| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1423487544483986, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028469750889679717, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.453, | |
| "eval_samples_per_second": 12.475, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008540925266903915, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.9665, | |
| "eval_samples_per_second": 12.342, | |
| "eval_steps_per_second": 1.543, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01708185053380783, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025622775800711744, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.028469750889679714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0728, | |
| "eval_samples_per_second": 12.315, | |
| "eval_steps_per_second": 1.539, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03416370106761566, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042704626334519574, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.042704626334519574, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0649, | |
| "eval_samples_per_second": 12.317, | |
| "eval_steps_per_second": 1.54, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05124555160142349, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0782, | |
| "eval_samples_per_second": 12.313, | |
| "eval_steps_per_second": 1.539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0597864768683274, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06832740213523132, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0711743772241993, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0728, | |
| "eval_samples_per_second": 12.315, | |
| "eval_steps_per_second": 1.539, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07686832740213523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08540925266903915, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08540925266903915, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0844, | |
| "eval_samples_per_second": 12.312, | |
| "eval_steps_per_second": 1.539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09395017793594305, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.099644128113879, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0691, | |
| "eval_samples_per_second": 12.316, | |
| "eval_steps_per_second": 1.539, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10249110320284698, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1110320284697509, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11387900355871886, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.1076, | |
| "eval_samples_per_second": 12.306, | |
| "eval_steps_per_second": 1.538, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1195729537366548, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12811387900355872, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12811387900355872, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0709, | |
| "eval_samples_per_second": 12.315, | |
| "eval_steps_per_second": 1.539, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13665480427046264, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1423487544483986, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.0816, | |
| "eval_samples_per_second": 12.312, | |
| "eval_steps_per_second": 1.539, | |
| "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": 8.886804283392e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |