| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0053273666826487666, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010654733365297533, | |
| "eval_loss": 3.038520336151123, | |
| "eval_runtime": 281.3921, | |
| "eval_samples_per_second": 14.044, | |
| "eval_steps_per_second": 7.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005327366682648767, | |
| "grad_norm": 1.6866191625595093, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9399, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010654733365297534, | |
| "grad_norm": 1.4231024980545044, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010654733365297534, | |
| "eval_loss": 2.8423962593078613, | |
| "eval_runtime": 281.9048, | |
| "eval_samples_per_second": 14.019, | |
| "eval_steps_per_second": 7.009, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00159821000479463, | |
| "grad_norm": 2.252937078475952, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7126, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002130946673059507, | |
| "grad_norm": 2.0720081329345703, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002130946673059507, | |
| "eval_loss": 2.4983227252960205, | |
| "eval_runtime": 282.0891, | |
| "eval_samples_per_second": 14.01, | |
| "eval_steps_per_second": 7.005, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0026636833413243833, | |
| "grad_norm": 2.7650818824768066, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4632, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00319642000958926, | |
| "grad_norm": 1.7404818534851074, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2886, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00319642000958926, | |
| "eval_loss": 2.391108274459839, | |
| "eval_runtime": 282.9021, | |
| "eval_samples_per_second": 13.969, | |
| "eval_steps_per_second": 6.985, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0037291566778541365, | |
| "grad_norm": 2.092820167541504, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004261893346119014, | |
| "grad_norm": 2.1878769397735596, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4348, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004261893346119014, | |
| "eval_loss": 2.3634743690490723, | |
| "eval_runtime": 282.4788, | |
| "eval_samples_per_second": 13.99, | |
| "eval_steps_per_second": 6.995, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00479463001438389, | |
| "grad_norm": 1.7152621746063232, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0053273666826487666, | |
| "grad_norm": 1.8380874395370483, | |
| "learning_rate": 0.0, | |
| "loss": 2.2616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0053273666826487666, | |
| "eval_loss": 2.3588783740997314, | |
| "eval_runtime": 282.7819, | |
| "eval_samples_per_second": 13.975, | |
| "eval_steps_per_second": 6.988, | |
| "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": 9340299453136896.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |