| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001554001554001554, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "grad_norm": 2.461033582687378, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001554001554001554, | |
| "eval_loss": 5.979092121124268, | |
| "eval_runtime": 118.7787, | |
| "eval_samples_per_second": 22.816, | |
| "eval_steps_per_second": 11.408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003108003108003108, | |
| "grad_norm": 1.8061084747314453, | |
| "learning_rate": 4e-05, | |
| "loss": 4.2089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "grad_norm": 2.806514024734497, | |
| "learning_rate": 6e-05, | |
| "loss": 5.928, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004662004662004662, | |
| "eval_loss": 5.9718146324157715, | |
| "eval_runtime": 117.4419, | |
| "eval_samples_per_second": 23.075, | |
| "eval_steps_per_second": 11.538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006216006216006216, | |
| "grad_norm": 2.470583200454712, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3336, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000777000777000777, | |
| "grad_norm": 1.9067507982254028, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3592, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "grad_norm": 3.4067890644073486, | |
| "learning_rate": 0.00012, | |
| "loss": 5.8512, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009324009324009324, | |
| "eval_loss": 5.809554576873779, | |
| "eval_runtime": 117.4521, | |
| "eval_samples_per_second": 23.073, | |
| "eval_steps_per_second": 11.537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010878010878010878, | |
| "grad_norm": 2.6836624145507812, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7178, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012432012432012432, | |
| "grad_norm": 3.25949764251709, | |
| "learning_rate": 0.00016, | |
| "loss": 5.602, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "grad_norm": 3.4510438442230225, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "eval_loss": 5.102389335632324, | |
| "eval_runtime": 117.4294, | |
| "eval_samples_per_second": 23.078, | |
| "eval_steps_per_second": 11.539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001554001554001554, | |
| "grad_norm": 3.6632792949676514, | |
| "learning_rate": 0.0002, | |
| "loss": 4.7611, | |
| "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": 2728107266015232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |