| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 4110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24330900243309003, | |
| "grad_norm": 14.526427268981934, | |
| "learning_rate": 1.9195458231954583e-05, | |
| "loss": 3.5943, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48661800486618007, | |
| "grad_norm": 16.526565551757812, | |
| "learning_rate": 1.8384428223844285e-05, | |
| "loss": 3.1431, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "grad_norm": 11.656450271606445, | |
| "learning_rate": 1.7573398215733984e-05, | |
| "loss": 2.9201, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9732360097323601, | |
| "grad_norm": 13.380396842956543, | |
| "learning_rate": 1.6762368207623682e-05, | |
| "loss": 2.7711, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 12.810223940577195, | |
| "eval_loss": 2.420867681503296, | |
| "eval_rouge": { | |
| "rouge1": 0.30991633445023503, | |
| "rouge2": 0.11181858129315748, | |
| "rougeL": 0.3092627118644087, | |
| "rougeLsum": 0.30911397265634744 | |
| }, | |
| "eval_runtime": 264.2267, | |
| "eval_samples_per_second": 33.494, | |
| "eval_steps_per_second": 2.097, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 1.2165450121654502, | |
| "grad_norm": 13.43653392791748, | |
| "learning_rate": 1.5951338199513384e-05, | |
| "loss": 2.3949, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4598540145985401, | |
| "grad_norm": 13.36623764038086, | |
| "learning_rate": 1.5140308191403083e-05, | |
| "loss": 2.2468, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7031630170316303, | |
| "grad_norm": 12.249001502990723, | |
| "learning_rate": 1.4329278183292783e-05, | |
| "loss": 2.2239, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.94647201946472, | |
| "grad_norm": 14.571913719177246, | |
| "learning_rate": 1.3518248175182482e-05, | |
| "loss": 2.1585, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 18.428136367860084, | |
| "eval_loss": 2.1254029273986816, | |
| "eval_rouge": { | |
| "rouge1": 0.3476506591337114, | |
| "rouge2": 0.13975840731772934, | |
| "rougeL": 0.34719576719576883, | |
| "rougeLsum": 0.3470716527665696 | |
| }, | |
| "eval_runtime": 264.8536, | |
| "eval_samples_per_second": 33.415, | |
| "eval_steps_per_second": 2.092, | |
| "step": 4110 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12330, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 344062842568704.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |