| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00301182139899104, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.02364279798208e-05, | |
| "eval_loss": 6.229126453399658, | |
| "eval_runtime": 686.8553, | |
| "eval_samples_per_second": 10.177, | |
| "eval_steps_per_second": 5.088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030118213989910396, | |
| "grad_norm": 68.98133850097656, | |
| "learning_rate": 5e-05, | |
| "loss": 24.7622, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "grad_norm": 47.577030181884766, | |
| "learning_rate": 0.0001, | |
| "loss": 17.8844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006023642797982079, | |
| "eval_loss": 2.717703342437744, | |
| "eval_runtime": 692.3214, | |
| "eval_samples_per_second": 10.096, | |
| "eval_steps_per_second": 5.048, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009035464196973119, | |
| "grad_norm": 334.9429626464844, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.4135, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "grad_norm": 31.033750534057617, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012047285595964158, | |
| "eval_loss": 0.6883819699287415, | |
| "eval_runtime": 693.124, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 5.042, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00150591069949552, | |
| "grad_norm": 22.133766174316406, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018070928393946238, | |
| "grad_norm": 38.62647247314453, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6636, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018070928393946238, | |
| "eval_loss": 0.3702947795391083, | |
| "eval_runtime": 693.0932, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 5.043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002108274979293728, | |
| "grad_norm": 20.019350051879883, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3196, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024094571191928317, | |
| "grad_norm": 25.286365509033203, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0024094571191928317, | |
| "eval_loss": 0.2982780337333679, | |
| "eval_runtime": 692.0766, | |
| "eval_samples_per_second": 10.1, | |
| "eval_steps_per_second": 5.05, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0027106392590919358, | |
| "grad_norm": 17.550260543823242, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2314, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00301182139899104, | |
| "grad_norm": 20.98444175720215, | |
| "learning_rate": 0.0, | |
| "loss": 1.1832, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00301182139899104, | |
| "eval_loss": 0.2857048511505127, | |
| "eval_runtime": 689.9907, | |
| "eval_samples_per_second": 10.131, | |
| "eval_steps_per_second": 5.065, | |
| "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": 1.445952573407232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |