| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018978333069745373, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006326111023248458, | |
| "eval_loss": 1.2244539260864258, | |
| "eval_runtime": 92.2209, | |
| "eval_samples_per_second": 7.222, | |
| "eval_steps_per_second": 3.611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018978333069745374, | |
| "grad_norm": 1.715061902999878, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8581, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003795666613949075, | |
| "grad_norm": 1.479522943496704, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005060888818598766, | |
| "eval_loss": 1.0666815042495728, | |
| "eval_runtime": 93.2572, | |
| "eval_samples_per_second": 7.142, | |
| "eval_steps_per_second": 3.571, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005693499920923612, | |
| "grad_norm": 1.4427181482315063, | |
| "learning_rate": 0.00018, | |
| "loss": 4.3806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00759133322789815, | |
| "grad_norm": 1.8158526420593262, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 4.0533, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009489166534872686, | |
| "grad_norm": 1.1403063535690308, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.7933, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010121777637197533, | |
| "eval_loss": 0.8931291103363037, | |
| "eval_runtime": 93.3125, | |
| "eval_samples_per_second": 7.137, | |
| "eval_steps_per_second": 3.569, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011386999841847224, | |
| "grad_norm": 1.1006195545196533, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.5634, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013284833148821762, | |
| "grad_norm": 1.0892219543457031, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.4429, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0151826664557963, | |
| "grad_norm": 1.1754521131515503, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.3734, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0151826664557963, | |
| "eval_loss": 0.8254575729370117, | |
| "eval_runtime": 93.299, | |
| "eval_samples_per_second": 7.138, | |
| "eval_steps_per_second": 3.569, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017080499762770835, | |
| "grad_norm": 1.0063222646713257, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.3129, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018978333069745373, | |
| "grad_norm": 1.0062178373336792, | |
| "learning_rate": 0.0, | |
| "loss": 3.2526, | |
| "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": 1.960374605709312e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |