| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 2220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_f1": 0.018691588785046728, | |
| "eval_loss": 0.8330444097518921, | |
| "eval_precision": 0.009461009174311927, | |
| "eval_recall": 0.7674418604651163, | |
| "eval_runtime": 51.6093, | |
| "eval_samples_per_second": 90.546, | |
| "eval_steps_per_second": 11.335, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.4809592068195343, | |
| "learning_rate": 3.998194945848376e-05, | |
| "loss": 0.0586, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.059180792421102524, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 52.6196, | |
| "eval_samples_per_second": 88.807, | |
| "eval_steps_per_second": 11.118, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 14.132050514221191, | |
| "learning_rate": 2.996389891696751e-05, | |
| "loss": 0.0557, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.05642171949148178, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 40.9562, | |
| "eval_samples_per_second": 114.097, | |
| "eval_steps_per_second": 14.284, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.548943996429443, | |
| "learning_rate": 1.9945848375451266e-05, | |
| "loss": 0.0553, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.05951603502035141, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 40.9175, | |
| "eval_samples_per_second": 114.205, | |
| "eval_steps_per_second": 14.297, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.44529011845588684, | |
| "learning_rate": 9.927797833935018e-06, | |
| "loss": 0.0558, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.059898294508457184, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 40.5657, | |
| "eval_samples_per_second": 115.196, | |
| "eval_steps_per_second": 14.421, | |
| "step": 2220 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2770, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.717028512353485e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |