| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004602991944764097, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046029919447640965, | |
| "grad_norm": 0.6887022852897644, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00046029919447640965, | |
| "eval_loss": 11.924036979675293, | |
| "eval_runtime": 63.2544, | |
| "eval_samples_per_second": 14.465, | |
| "eval_steps_per_second": 7.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009205983889528193, | |
| "grad_norm": 0.6521114706993103, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001380897583429229, | |
| "grad_norm": 0.5372654795646667, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001380897583429229, | |
| "eval_loss": 11.923266410827637, | |
| "eval_runtime": 62.2177, | |
| "eval_samples_per_second": 14.706, | |
| "eval_steps_per_second": 7.361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018411967779056386, | |
| "grad_norm": 0.7256842255592346, | |
| "learning_rate": 8e-05, | |
| "loss": 11.911, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023014959723820483, | |
| "grad_norm": 0.5256912112236023, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9209, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002761795166858458, | |
| "grad_norm": 0.6058363318443298, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9211, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002761795166858458, | |
| "eval_loss": 11.920125007629395, | |
| "eval_runtime": 62.2091, | |
| "eval_samples_per_second": 14.708, | |
| "eval_steps_per_second": 7.362, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003222094361334868, | |
| "grad_norm": 0.5202929377555847, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9359, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003682393555811277, | |
| "grad_norm": 0.5931057929992676, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004142692750287687, | |
| "grad_norm": 0.615904688835144, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9165, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004142692750287687, | |
| "eval_loss": 11.914743423461914, | |
| "eval_runtime": 62.3061, | |
| "eval_samples_per_second": 14.686, | |
| "eval_steps_per_second": 7.351, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004602991944764097, | |
| "grad_norm": 0.7456185221672058, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9042, | |
| "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": 10156108677120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |