| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.025380710659898477, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025380710659898475, | |
| "grad_norm": 7.696322917938232, | |
| "learning_rate": 2e-05, | |
| "loss": 8.0605, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025380710659898475, | |
| "eval_loss": 5.894983291625977, | |
| "eval_runtime": 12.5783, | |
| "eval_samples_per_second": 13.197, | |
| "eval_steps_per_second": 6.599, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005076142131979695, | |
| "grad_norm": 3.208069324493408, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8856, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007614213197969543, | |
| "grad_norm": 2.330354690551758, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0228, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007614213197969543, | |
| "eval_loss": 5.871275901794434, | |
| "eval_runtime": 11.6385, | |
| "eval_samples_per_second": 14.263, | |
| "eval_steps_per_second": 7.132, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01015228426395939, | |
| "grad_norm": 2.8737056255340576, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9663, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012690355329949238, | |
| "grad_norm": 2.812922954559326, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5981, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015228426395939087, | |
| "grad_norm": 3.180525302886963, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5543, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015228426395939087, | |
| "eval_loss": 5.608060359954834, | |
| "eval_runtime": 11.8629, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 6.997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017766497461928935, | |
| "grad_norm": 2.6752285957336426, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8336, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02030456852791878, | |
| "grad_norm": 5.490387916564941, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0699, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02284263959390863, | |
| "grad_norm": 3.5671842098236084, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5838, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02284263959390863, | |
| "eval_loss": 5.221318244934082, | |
| "eval_runtime": 11.8016, | |
| "eval_samples_per_second": 14.066, | |
| "eval_steps_per_second": 7.033, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025380710659898477, | |
| "grad_norm": 3.9852616786956787, | |
| "learning_rate": 0.0002, | |
| "loss": 2.921, | |
| "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": 1988281566756864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |