| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024524831391784182, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002452483139178418, | |
| "grad_norm": 1.1516366004943848, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002452483139178418, | |
| "eval_loss": 1.8329464197158813, | |
| "eval_runtime": 10.3497, | |
| "eval_samples_per_second": 16.619, | |
| "eval_steps_per_second": 8.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004904966278356836, | |
| "grad_norm": 1.176713466644287, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0191, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007357449417535254, | |
| "grad_norm": 1.104511022567749, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007357449417535254, | |
| "eval_loss": 1.829694390296936, | |
| "eval_runtime": 9.3504, | |
| "eval_samples_per_second": 18.395, | |
| "eval_steps_per_second": 9.197, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009809932556713672, | |
| "grad_norm": 0.9908570051193237, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9534, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012262415695892091, | |
| "grad_norm": 1.0199905633926392, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6022, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014714898835070508, | |
| "grad_norm": 1.086060881614685, | |
| "learning_rate": 0.00012, | |
| "loss": 1.554, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014714898835070508, | |
| "eval_loss": 1.8062726259231567, | |
| "eval_runtime": 9.3622, | |
| "eval_samples_per_second": 18.372, | |
| "eval_steps_per_second": 9.186, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017167381974248927, | |
| "grad_norm": 1.1592398881912231, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8487, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019619865113427344, | |
| "grad_norm": 1.2560908794403076, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9289, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022072348252605765, | |
| "grad_norm": 1.6090513467788696, | |
| "learning_rate": 0.00018, | |
| "loss": 1.802, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022072348252605765, | |
| "eval_loss": 1.684467077255249, | |
| "eval_runtime": 9.365, | |
| "eval_samples_per_second": 18.366, | |
| "eval_steps_per_second": 9.183, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024524831391784182, | |
| "grad_norm": 1.31636381149292, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5509, | |
| "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": 3135311286632448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |