| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029473746260518445, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.8947492521036884e-05, | |
| "eval_loss": 4.235436916351318, | |
| "eval_runtime": 456.8159, | |
| "eval_samples_per_second": 15.636, | |
| "eval_steps_per_second": 7.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029473746260518446, | |
| "grad_norm": 127.63593292236328, | |
| "learning_rate": 5e-05, | |
| "loss": 14.4377, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005894749252103689, | |
| "grad_norm": 87.82167053222656, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6617, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005894749252103689, | |
| "eval_loss": 1.4089908599853516, | |
| "eval_runtime": 457.5771, | |
| "eval_samples_per_second": 15.61, | |
| "eval_steps_per_second": 7.806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008842123878155533, | |
| "grad_norm": 102.32630920410156, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2139, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011789498504207378, | |
| "grad_norm": 47.46616744995117, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011789498504207378, | |
| "eval_loss": 0.29977118968963623, | |
| "eval_runtime": 457.6273, | |
| "eval_samples_per_second": 15.609, | |
| "eval_steps_per_second": 7.805, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014736873130259222, | |
| "grad_norm": 52.976806640625, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.754, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017684247756311066, | |
| "grad_norm": 12.571455955505371, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017684247756311066, | |
| "eval_loss": 0.15256403386592865, | |
| "eval_runtime": 458.4039, | |
| "eval_samples_per_second": 15.582, | |
| "eval_steps_per_second": 7.792, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002063162238236291, | |
| "grad_norm": 10.54803466796875, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3606, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0023578997008414757, | |
| "grad_norm": 1.0242526531219482, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023578997008414757, | |
| "eval_loss": 0.014833731576800346, | |
| "eval_runtime": 458.2308, | |
| "eval_samples_per_second": 15.588, | |
| "eval_steps_per_second": 7.795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00265263716344666, | |
| "grad_norm": 1.501258373260498, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0159, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0029473746260518445, | |
| "grad_norm": 3.8253798484802246, | |
| "learning_rate": 0.0, | |
| "loss": 0.0492, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029473746260518445, | |
| "eval_loss": 0.009184408001601696, | |
| "eval_runtime": 458.1086, | |
| "eval_samples_per_second": 15.592, | |
| "eval_steps_per_second": 7.797, | |
| "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": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |