| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006351222610352493, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "grad_norm": 1.7062007827917114e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.4713, | |
| "eval_samples_per_second": 190.997, | |
| "eval_steps_per_second": 95.643, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012702445220704986, | |
| "grad_norm": 1.8129745512851514e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "grad_norm": 1.546772000438068e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.6127, | |
| "eval_samples_per_second": 183.52, | |
| "eval_steps_per_second": 91.898, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025404890441409972, | |
| "grad_norm": 3.256682975916192e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031756113051762463, | |
| "grad_norm": 3.3200616599060595e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "grad_norm": 2.9896031264797784e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.6001, | |
| "eval_samples_per_second": 184.163, | |
| "eval_steps_per_second": 92.22, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004445855827246745, | |
| "grad_norm": 1.4344588635140099e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0050809780882819944, | |
| "grad_norm": 1.4874678527121432e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "grad_norm": 2.7079668143414892e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.6694, | |
| "eval_samples_per_second": 180.685, | |
| "eval_steps_per_second": 90.479, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006351222610352493, | |
| "grad_norm": 3.1126408430282027e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 214170943488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |