| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014116019564803116, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8232039129606233e-05, | |
| "eval_loss": 1.372756004333496, | |
| "eval_runtime": 1295.716, | |
| "eval_samples_per_second": 11.511, | |
| "eval_steps_per_second": 5.756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014116019564803118, | |
| "grad_norm": 9.01905632019043, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2824, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00028232039129606236, | |
| "grad_norm": 6.25973653793335, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00028232039129606236, | |
| "eval_loss": 1.1299453973770142, | |
| "eval_runtime": 1315.7538, | |
| "eval_samples_per_second": 11.336, | |
| "eval_steps_per_second": 5.668, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004234805869440935, | |
| "grad_norm": 6.059873104095459, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.3526, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005646407825921247, | |
| "grad_norm": 6.142041206359863, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005646407825921247, | |
| "eval_loss": 0.9743238091468811, | |
| "eval_runtime": 1313.8488, | |
| "eval_samples_per_second": 11.352, | |
| "eval_steps_per_second": 5.676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007058009782401558, | |
| "grad_norm": 6.113480567932129, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.1495, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000846961173888187, | |
| "grad_norm": 5.63142728805542, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000846961173888187, | |
| "eval_loss": 0.9139702916145325, | |
| "eval_runtime": 1315.7943, | |
| "eval_samples_per_second": 11.335, | |
| "eval_steps_per_second": 5.668, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009881213695362183, | |
| "grad_norm": 5.424609184265137, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.5494, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0011292815651842494, | |
| "grad_norm": 5.923633098602295, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011292815651842494, | |
| "eval_loss": 0.8934321403503418, | |
| "eval_runtime": 1315.4296, | |
| "eval_samples_per_second": 11.339, | |
| "eval_steps_per_second": 5.67, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012704417608322806, | |
| "grad_norm": 6.608625411987305, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.7016, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0014116019564803116, | |
| "grad_norm": 5.440760135650635, | |
| "learning_rate": 0.0, | |
| "loss": 3.3832, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014116019564803116, | |
| "eval_loss": 0.8904063701629639, | |
| "eval_runtime": 1315.2003, | |
| "eval_samples_per_second": 11.34, | |
| "eval_steps_per_second": 5.671, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |