| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008509733007126901, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.509733007126901e-05, | |
| "grad_norm": 1.3362045288085938, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.509733007126901e-05, | |
| "eval_loss": 2.56070876121521, | |
| "eval_runtime": 244.3553, | |
| "eval_samples_per_second": 20.249, | |
| "eval_steps_per_second": 10.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017019466014253802, | |
| "grad_norm": 1.5068103075027466, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3577, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025529199021380705, | |
| "grad_norm": 1.5330816507339478, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5584, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025529199021380705, | |
| "eval_loss": 2.552053451538086, | |
| "eval_runtime": 243.6642, | |
| "eval_samples_per_second": 20.307, | |
| "eval_steps_per_second": 10.153, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034038932028507605, | |
| "grad_norm": 1.5739260911941528, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3949, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042548665035634504, | |
| "grad_norm": 0.9977084994316101, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005105839804276141, | |
| "grad_norm": 1.1806941032409668, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005105839804276141, | |
| "eval_loss": 2.410656690597534, | |
| "eval_runtime": 243.5297, | |
| "eval_samples_per_second": 20.318, | |
| "eval_steps_per_second": 10.159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005956813104988831, | |
| "grad_norm": 2.028729200363159, | |
| "learning_rate": 0.00014, | |
| "loss": 2.396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006807786405701521, | |
| "grad_norm": 1.9360212087631226, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1667, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007658759706414211, | |
| "grad_norm": 1.4998698234558105, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9319, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007658759706414211, | |
| "eval_loss": 1.819492220878601, | |
| "eval_runtime": 243.5183, | |
| "eval_samples_per_second": 20.319, | |
| "eval_steps_per_second": 10.159, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008509733007126901, | |
| "grad_norm": 1.642189383506775, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0084, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3166205430988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |