| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002542013839853128, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028244598220590313, | |
| "grad_norm": 0.5747796893119812, | |
| "learning_rate": 2e-05, | |
| "loss": 1.694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028244598220590313, | |
| "eval_loss": 1.4107834100723267, | |
| "eval_runtime": 85.4385, | |
| "eval_samples_per_second": 17.451, | |
| "eval_steps_per_second": 8.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005648919644118063, | |
| "grad_norm": 0.48896852135658264, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2039, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008473379466177093, | |
| "grad_norm": 0.49957290291786194, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008473379466177093, | |
| "eval_loss": 1.4086753129959106, | |
| "eval_runtime": 83.6679, | |
| "eval_samples_per_second": 17.82, | |
| "eval_steps_per_second": 8.916, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011297839288236125, | |
| "grad_norm": 0.5963613986968994, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5737, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014122299110295156, | |
| "grad_norm": 0.5199744701385498, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2807, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016946758932354187, | |
| "grad_norm": 0.6121755838394165, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4986, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016946758932354187, | |
| "eval_loss": 1.3738065958023071, | |
| "eval_runtime": 83.6437, | |
| "eval_samples_per_second": 17.826, | |
| "eval_steps_per_second": 8.919, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001977121875441322, | |
| "grad_norm": 0.5695703625679016, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2501, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002259567857647225, | |
| "grad_norm": 0.6682353019714355, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002542013839853128, | |
| "grad_norm": 0.4877820312976837, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0721, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002542013839853128, | |
| "eval_loss": 1.3457406759262085, | |
| "eval_runtime": 83.8049, | |
| "eval_samples_per_second": 17.791, | |
| "eval_steps_per_second": 8.902, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3282976540459008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |