| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004606384448846101, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.212768897692202e-05, | |
| "eval_loss": 3.2426815032958984, | |
| "eval_runtime": 267.9849, | |
| "eval_samples_per_second": 17.057, | |
| "eval_steps_per_second": 8.53, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004606384448846101, | |
| "grad_norm": 2.7321012020111084, | |
| "learning_rate": 5e-05, | |
| "loss": 13.2688, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009212768897692202, | |
| "grad_norm": 3.018977403640747, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009212768897692202, | |
| "eval_loss": 3.052807331085205, | |
| "eval_runtime": 268.2599, | |
| "eval_samples_per_second": 17.039, | |
| "eval_steps_per_second": 8.522, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013819153346538303, | |
| "grad_norm": 5.066298961639404, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.4043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018425537795384403, | |
| "grad_norm": 2.848259687423706, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.0901, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018425537795384403, | |
| "eval_loss": 2.4847605228424072, | |
| "eval_runtime": 267.7916, | |
| "eval_samples_per_second": 17.069, | |
| "eval_steps_per_second": 8.536, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023031922244230504, | |
| "grad_norm": 3.9828901290893555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 9.5732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0027638306693076606, | |
| "grad_norm": 3.964927911758423, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1613, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027638306693076606, | |
| "eval_loss": 2.22302508354187, | |
| "eval_runtime": 268.9169, | |
| "eval_samples_per_second": 16.998, | |
| "eval_steps_per_second": 8.501, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0032244691141922704, | |
| "grad_norm": 3.796499013900757, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.9359, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0036851075590768807, | |
| "grad_norm": 3.254136562347412, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 8.5177, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0036851075590768807, | |
| "eval_loss": 2.112778663635254, | |
| "eval_runtime": 268.0758, | |
| "eval_samples_per_second": 17.051, | |
| "eval_steps_per_second": 8.527, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0041457460039614905, | |
| "grad_norm": 3.4319705963134766, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.4412, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004606384448846101, | |
| "grad_norm": 3.498079776763916, | |
| "learning_rate": 0.0, | |
| "loss": 8.5155, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004606384448846101, | |
| "eval_loss": 2.092695713043213, | |
| "eval_runtime": 268.109, | |
| "eval_samples_per_second": 17.049, | |
| "eval_steps_per_second": 8.526, | |
| "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": 5301180756393984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |