| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011490950876185005, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011490950876185004, | |
| "grad_norm": 0.4355420172214508, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1452, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011490950876185004, | |
| "eval_loss": 0.24649782478809357, | |
| "eval_runtime": 55.9857, | |
| "eval_samples_per_second": 65.463, | |
| "eval_steps_per_second": 32.74, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022981901752370008, | |
| "grad_norm": 0.24712371826171875, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1321, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003447285262855501, | |
| "grad_norm": 0.2532672584056854, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1581, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003447285262855501, | |
| "eval_loss": 0.24553273618221283, | |
| "eval_runtime": 54.6321, | |
| "eval_samples_per_second": 67.085, | |
| "eval_steps_per_second": 33.552, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00045963803504740016, | |
| "grad_norm": 0.32027900218963623, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005745475438092502, | |
| "grad_norm": 0.38881251215934753, | |
| "learning_rate": 0.0001, | |
| "loss": 0.732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006894570525711002, | |
| "grad_norm": 0.2480206936597824, | |
| "learning_rate": 0.00012, | |
| "loss": 0.2059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006894570525711002, | |
| "eval_loss": 0.22881807386875153, | |
| "eval_runtime": 53.9174, | |
| "eval_samples_per_second": 67.974, | |
| "eval_steps_per_second": 33.996, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008043665613329503, | |
| "grad_norm": 0.5224636197090149, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8476, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009192760700948003, | |
| "grad_norm": 0.33684462308883667, | |
| "learning_rate": 0.00016, | |
| "loss": 0.1473, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010341855788566503, | |
| "grad_norm": 0.2588774263858795, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0942, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010341855788566503, | |
| "eval_loss": 0.18360577523708344, | |
| "eval_runtime": 54.7844, | |
| "eval_samples_per_second": 66.899, | |
| "eval_steps_per_second": 33.458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011490950876185005, | |
| "grad_norm": 0.31410184502601624, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0808, | |
| "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": 270613704867840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |