| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3184713375796178, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006369426751592357, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.2416, | |
| "eval_samples_per_second": 11.402, | |
| "eval_steps_per_second": 1.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01910828025477707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03184713375796178, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.968, | |
| "eval_samples_per_second": 11.538, | |
| "eval_steps_per_second": 1.48, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03821656050955414, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05732484076433121, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06369426751592357, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.0759, | |
| "eval_samples_per_second": 11.484, | |
| "eval_steps_per_second": 1.473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07643312101910828, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09554140127388536, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09554140127388536, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1097, | |
| "eval_samples_per_second": 11.467, | |
| "eval_steps_per_second": 1.471, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11464968152866242, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12738853503184713, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1132, | |
| "eval_samples_per_second": 11.465, | |
| "eval_steps_per_second": 1.471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1337579617834395, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15286624203821655, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1592356687898089, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1113, | |
| "eval_samples_per_second": 11.466, | |
| "eval_steps_per_second": 1.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17197452229299362, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1910828025477707, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1910828025477707, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1079, | |
| "eval_samples_per_second": 11.468, | |
| "eval_steps_per_second": 1.471, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21019108280254778, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2229299363057325, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1162, | |
| "eval_samples_per_second": 11.464, | |
| "eval_steps_per_second": 1.471, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22929936305732485, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2484076433121019, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25477707006369427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.0921, | |
| "eval_samples_per_second": 11.476, | |
| "eval_steps_per_second": 1.472, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.267515923566879, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28662420382165604, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.28662420382165604, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1002, | |
| "eval_samples_per_second": 11.472, | |
| "eval_steps_per_second": 1.472, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3057324840764331, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3184713375796178, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1037, | |
| "eval_samples_per_second": 11.47, | |
| "eval_steps_per_second": 1.472, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.421305055864422e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |