| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 1365, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.4039404629917024, | |
| "eval_loss": 7.20004940032959, | |
| "eval_runtime": 50.7329, | |
| "eval_samples_per_second": 5.657, | |
| "eval_steps_per_second": 0.355, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.4787465734896706, | |
| "eval_loss": 5.66867733001709, | |
| "eval_runtime": 55.4465, | |
| "eval_samples_per_second": 5.176, | |
| "eval_steps_per_second": 0.325, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.5904877349198384, | |
| "eval_loss": 3.6859664916992188, | |
| "eval_runtime": 73.5691, | |
| "eval_samples_per_second": 3.901, | |
| "eval_steps_per_second": 0.245, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 6.668761007881571e-178, | |
| "eval_loss": 1.9221504926681519, | |
| "eval_runtime": 88.9014, | |
| "eval_samples_per_second": 3.228, | |
| "eval_steps_per_second": 0.202, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 1.316543479590963e-205, | |
| "eval_loss": 1.7383414506912231, | |
| "eval_runtime": 88.8327, | |
| "eval_samples_per_second": 3.231, | |
| "eval_steps_per_second": 0.203, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.4945054945054945, | |
| "grad_norm": 0.6254580616950989, | |
| "learning_rate": 2.982e-05, | |
| "loss": 4.7555, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.0, | |
| "eval_loss": 1.7286174297332764, | |
| "eval_runtime": 89.2075, | |
| "eval_samples_per_second": 3.217, | |
| "eval_steps_per_second": 0.202, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 1.8315963154383955e-15, | |
| "eval_loss": 1.7183585166931152, | |
| "eval_runtime": 87.5119, | |
| "eval_samples_per_second": 3.28, | |
| "eval_steps_per_second": 0.206, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 5.711058681679802, | |
| "eval_loss": 1.7143831253051758, | |
| "eval_runtime": 83.3467, | |
| "eval_samples_per_second": 3.443, | |
| "eval_steps_per_second": 0.216, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 13.353099059164704, | |
| "eval_loss": 1.7164381742477417, | |
| "eval_runtime": 80.7841, | |
| "eval_samples_per_second": 3.553, | |
| "eval_steps_per_second": 0.223, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 32.34281074053716, | |
| "eval_loss": 1.7173446416854858, | |
| "eval_runtime": 77.2458, | |
| "eval_samples_per_second": 3.715, | |
| "eval_steps_per_second": 0.233, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.989010989010989, | |
| "grad_norm": 0.37531596422195435, | |
| "learning_rate": 1.2763005780346821e-05, | |
| "loss": 1.5949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 41.978377435878755, | |
| "eval_loss": 1.7218164205551147, | |
| "eval_runtime": 66.2616, | |
| "eval_samples_per_second": 4.331, | |
| "eval_steps_per_second": 0.272, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 44.67533118422782, | |
| "eval_loss": 1.7217276096343994, | |
| "eval_runtime": 55.1606, | |
| "eval_samples_per_second": 5.203, | |
| "eval_steps_per_second": 0.326, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 44.686988280960264, | |
| "eval_loss": 1.7241053581237793, | |
| "eval_runtime": 54.4796, | |
| "eval_samples_per_second": 5.268, | |
| "eval_steps_per_second": 0.33, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 45.054758788488726, | |
| "eval_loss": 1.7239420413970947, | |
| "eval_runtime": 52.5392, | |
| "eval_samples_per_second": 5.463, | |
| "eval_steps_per_second": 0.343, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 44.208743444926874, | |
| "eval_loss": 1.7256550788879395, | |
| "eval_runtime": 58.9783, | |
| "eval_samples_per_second": 4.866, | |
| "eval_steps_per_second": 0.305, | |
| "step": 1365 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1365, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.172674477817856e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |