| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10576414595452142, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021152829190904283, | |
| "eval_loss": 1.9689923524856567, | |
| "eval_runtime": 6.4166, | |
| "eval_samples_per_second": 31.013, | |
| "eval_steps_per_second": 15.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010576414595452142, | |
| "grad_norm": 5.373104572296143, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1577, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "grad_norm": 3.8552494049072266, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "eval_loss": 1.118636965751648, | |
| "eval_runtime": 6.4605, | |
| "eval_samples_per_second": 30.802, | |
| "eval_steps_per_second": 15.479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03172924378635643, | |
| "grad_norm": 2.8296666145324707, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7073, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04230565838180857, | |
| "grad_norm": 4.8804402351379395, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04230565838180857, | |
| "eval_loss": 0.28694838285446167, | |
| "eval_runtime": 6.4229, | |
| "eval_samples_per_second": 30.983, | |
| "eval_steps_per_second": 15.569, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05288207297726071, | |
| "grad_norm": 1.0777591466903687, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1422, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06345848757271286, | |
| "grad_norm": 3.978870153427124, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4526, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06345848757271286, | |
| "eval_loss": 0.26992300152778625, | |
| "eval_runtime": 6.5063, | |
| "eval_samples_per_second": 30.586, | |
| "eval_steps_per_second": 15.37, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.074034902168165, | |
| "grad_norm": 0.7584536671638489, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1988, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08461131676361713, | |
| "grad_norm": 0.49464961886405945, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1346, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08461131676361713, | |
| "eval_loss": 0.2684724032878876, | |
| "eval_runtime": 6.6633, | |
| "eval_samples_per_second": 29.865, | |
| "eval_steps_per_second": 15.008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09518773135906927, | |
| "grad_norm": 8.192705154418945, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10576414595452142, | |
| "grad_norm": 0.44778746366500854, | |
| "learning_rate": 0.0, | |
| "loss": 0.2014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10576414595452142, | |
| "eval_loss": 0.26204103231430054, | |
| "eval_runtime": 6.4158, | |
| "eval_samples_per_second": 31.017, | |
| "eval_steps_per_second": 15.586, | |
| "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": 1349302685270016.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |