| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07215874924834637, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024052916416115455, | |
| "eval_loss": 2.8067831993103027, | |
| "eval_runtime": 3.6543, | |
| "eval_samples_per_second": 47.889, | |
| "eval_steps_per_second": 24.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0072158749248346366, | |
| "grad_norm": 0.44602859020233154, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014431749849669273, | |
| "grad_norm": 0.6594803333282471, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019242333132892364, | |
| "eval_loss": 2.7753758430480957, | |
| "eval_runtime": 2.4839, | |
| "eval_samples_per_second": 70.453, | |
| "eval_steps_per_second": 35.428, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02164762477450391, | |
| "grad_norm": 0.4808473289012909, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.028863499699338546, | |
| "grad_norm": 0.5767693519592285, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.8209, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03607937462417318, | |
| "grad_norm": 1.131788969039917, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.978, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03848466626578473, | |
| "eval_loss": 2.703683614730835, | |
| "eval_runtime": 2.6207, | |
| "eval_samples_per_second": 66.776, | |
| "eval_steps_per_second": 33.579, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04329524954900782, | |
| "grad_norm": 0.47926196455955505, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.8346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.050511124473842456, | |
| "grad_norm": 0.4692942500114441, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.7138, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05772699939867709, | |
| "grad_norm": 0.41733187437057495, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.8068, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05772699939867709, | |
| "eval_loss": 2.67342209815979, | |
| "eval_runtime": 2.7373, | |
| "eval_samples_per_second": 63.931, | |
| "eval_steps_per_second": 32.148, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06494287432351173, | |
| "grad_norm": 0.6234534382820129, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.0337, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07215874924834637, | |
| "grad_norm": 1.1161253452301025, | |
| "learning_rate": 0.0, | |
| "loss": 2.9483, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 208256379125760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |