| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008437928488556059, | |
| "eval_steps": 1, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "grad_norm": 0.03186611086130142, | |
| "learning_rate": 2e-05, | |
| "loss": 10.378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": 10.378701210021973, | |
| "eval_runtime": 40.1148, | |
| "eval_samples_per_second": 124.393, | |
| "eval_steps_per_second": 62.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016875856977112118, | |
| "grad_norm": 0.02888074889779091, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3767, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016875856977112118, | |
| "eval_loss": 10.37869930267334, | |
| "eval_runtime": 39.9483, | |
| "eval_samples_per_second": 124.911, | |
| "eval_steps_per_second": 62.456, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002531378546566818, | |
| "grad_norm": 0.03415323421359062, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3818, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002531378546566818, | |
| "eval_loss": 10.378689765930176, | |
| "eval_runtime": 39.9436, | |
| "eval_samples_per_second": 124.926, | |
| "eval_steps_per_second": 62.463, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "grad_norm": 0.03634943813085556, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3757, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "eval_loss": 10.37867259979248, | |
| "eval_runtime": 39.9646, | |
| "eval_samples_per_second": 124.861, | |
| "eval_steps_per_second": 62.43, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "grad_norm": 0.03636252507567406, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "eval_loss": 10.37865161895752, | |
| "eval_runtime": 39.9036, | |
| "eval_samples_per_second": 125.051, | |
| "eval_steps_per_second": 62.526, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005062757093133636, | |
| "grad_norm": 0.033302322030067444, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3826, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005062757093133636, | |
| "eval_loss": 10.378623962402344, | |
| "eval_runtime": 39.9143, | |
| "eval_samples_per_second": 125.018, | |
| "eval_steps_per_second": 62.509, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005906549941989242, | |
| "grad_norm": 0.03907749429345131, | |
| "learning_rate": 0.00014, | |
| "loss": 10.383, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005906549941989242, | |
| "eval_loss": 10.378588676452637, | |
| "eval_runtime": 39.9499, | |
| "eval_samples_per_second": 124.907, | |
| "eval_steps_per_second": 62.453, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "grad_norm": 0.027698226273059845, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3717, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "eval_loss": 10.378549575805664, | |
| "eval_runtime": 39.8993, | |
| "eval_samples_per_second": 125.065, | |
| "eval_steps_per_second": 62.532, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007594135639700454, | |
| "grad_norm": 0.0266389362514019, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007594135639700454, | |
| "eval_loss": 10.37850284576416, | |
| "eval_runtime": 39.9499, | |
| "eval_samples_per_second": 124.906, | |
| "eval_steps_per_second": 62.453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": 0.030299000442028046, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "eval_loss": 10.37845230102539, | |
| "eval_runtime": 39.9165, | |
| "eval_samples_per_second": 125.011, | |
| "eval_steps_per_second": 62.505, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 517236326400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |