| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.16501650165016502, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0033003300330033004, |
| "eval_loss": 0.7488853931427002, |
| "eval_runtime": 19.7022, |
| "eval_samples_per_second": 6.497, |
| "eval_steps_per_second": 3.248, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0165016501650165, |
| "grad_norm": 3.9368174076080322, |
| "learning_rate": 5e-05, |
| "loss": 2.8219, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.033003300330033, |
| "grad_norm": 4.35306978225708, |
| "learning_rate": 0.0001, |
| "loss": 2.5563, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.033003300330033, |
| "eval_loss": 0.6635968089103699, |
| "eval_runtime": 19.9265, |
| "eval_samples_per_second": 6.424, |
| "eval_steps_per_second": 3.212, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04950495049504951, |
| "grad_norm": 3.046280860900879, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.2334, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.066006600660066, |
| "grad_norm": 2.661982536315918, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.3494, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.066006600660066, |
| "eval_loss": 0.6079679131507874, |
| "eval_runtime": 20.0073, |
| "eval_samples_per_second": 6.398, |
| "eval_steps_per_second": 3.199, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08250825082508251, |
| "grad_norm": 3.2515509128570557, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 2.2636, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.09900990099009901, |
| "grad_norm": 2.502488136291504, |
| "learning_rate": 5e-05, |
| "loss": 2.3351, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09900990099009901, |
| "eval_loss": 0.5951216220855713, |
| "eval_runtime": 20.0481, |
| "eval_samples_per_second": 6.385, |
| "eval_steps_per_second": 3.192, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11551155115511551, |
| "grad_norm": 2.753608465194702, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 2.3589, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.132013201320132, |
| "grad_norm": 2.7407712936401367, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 2.3514, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.132013201320132, |
| "eval_loss": 0.5916140079498291, |
| "eval_runtime": 20.0668, |
| "eval_samples_per_second": 6.379, |
| "eval_steps_per_second": 3.189, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1485148514851485, |
| "grad_norm": 2.506066083908081, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 2.2329, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.16501650165016502, |
| "grad_norm": 2.6105473041534424, |
| "learning_rate": 0.0, |
| "loss": 2.2213, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16501650165016502, |
| "eval_loss": 0.590599775314331, |
| "eval_runtime": 20.062, |
| "eval_samples_per_second": 6.38, |
| "eval_steps_per_second": 3.19, |
| "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": 1.75266978594816e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
