| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07259528130671507, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "eval_loss": 2.4837050437927246, | |
| "eval_runtime": 34.809, | |
| "eval_samples_per_second": 8.331, | |
| "eval_steps_per_second": 4.166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007259528130671506, | |
| "grad_norm": 1.4090709686279297, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4528, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "grad_norm": 1.6987773180007935, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014519056261343012, | |
| "eval_loss": 2.2202208042144775, | |
| "eval_runtime": 35.1159, | |
| "eval_samples_per_second": 8.258, | |
| "eval_steps_per_second": 4.129, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021778584392014518, | |
| "grad_norm": 3.0617473125457764, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1563, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 2.7853174209594727, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9604, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "eval_loss": 1.92987859249115, | |
| "eval_runtime": 35.1927, | |
| "eval_samples_per_second": 8.24, | |
| "eval_steps_per_second": 4.12, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.036297640653357534, | |
| "grad_norm": 2.5411033630371094, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "grad_norm": 2.588447093963623, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8994, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.043557168784029036, | |
| "eval_loss": 1.8195312023162842, | |
| "eval_runtime": 35.2383, | |
| "eval_samples_per_second": 8.23, | |
| "eval_steps_per_second": 4.115, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.050816696914700546, | |
| "grad_norm": 2.859415054321289, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8508, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "grad_norm": 2.951900005340576, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05807622504537205, | |
| "eval_loss": 1.776922345161438, | |
| "eval_runtime": 35.2749, | |
| "eval_samples_per_second": 8.221, | |
| "eval_steps_per_second": 4.111, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06533575317604355, | |
| "grad_norm": 2.383507251739502, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7098, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 2.7600584030151367, | |
| "learning_rate": 0.0, | |
| "loss": 1.7854, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "eval_loss": 1.769264578819275, | |
| "eval_runtime": 35.2817, | |
| "eval_samples_per_second": 8.22, | |
| "eval_steps_per_second": 4.11, | |
| "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": 1.803325141942272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |