| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1996007984031936, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003992015968063872, | |
| "eval_loss": 2.9855740070343018, | |
| "eval_runtime": 4.6864, | |
| "eval_samples_per_second": 22.618, | |
| "eval_steps_per_second": 11.309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01996007984031936, | |
| "grad_norm": 0.9795141816139221, | |
| "learning_rate": 5e-05, | |
| "loss": 2.823, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03992015968063872, | |
| "grad_norm": 1.2677401304244995, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03992015968063872, | |
| "eval_loss": 2.8597536087036133, | |
| "eval_runtime": 4.1263, | |
| "eval_samples_per_second": 25.689, | |
| "eval_steps_per_second": 12.844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.059880239520958084, | |
| "grad_norm": 2.088879346847534, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6889, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07984031936127745, | |
| "grad_norm": 2.568920373916626, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2853, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07984031936127745, | |
| "eval_loss": 2.2561004161834717, | |
| "eval_runtime": 4.2095, | |
| "eval_samples_per_second": 25.181, | |
| "eval_steps_per_second": 12.591, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0998003992015968, | |
| "grad_norm": 3.2531826496124268, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0505, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 2.2862043380737305, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9431, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "eval_loss": 1.808345913887024, | |
| "eval_runtime": 4.2586, | |
| "eval_samples_per_second": 24.891, | |
| "eval_steps_per_second": 12.445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13972055888223553, | |
| "grad_norm": 2.9611470699310303, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.775, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1596806387225549, | |
| "grad_norm": 2.191890239715576, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1596806387225549, | |
| "eval_loss": 1.6713372468948364, | |
| "eval_runtime": 4.3592, | |
| "eval_samples_per_second": 24.316, | |
| "eval_steps_per_second": 12.158, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17964071856287425, | |
| "grad_norm": 1.7487860918045044, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6053, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1996007984031936, | |
| "grad_norm": 2.035626173019409, | |
| "learning_rate": 0.0, | |
| "loss": 1.565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1996007984031936, | |
| "eval_loss": 1.6555358171463013, | |
| "eval_runtime": 4.1456, | |
| "eval_samples_per_second": 25.569, | |
| "eval_steps_per_second": 12.785, | |
| "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": 1621491292569600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |