| { | |
| "best_metric": 0.21195632219314575, | |
| "best_model_checkpoint": "./home/dev15/web/Projects/monitoring_ai/resources/ai/Translation/results/checkpoint-1835", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1835, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.24953831732273102, | |
| "eval_runtime": 127.7934, | |
| "eval_samples_per_second": 11.472, | |
| "eval_steps_per_second": 0.72, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.3623978201634879, | |
| "grad_norm": 0.6348655223846436, | |
| "learning_rate": 4.3188010899182565e-05, | |
| "loss": 0.2975, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.22699691355228424, | |
| "eval_runtime": 117.6853, | |
| "eval_samples_per_second": 12.457, | |
| "eval_steps_per_second": 0.782, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 2.7247956403269757, | |
| "grad_norm": 0.7137888073921204, | |
| "learning_rate": 3.637602179836512e-05, | |
| "loss": 0.1989, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.21688026189804077, | |
| "eval_runtime": 115.8928, | |
| "eval_samples_per_second": 12.65, | |
| "eval_steps_per_second": 0.794, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.2130550593137741, | |
| "eval_runtime": 127.3999, | |
| "eval_samples_per_second": 11.507, | |
| "eval_steps_per_second": 0.722, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 4.087193460490464, | |
| "grad_norm": 0.601416826248169, | |
| "learning_rate": 2.9564032697547683e-05, | |
| "loss": 0.1552, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.21195632219314575, | |
| "eval_runtime": 126.6476, | |
| "eval_samples_per_second": 11.575, | |
| "eval_steps_per_second": 0.726, | |
| "step": 1835 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3670, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 993561076039680.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |