| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0935672514619883, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 84.49740600585938, | |
| "learning_rate": 1e-05, | |
| "loss": 197.3114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "eval_loss": 12.250398635864258, | |
| "eval_runtime": 39.945, | |
| "eval_samples_per_second": 2.253, | |
| "eval_steps_per_second": 1.127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 64.42476654052734, | |
| "learning_rate": 2e-05, | |
| "loss": 193.3897, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "eval_loss": 12.096670150756836, | |
| "eval_runtime": 19.6632, | |
| "eval_samples_per_second": 4.577, | |
| "eval_steps_per_second": 2.289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 66.10076141357422, | |
| "learning_rate": 3e-05, | |
| "loss": 182.7836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "grad_norm": 108.9141616821289, | |
| "learning_rate": 4e-05, | |
| "loss": 193.7319, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "eval_loss": 11.990538597106934, | |
| "eval_runtime": 21.4072, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 2.102, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 88.95408630371094, | |
| "learning_rate": 5e-05, | |
| "loss": 185.9496, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6148528388702208.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |