| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004825672578115575, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009651345156231149, | |
| "grad_norm": 18.197153091430664, | |
| "learning_rate": 1e-05, | |
| "loss": 29.4443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009651345156231149, | |
| "eval_loss": 1.8182178735733032, | |
| "eval_runtime": 117.4006, | |
| "eval_samples_per_second": 14.864, | |
| "eval_steps_per_second": 7.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019302690312462299, | |
| "grad_norm": 17.190515518188477, | |
| "learning_rate": 2e-05, | |
| "loss": 28.9688, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019302690312462299, | |
| "eval_loss": NaN, | |
| "eval_runtime": 95.5577, | |
| "eval_samples_per_second": 18.261, | |
| "eval_steps_per_second": 9.136, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002895403546869345, | |
| "grad_norm": 22.34606170654297, | |
| "learning_rate": 3e-05, | |
| "loss": 28.0539, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0038605380624924597, | |
| "grad_norm": 18.832284927368164, | |
| "learning_rate": 4e-05, | |
| "loss": 30.457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0038605380624924597, | |
| "eval_loss": NaN, | |
| "eval_runtime": 127.7053, | |
| "eval_samples_per_second": 13.664, | |
| "eval_steps_per_second": 6.836, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004825672578115575, | |
| "grad_norm": 16.282943725585938, | |
| "learning_rate": 5e-05, | |
| "loss": 28.828, | |
| "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": 6332408345395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |