| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00421896424427803, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437928488556059e-05, | |
| "eval_loss": 1.3113551139831543, | |
| "eval_runtime": 412.6536, | |
| "eval_samples_per_second": 12.092, | |
| "eval_steps_per_second": 6.046, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042189642442780296, | |
| "grad_norm": 26.7180233001709, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "grad_norm": 17.810115814208984, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0347, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008437928488556059, | |
| "eval_loss": 0.662794291973114, | |
| "eval_runtime": 415.9268, | |
| "eval_samples_per_second": 11.997, | |
| "eval_steps_per_second": 5.999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012656892732834089, | |
| "grad_norm": 18.003822326660156, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.691, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": 49.9283332824707, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "eval_loss": 0.10913728177547455, | |
| "eval_runtime": 414.3397, | |
| "eval_samples_per_second": 12.043, | |
| "eval_steps_per_second": 6.022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002109482122139015, | |
| "grad_norm": 16.146228790283203, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6352, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "grad_norm": 12.149748802185059, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2221, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025313785465668178, | |
| "eval_loss": 0.0454639196395874, | |
| "eval_runtime": 416.6408, | |
| "eval_samples_per_second": 11.977, | |
| "eval_steps_per_second": 5.988, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029532749709946207, | |
| "grad_norm": 9.316723823547363, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1035, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "grad_norm": 3.8980655670166016, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0706, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "eval_loss": 0.03316744044423103, | |
| "eval_runtime": 416.306, | |
| "eval_samples_per_second": 11.986, | |
| "eval_steps_per_second": 5.993, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037970678198502267, | |
| "grad_norm": 1.4486910104751587, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0732, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "grad_norm": 14.409627914428711, | |
| "learning_rate": 0.0, | |
| "loss": 0.1699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00421896424427803, | |
| "eval_loss": 0.03202228248119354, | |
| "eval_runtime": 413.9912, | |
| "eval_samples_per_second": 12.053, | |
| "eval_steps_per_second": 6.027, | |
| "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": 1.0910369417527296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |