| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022013097793186946, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011006548896593473, | |
| "eval_loss": 1.3274837732315063, | |
| "eval_runtime": 241.8919, | |
| "eval_samples_per_second": 15.817, | |
| "eval_steps_per_second": 7.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011006548896593472, | |
| "grad_norm": 0.49815604090690613, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2469, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022013097793186945, | |
| "grad_norm": 0.4162350296974182, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003301964668978042, | |
| "grad_norm": 0.4359431564807892, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1139, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004402619558637389, | |
| "grad_norm": 0.34668853878974915, | |
| "learning_rate": 0.0002, | |
| "loss": 1.103, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005503274448296736, | |
| "grad_norm": 0.36034461855888367, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0576, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005503274448296736, | |
| "eval_loss": 1.0534749031066895, | |
| "eval_runtime": 240.7504, | |
| "eval_samples_per_second": 15.892, | |
| "eval_steps_per_second": 7.946, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006603929337956084, | |
| "grad_norm": 0.42812806367874146, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007704584227615431, | |
| "grad_norm": 0.44979560375213623, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0747, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008805239117274778, | |
| "grad_norm": 0.444010466337204, | |
| "learning_rate": 0.0002, | |
| "loss": 1.031, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009905894006934125, | |
| "grad_norm": 0.44595256447792053, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0268, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011006548896593473, | |
| "grad_norm": 0.46254387497901917, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0139, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011006548896593473, | |
| "eval_loss": 1.0108003616333008, | |
| "eval_runtime": 240.8303, | |
| "eval_samples_per_second": 15.887, | |
| "eval_steps_per_second": 7.943, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01210720378625282, | |
| "grad_norm": 0.47793570160865784, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9809, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.013207858675912168, | |
| "grad_norm": 0.5524470806121826, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0559, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.014308513565571515, | |
| "grad_norm": 0.5550538301467896, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9841, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.015409168455230863, | |
| "grad_norm": 0.46083733439445496, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0335, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01650982334489021, | |
| "grad_norm": 0.4849002957344055, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9981, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01650982334489021, | |
| "eval_loss": 0.9864005446434021, | |
| "eval_runtime": 240.7832, | |
| "eval_samples_per_second": 15.89, | |
| "eval_steps_per_second": 7.945, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.017610478234549556, | |
| "grad_norm": 0.5414583086967468, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9461, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.018711133124208905, | |
| "grad_norm": 0.47824686765670776, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0095, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01981178801386825, | |
| "grad_norm": 0.47877955436706543, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9779, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0209124429035276, | |
| "grad_norm": 0.3664035499095917, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0182, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.022013097793186946, | |
| "grad_norm": 0.4645732045173645, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9779, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.022013097793186946, | |
| "eval_loss": 0.9666519165039062, | |
| "eval_runtime": 240.7663, | |
| "eval_samples_per_second": 15.891, | |
| "eval_steps_per_second": 7.945, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.78621657923584e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |