| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00010532330304410677, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0532330304410676e-05, | |
| "grad_norm": 0.01830104924738407, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3812, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0532330304410676e-05, | |
| "eval_loss": 10.377663612365723, | |
| "eval_runtime": 122.1992, | |
| "eval_samples_per_second": 327.154, | |
| "eval_steps_per_second": 163.577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.1064660608821352e-05, | |
| "grad_norm": 0.02588691934943199, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3804, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.159699091323203e-05, | |
| "grad_norm": 0.024608928710222244, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3747, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.159699091323203e-05, | |
| "eval_loss": 10.377643585205078, | |
| "eval_runtime": 121.7883, | |
| "eval_samples_per_second": 328.258, | |
| "eval_steps_per_second": 164.129, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.2129321217642704e-05, | |
| "grad_norm": 0.023038163781166077, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3759, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.2661651522053385e-05, | |
| "grad_norm": 0.02481148950755596, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3778, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.319398182646406e-05, | |
| "grad_norm": 0.03077760897576809, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.319398182646406e-05, | |
| "eval_loss": 10.377541542053223, | |
| "eval_runtime": 124.0687, | |
| "eval_samples_per_second": 322.225, | |
| "eval_steps_per_second": 161.112, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.372631213087474e-05, | |
| "grad_norm": 0.0235343836247921, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3782, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.425864243528541e-05, | |
| "grad_norm": 0.02634567767381668, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3819, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.479097273969609e-05, | |
| "grad_norm": 0.021794479340314865, | |
| "learning_rate": 0.00018, | |
| "loss": 10.379, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 9.479097273969609e-05, | |
| "eval_loss": 10.377360343933105, | |
| "eval_runtime": 124.0443, | |
| "eval_samples_per_second": 322.288, | |
| "eval_steps_per_second": 161.144, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00010532330304410677, | |
| "grad_norm": 0.023253479972481728, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3774, | |
| "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": 168101806080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |