| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004309137526124146, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.618275052248293e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 246.5636, | |
| "eval_samples_per_second": 19.816, | |
| "eval_steps_per_second": 9.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004309137526124146, | |
| "grad_norm": 1.3349863290786743, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5952, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008618275052248292, | |
| "grad_norm": 0.6459352374076843, | |
| "learning_rate": 0.0001, | |
| "loss": 1.632, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008618275052248292, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.3987, | |
| "eval_samples_per_second": 19.75, | |
| "eval_steps_per_second": 9.875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012927412578372438, | |
| "grad_norm": 0.7828249335289001, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0017236550104496584, | |
| "grad_norm": 3.3571083545684814, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2702, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017236550104496584, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.5543, | |
| "eval_samples_per_second": 19.737, | |
| "eval_steps_per_second": 9.869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002154568763062073, | |
| "grad_norm": 2.058995008468628, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0782, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025854825156744875, | |
| "grad_norm": 5.677429676055908, | |
| "learning_rate": 5e-05, | |
| "loss": 0.795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025854825156744875, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.7294, | |
| "eval_samples_per_second": 19.723, | |
| "eval_steps_per_second": 9.862, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0030163962682869024, | |
| "grad_norm": 2.328920841217041, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.075, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003447310020899317, | |
| "grad_norm": 2.688364267349243, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8601, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003447310020899317, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.6701, | |
| "eval_samples_per_second": 19.728, | |
| "eval_steps_per_second": 9.864, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0038782237735117317, | |
| "grad_norm": 1.784724235534668, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8389, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004309137526124146, | |
| "grad_norm": 1.6380950212478638, | |
| "learning_rate": 0.0, | |
| "loss": 0.6914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004309137526124146, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.0152, | |
| "eval_samples_per_second": 19.78, | |
| "eval_steps_per_second": 9.89, | |
| "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": 5965854037770240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |