| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002789166875854182, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "grad_norm": 2.08347749710083, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2128, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "eval_loss": 1.3509711027145386, | |
| "eval_runtime": 366.0617, | |
| "eval_samples_per_second": 41.242, | |
| "eval_steps_per_second": 20.622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.578333751708365e-05, | |
| "grad_norm": 2.326923370361328, | |
| "learning_rate": 4e-05, | |
| "loss": 5.7631, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.367500627562547e-05, | |
| "grad_norm": 2.4791812896728516, | |
| "learning_rate": 6e-05, | |
| "loss": 5.6827, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.367500627562547e-05, | |
| "eval_loss": 1.3463988304138184, | |
| "eval_runtime": 335.5169, | |
| "eval_samples_per_second": 44.996, | |
| "eval_steps_per_second": 22.5, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "grad_norm": 2.8579959869384766, | |
| "learning_rate": 8e-05, | |
| "loss": 6.107, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001394583437927091, | |
| "grad_norm": 2.5855050086975098, | |
| "learning_rate": 0.0001, | |
| "loss": 5.7515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016735001255125095, | |
| "grad_norm": 2.8977739810943604, | |
| "learning_rate": 0.00012, | |
| "loss": 6.4357, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016735001255125095, | |
| "eval_loss": 1.313152551651001, | |
| "eval_runtime": 302.6126, | |
| "eval_samples_per_second": 49.889, | |
| "eval_steps_per_second": 24.946, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019524168130979276, | |
| "grad_norm": 2.1591832637786865, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7041, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "grad_norm": 2.9507343769073486, | |
| "learning_rate": 0.00016, | |
| "loss": 6.1911, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002510250188268764, | |
| "grad_norm": 3.269846200942993, | |
| "learning_rate": 0.00018, | |
| "loss": 5.7977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002510250188268764, | |
| "eval_loss": 1.2447813749313354, | |
| "eval_runtime": 257.3929, | |
| "eval_samples_per_second": 58.654, | |
| "eval_steps_per_second": 29.329, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002789166875854182, | |
| "grad_norm": 2.935885429382324, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2923, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 567654720995328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |