493916034698486, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1495, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0073569983446753725, | |
| "grad_norm": 4.465775012969971, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9538, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073569983446753725, | |
| "eval_loss": 4.622633934020996, | |
| "eval_runtime": 69.7393, | |
| "eval_samples_per_second": 8.216, | |
| "eval_steps_per_second": 4.115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011035497517013059, | |
| "grad_norm": 4.096086025238037, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.9878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014713996689350745, | |
| "grad_norm": 3.0774028301239014, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014713996689350745, | |
| "eval_loss": 2.295875072479248, | |
| "eval_runtime": 69.7741, | |
| "eval_samples_per_second": 8.212, | |
| "eval_steps_per_second": 4.113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01839249586168843, | |
| "grad_norm": 5.925327301025391, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4277, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022070995034026118, | |
| "grad_norm": 5.442073345184326, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022070995034026118, | |
| "eval_loss": 0.6382670402526855, | |
| "eval_runtime": 69.817, | |
| "eval_samples_per_second": 8.207, | |
| "eval_steps_per_second": 4.111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025749494206363802, | |
| "grad_norm": 5.2258806228637695, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6099, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02942799337870149, | |
| "grad_norm": 1.8065462112426758, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5825, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02942799337870149, | |
| "eval_loss": 0.33358922600746155, | |
| "eval_runtime": 69.8878, | |
| "eval_samples_per_second": 8.199, | |
| "eval_steps_per_second": 4.107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033106492551039174, | |
| "grad_norm": 2.2164061069488525, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.29, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03678499172337686, | |
| "grad_norm": 4.350715637207031, | |
| "learning_rate": 0.0, | |
| "loss": 0.5206, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03678499172337686, | |
| "eval_loss": 0.31103309988975525, | |
| "eval_runtime": 69.89, | |
| "eval_samples_per_second": 8.199, | |
| "eval_steps_per_second": 4.106, | |
| "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": 1.7382794559750144e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |