| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10427528675703858, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020855057351407717, | |
| "eval_loss": 2.006255865097046, | |
| "eval_runtime": 11.3423, | |
| "eval_samples_per_second": 17.809, | |
| "eval_steps_per_second": 8.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010427528675703858, | |
| "grad_norm": 0.7133792042732239, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020855057351407715, | |
| "grad_norm": 0.760151743888855, | |
| "learning_rate": 0.0001, | |
| "loss": 1.696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020855057351407715, | |
| "eval_loss": 1.9778136014938354, | |
| "eval_runtime": 11.2809, | |
| "eval_samples_per_second": 17.906, | |
| "eval_steps_per_second": 8.953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03128258602711158, | |
| "grad_norm": 0.90077143907547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0586, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04171011470281543, | |
| "grad_norm": 0.7349458336830139, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.938, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04171011470281543, | |
| "eval_loss": 1.9062426090240479, | |
| "eval_runtime": 11.3111, | |
| "eval_samples_per_second": 17.859, | |
| "eval_steps_per_second": 8.929, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05213764337851929, | |
| "grad_norm": 1.0582647323608398, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06256517205422316, | |
| "grad_norm": 0.9831803441047668, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06256517205422316, | |
| "eval_loss": 1.8727952241897583, | |
| "eval_runtime": 11.3697, | |
| "eval_samples_per_second": 17.766, | |
| "eval_steps_per_second": 8.883, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.890938937664032, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9681, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08342022940563086, | |
| "grad_norm": 1.0751326084136963, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8917, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08342022940563086, | |
| "eval_loss": 1.8614988327026367, | |
| "eval_runtime": 11.3927, | |
| "eval_samples_per_second": 17.731, | |
| "eval_steps_per_second": 8.865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09384775808133472, | |
| "grad_norm": 1.260564923286438, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6922, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10427528675703858, | |
| "grad_norm": 0.9989824295043945, | |
| "learning_rate": 0.0, | |
| "loss": 1.8681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10427528675703858, | |
| "eval_loss": 1.8599786758422852, | |
| "eval_runtime": 11.3163, | |
| "eval_samples_per_second": 17.85, | |
| "eval_steps_per_second": 8.925, | |
| "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": 2800545051967488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |