| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8509367363562315, | |
| "eval_steps": 500, | |
| "global_step": 10500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13575889220743959, | |
| "grad_norm": 0.42541322112083435, | |
| "learning_rate": 4.775092768576342e-05, | |
| "loss": 1.6148, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27151778441487917, | |
| "grad_norm": 0.3683030903339386, | |
| "learning_rate": 4.5488279482306095e-05, | |
| "loss": 1.4559, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.40727667662231876, | |
| "grad_norm": 0.2653275728225708, | |
| "learning_rate": 4.322563127884877e-05, | |
| "loss": 1.4429, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5430355688297583, | |
| "grad_norm": 0.2617078423500061, | |
| "learning_rate": 4.096298307539144e-05, | |
| "loss": 1.4354, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.678794461037198, | |
| "grad_norm": 0.2017202079296112, | |
| "learning_rate": 3.8700334871934116e-05, | |
| "loss": 1.4308, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8145533532446375, | |
| "grad_norm": 0.20993387699127197, | |
| "learning_rate": 3.643768666847679e-05, | |
| "loss": 1.4278, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9503122454520772, | |
| "grad_norm": 0.16242703795433044, | |
| "learning_rate": 3.417503846501946e-05, | |
| "loss": 1.4253, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.4292237758636475, | |
| "eval_meteor": 0.03936079398500908, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 213.0238, | |
| "eval_samples_per_second": 7.281, | |
| "eval_steps_per_second": 1.821, | |
| "step": 3683 | |
| }, | |
| { | |
| "epoch": 1.0860711376595167, | |
| "grad_norm": 0.29393067955970764, | |
| "learning_rate": 3.1912390261562137e-05, | |
| "loss": 1.4232, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.2218300298669562, | |
| "grad_norm": 0.14881190657615662, | |
| "learning_rate": 2.9649742058104807e-05, | |
| "loss": 1.4215, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.3575889220743957, | |
| "grad_norm": 0.15426018834114075, | |
| "learning_rate": 2.7387093854647484e-05, | |
| "loss": 1.4205, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4933478142818355, | |
| "grad_norm": 0.20635420083999634, | |
| "learning_rate": 2.5124445651190154e-05, | |
| "loss": 1.4196, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.629106706489275, | |
| "grad_norm": 0.1161305382847786, | |
| "learning_rate": 2.2861797447732827e-05, | |
| "loss": 1.4189, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7648655986967148, | |
| "grad_norm": 0.18034473061561584, | |
| "learning_rate": 2.05991492442755e-05, | |
| "loss": 1.4181, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.9006244909041543, | |
| "grad_norm": 0.12195830792188644, | |
| "learning_rate": 1.8336501040818175e-05, | |
| "loss": 1.4177, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.0, | |
| "eval_gen_len": 19.0, | |
| "eval_loss": 1.4223343133926392, | |
| "eval_meteor": 0.07128909550595973, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 214.8209, | |
| "eval_samples_per_second": 7.22, | |
| "eval_steps_per_second": 1.806, | |
| "step": 7366 | |
| }, | |
| { | |
| "epoch": 2.036383383111594, | |
| "grad_norm": 0.09966401755809784, | |
| "learning_rate": 1.6073852837360848e-05, | |
| "loss": 1.4171, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.1721422753190334, | |
| "grad_norm": 0.12720510363578796, | |
| "learning_rate": 1.3811204633903522e-05, | |
| "loss": 1.4165, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.307901167526473, | |
| "grad_norm": 0.17217351496219635, | |
| "learning_rate": 1.1548556430446195e-05, | |
| "loss": 1.4163, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.4436600597339124, | |
| "grad_norm": 0.1286771595478058, | |
| "learning_rate": 9.285908226988869e-06, | |
| "loss": 1.4161, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.579418951941352, | |
| "grad_norm": 0.12232056260108948, | |
| "learning_rate": 7.023260023531542e-06, | |
| "loss": 1.4158, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.7151778441487915, | |
| "grad_norm": 0.14986146986484528, | |
| "learning_rate": 4.760611820074215e-06, | |
| "loss": 1.4156, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.8509367363562315, | |
| "grad_norm": 0.08726570755243301, | |
| "learning_rate": 2.4979636166168884e-06, | |
| "loss": 1.4155, | |
| "step": 10500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 11049, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5158605926308512e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |