| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033983744442241796, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011327914814080598, | |
| "eval_loss": 10.376569747924805, | |
| "eval_runtime": 21.9746, | |
| "eval_samples_per_second": 169.15, | |
| "eval_steps_per_second": 84.598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003398374444224179, | |
| "grad_norm": 0.042266711592674255, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3737, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006796748888448359, | |
| "grad_norm": 0.057990022003650665, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.3771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009062331851264478, | |
| "eval_loss": 10.375176429748535, | |
| "eval_runtime": 22.0391, | |
| "eval_samples_per_second": 168.655, | |
| "eval_steps_per_second": 84.35, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010195123332672538, | |
| "grad_norm": 0.048735857009887695, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3756, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013593497776896717, | |
| "grad_norm": 0.04772263020277023, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.3747, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0016991872221120898, | |
| "grad_norm": 0.05866085737943649, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3747, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018124663702528956, | |
| "eval_loss": 10.373068809509277, | |
| "eval_runtime": 22.1328, | |
| "eval_samples_per_second": 167.941, | |
| "eval_steps_per_second": 83.993, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0020390246665345077, | |
| "grad_norm": 0.05547315254807472, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.3714, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0023788621109569258, | |
| "grad_norm": 0.07062539458274841, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 10.3731, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0027186995553793434, | |
| "grad_norm": 0.07306697219610214, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.3711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0027186995553793434, | |
| "eval_loss": 10.371893882751465, | |
| "eval_runtime": 22.0107, | |
| "eval_samples_per_second": 168.872, | |
| "eval_steps_per_second": 84.459, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0030585369998017615, | |
| "grad_norm": 0.06676942855119705, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 10.3717, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0033983744442241796, | |
| "grad_norm": 0.07616107165813446, | |
| "learning_rate": 0.0, | |
| "loss": 10.3713, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 849914757120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |