| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04441154700222058, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014803849000740192, | |
| "eval_loss": 10.374429702758789, | |
| "eval_runtime": 2.6683, | |
| "eval_samples_per_second": 106.808, | |
| "eval_steps_per_second": 53.591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0044411547002220575, | |
| "grad_norm": 0.03707285597920418, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3739, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008882309400444115, | |
| "grad_norm": 0.036970049142837524, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3758, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011843079200592153, | |
| "eval_loss": 10.373944282531738, | |
| "eval_runtime": 2.6669, | |
| "eval_samples_per_second": 106.868, | |
| "eval_steps_per_second": 53.621, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013323464100666173, | |
| "grad_norm": 0.03798874840140343, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01776461880088823, | |
| "grad_norm": 0.03467576950788498, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3733, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02220577350111029, | |
| "grad_norm": 0.04072782024741173, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3737, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023686158401184307, | |
| "eval_loss": 10.372544288635254, | |
| "eval_runtime": 2.6949, | |
| "eval_samples_per_second": 105.757, | |
| "eval_steps_per_second": 53.064, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026646928201332347, | |
| "grad_norm": 0.03554646670818329, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3728, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 0.05102809518575668, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3723, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03552923760177646, | |
| "grad_norm": 0.038376905024051666, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3709, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03552923760177646, | |
| "eval_loss": 10.371623039245605, | |
| "eval_runtime": 2.7014, | |
| "eval_samples_per_second": 105.5, | |
| "eval_steps_per_second": 52.935, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03997039230199852, | |
| "grad_norm": 0.03772800788283348, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3713, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04441154700222058, | |
| "grad_norm": 0.0479939766228199, | |
| "learning_rate": 0.0, | |
| "loss": 10.3705, | |
| "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": 1562535591936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |