| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1221001221001221, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002442002442002442, | |
| "eval_loss": 1.5199602842330933, | |
| "eval_runtime": 10.9508, | |
| "eval_samples_per_second": 15.798, | |
| "eval_steps_per_second": 7.945, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 5.148207664489746, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 5.6002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "eval_loss": 1.1478352546691895, | |
| "eval_runtime": 9.4464, | |
| "eval_samples_per_second": 18.314, | |
| "eval_steps_per_second": 9.21, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "grad_norm": 4.831728458404541, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.4207, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "eval_loss": 1.008975863456726, | |
| "eval_runtime": 9.4523, | |
| "eval_samples_per_second": 18.302, | |
| "eval_steps_per_second": 9.204, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "grad_norm": 4.645752906799316, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 4.0549, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "eval_loss": 0.9627972841262817, | |
| "eval_runtime": 9.4525, | |
| "eval_samples_per_second": 18.302, | |
| "eval_steps_per_second": 9.204, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09768009768009768, | |
| "grad_norm": 4.531153202056885, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 3.7785, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1221001221001221, | |
| "grad_norm": 4.782752990722656, | |
| "learning_rate": 0.0, | |
| "loss": 3.7577, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7044733247356928e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |