| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.010989010989011, | |
| "eval_steps": 18, | |
| "global_step": 69, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014652014652014652, | |
| "eval_loss": 1.734892725944519, | |
| "eval_runtime": 1.6866, | |
| "eval_samples_per_second": 17.195, | |
| "eval_steps_per_second": 8.894, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "grad_norm": 0.23976674675941467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7015, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 0.25410085916519165, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 0.42443525791168213, | |
| "learning_rate": 9.82383934407258e-05, | |
| "loss": 1.6018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26373626373626374, | |
| "eval_loss": 1.4797354936599731, | |
| "eval_runtime": 1.6858, | |
| "eval_samples_per_second": 17.202, | |
| "eval_steps_per_second": 8.898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 0.3112971782684326, | |
| "learning_rate": 9.30777040696903e-05, | |
| "loss": 1.5036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3663003663003663, | |
| "grad_norm": 0.26191750168800354, | |
| "learning_rate": 8.488157605674925e-05, | |
| "loss": 1.4147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.2886798083782196, | |
| "learning_rate": 7.422754351663252e-05, | |
| "loss": 1.3807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.24221237003803253, | |
| "learning_rate": 6.186633499355576e-05, | |
| "loss": 1.3328, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5274725274725275, | |
| "eval_loss": 1.3494279384613037, | |
| "eval_runtime": 1.6879, | |
| "eval_samples_per_second": 17.181, | |
| "eval_steps_per_second": 8.887, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.2196742296218872, | |
| "learning_rate": 4.866897392811126e-05, | |
| "loss": 1.399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.23982864618301392, | |
| "learning_rate": 3.556540263301896e-05, | |
| "loss": 1.3184, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 0.22501102089881897, | |
| "learning_rate": 2.347895459401288e-05, | |
| "loss": 1.2391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7912087912087912, | |
| "eval_loss": 1.2975658178329468, | |
| "eval_runtime": 1.6936, | |
| "eval_samples_per_second": 17.124, | |
| "eval_steps_per_second": 8.857, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8058608058608059, | |
| "grad_norm": 0.17278903722763062, | |
| "learning_rate": 1.3261292456846647e-05, | |
| "loss": 1.3108, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.17497693002223969, | |
| "learning_rate": 5.6323962471714286e-06, | |
| "loss": 1.3163, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.23885966837406158, | |
| "learning_rate": 1.1298305091066664e-06, | |
| "loss": 1.292, | |
| "step": 65 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 69, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.0986773236678656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |