| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.191996594295445, | |
| "eval_steps": 2800, | |
| "global_step": 14000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23839931885908897, | |
| "grad_norm": 9.698241233825684, | |
| "learning_rate": 1.2004287245444802e-05, | |
| "loss": 1.746, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.23839931885908897, | |
| "eval_loss": 1.6161515712738037, | |
| "eval_runtime": 2098.002, | |
| "eval_samples_per_second": 1.4, | |
| "eval_steps_per_second": 0.175, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.47679863771817793, | |
| "grad_norm": 6.200751781463623, | |
| "learning_rate": 9.003215434083602e-06, | |
| "loss": 1.5909, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.47679863771817793, | |
| "eval_loss": 1.5394023656845093, | |
| "eval_runtime": 2068.134, | |
| "eval_samples_per_second": 1.42, | |
| "eval_steps_per_second": 0.178, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.7151979565772669, | |
| "grad_norm": 8.85448169708252, | |
| "learning_rate": 6.002143622722401e-06, | |
| "loss": 1.4945, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.7151979565772669, | |
| "eval_loss": 1.4963045120239258, | |
| "eval_runtime": 2077.7916, | |
| "eval_samples_per_second": 1.414, | |
| "eval_steps_per_second": 0.177, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.9535972754363559, | |
| "grad_norm": 9.303555488586426, | |
| "learning_rate": 3.0010718113612005e-06, | |
| "loss": 1.4832, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.9535972754363559, | |
| "eval_loss": 1.4696238040924072, | |
| "eval_runtime": 2075.1801, | |
| "eval_samples_per_second": 1.415, | |
| "eval_steps_per_second": 0.177, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.191996594295445, | |
| "grad_norm": 9.281532287597656, | |
| "learning_rate": 0.0, | |
| "loss": 1.4425, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.191996594295445, | |
| "eval_loss": 1.4569294452667236, | |
| "eval_runtime": 2302.3378, | |
| "eval_samples_per_second": 1.276, | |
| "eval_steps_per_second": 0.16, | |
| "step": 14000 | |
| } | |
| ], | |
| "logging_steps": 2800, | |
| "max_steps": 14000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 2800, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.69679748808704e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |