| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020930354246245617, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020930354246245618, | |
| "grad_norm": 1.8069729804992676, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020930354246245618, | |
| "eval_loss": 2.6074929237365723, | |
| "eval_runtime": 75.0099, | |
| "eval_samples_per_second": 26.823, | |
| "eval_steps_per_second": 13.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041860708492491236, | |
| "grad_norm": 1.9798526763916016, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5943, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006279106273873685, | |
| "grad_norm": 1.9045490026474, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5511, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006279106273873685, | |
| "eval_loss": 2.589160442352295, | |
| "eval_runtime": 74.8734, | |
| "eval_samples_per_second": 26.872, | |
| "eval_steps_per_second": 13.436, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008372141698498247, | |
| "grad_norm": 1.8883458375930786, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6434, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010465177123122808, | |
| "grad_norm": 1.859239935874939, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001255821254774737, | |
| "grad_norm": 1.732227087020874, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4172, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001255821254774737, | |
| "eval_loss": 2.3991305828094482, | |
| "eval_runtime": 74.9832, | |
| "eval_samples_per_second": 26.833, | |
| "eval_steps_per_second": 13.416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014651247972371933, | |
| "grad_norm": 1.3966670036315918, | |
| "learning_rate": 0.00014, | |
| "loss": 2.318, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016744283396996494, | |
| "grad_norm": 1.2437927722930908, | |
| "learning_rate": 0.00016, | |
| "loss": 2.2546, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018837318821621056, | |
| "grad_norm": 1.1125547885894775, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4425, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018837318821621056, | |
| "eval_loss": 2.2520806789398193, | |
| "eval_runtime": 74.9585, | |
| "eval_samples_per_second": 26.842, | |
| "eval_steps_per_second": 13.421, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020930354246245617, | |
| "grad_norm": 1.0390887260437012, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2821, | |
| "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": 887672762007552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |