| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00121921482565228, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.064049418840933e-05, | |
| "eval_loss": 11.762539863586426, | |
| "eval_runtime": 48.8482, | |
| "eval_samples_per_second": 212.106, | |
| "eval_steps_per_second": 106.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000121921482565228, | |
| "grad_norm": 0.0339069738984108, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7631, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000243842965130456, | |
| "grad_norm": 0.041261523962020874, | |
| "learning_rate": 0.00012, | |
| "loss": 11.7618, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "eval_loss": 11.761956214904785, | |
| "eval_runtime": 49.0627, | |
| "eval_samples_per_second": 211.179, | |
| "eval_steps_per_second": 105.6, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000365764447695684, | |
| "grad_norm": 0.03510475158691406, | |
| "learning_rate": 0.00018, | |
| "loss": 11.7622, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.046722933650016785, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.7637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00060960741282614, | |
| "grad_norm": 0.04540090635418892, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 11.7614, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "eval_loss": 11.760395050048828, | |
| "eval_runtime": 49.1458, | |
| "eval_samples_per_second": 210.822, | |
| "eval_steps_per_second": 105.421, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000731528895391368, | |
| "grad_norm": 0.0367448627948761, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.7622, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000853450377956596, | |
| "grad_norm": 0.04216024652123451, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 11.7596, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 0.04545463249087334, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 11.7596, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "eval_loss": 11.75940227508545, | |
| "eval_runtime": 49.2388, | |
| "eval_samples_per_second": 210.424, | |
| "eval_steps_per_second": 105.222, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010972933430870519, | |
| "grad_norm": 0.04417893663048744, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 11.7591, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00121921482565228, | |
| "grad_norm": 0.046904273331165314, | |
| "learning_rate": 0.0, | |
| "loss": 11.7603, | |
| "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": 3055500656640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |