| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011949810794662417, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039832702648874725, | |
| "eval_loss": 5.335007190704346, | |
| "eval_runtime": 16.5498, | |
| "eval_samples_per_second": 63.928, | |
| "eval_steps_per_second": 31.964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011949810794662419, | |
| "grad_norm": 9.828206062316895, | |
| "learning_rate": 4e-05, | |
| "loss": 21.5404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019916351324437364, | |
| "eval_loss": 5.222269058227539, | |
| "eval_runtime": 15.9043, | |
| "eval_samples_per_second": 66.523, | |
| "eval_steps_per_second": 33.261, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023899621589324837, | |
| "grad_norm": 10.285325050354004, | |
| "learning_rate": 8e-05, | |
| "loss": 21.2409, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035849432383987254, | |
| "grad_norm": 8.375535011291504, | |
| "learning_rate": 0.00012, | |
| "loss": 20.3485, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003983270264887473, | |
| "eval_loss": 4.795277118682861, | |
| "eval_runtime": 15.8771, | |
| "eval_samples_per_second": 66.637, | |
| "eval_steps_per_second": 33.318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0047799243178649675, | |
| "grad_norm": 8.881246566772461, | |
| "learning_rate": 0.00016, | |
| "loss": 19.7061, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005974905397331209, | |
| "grad_norm": 8.536454200744629, | |
| "learning_rate": 0.0002, | |
| "loss": 18.2456, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005974905397331209, | |
| "eval_loss": 4.413322448730469, | |
| "eval_runtime": 15.8995, | |
| "eval_samples_per_second": 66.543, | |
| "eval_steps_per_second": 33.272, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007169886476797451, | |
| "grad_norm": 9.679789543151855, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 17.8988, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007966540529774946, | |
| "eval_loss": 4.2372236251831055, | |
| "eval_runtime": 15.9685, | |
| "eval_samples_per_second": 66.255, | |
| "eval_steps_per_second": 33.128, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008364867556263693, | |
| "grad_norm": 9.835699081420898, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 17.8623, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009559848635729935, | |
| "grad_norm": 9.328329086303711, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 17.2585, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009958175662218682, | |
| "eval_loss": 4.13242769241333, | |
| "eval_runtime": 15.958, | |
| "eval_samples_per_second": 66.299, | |
| "eval_steps_per_second": 33.15, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010754829715196175, | |
| "grad_norm": 8.610879898071289, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 16.9122, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011949810794662417, | |
| "grad_norm": 8.168183326721191, | |
| "learning_rate": 0.0, | |
| "loss": 16.8184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011949810794662417, | |
| "eval_loss": 4.110958099365234, | |
| "eval_runtime": 15.9047, | |
| "eval_samples_per_second": 66.521, | |
| "eval_steps_per_second": 33.261, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 457828749803520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |