| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07261724659606657, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002017145738779627, | |
| "eval_loss": 1.3803871870040894, | |
| "eval_runtime": 46.8345, | |
| "eval_samples_per_second": 17.829, | |
| "eval_steps_per_second": 2.242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006051437216338881, | |
| "grad_norm": 0.0706619843840599, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.3971, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012102874432677761, | |
| "grad_norm": 0.060850467532873154, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018154311649016642, | |
| "grad_norm": 0.0778835117816925, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.387, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018154311649016642, | |
| "eval_loss": 1.3788137435913086, | |
| "eval_runtime": 47.4343, | |
| "eval_samples_per_second": 17.603, | |
| "eval_steps_per_second": 2.214, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024205748865355523, | |
| "grad_norm": 0.07908966392278671, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 1.4137, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030257186081694403, | |
| "grad_norm": 0.07839653640985489, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 1.3398, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.036308623298033284, | |
| "grad_norm": 0.08289563655853271, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 1.4154, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.036308623298033284, | |
| "eval_loss": 1.3672126531600952, | |
| "eval_runtime": 47.5202, | |
| "eval_samples_per_second": 17.571, | |
| "eval_steps_per_second": 2.21, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04236006051437216, | |
| "grad_norm": 0.07574637979269028, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 1.3475, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.048411497730711045, | |
| "grad_norm": 0.06648290902376175, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 1.2828, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05446293494704992, | |
| "grad_norm": 0.07902548462152481, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 1.3281, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05446293494704992, | |
| "eval_loss": 1.3498567342758179, | |
| "eval_runtime": 47.5478, | |
| "eval_samples_per_second": 17.561, | |
| "eval_steps_per_second": 2.208, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.060514372163388806, | |
| "grad_norm": 0.07119950652122498, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 1.4393, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06656580937972768, | |
| "grad_norm": 0.06678444892168045, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 1.3122, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07261724659606657, | |
| "grad_norm": 0.06940136104822159, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 1.3441, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07261724659606657, | |
| "eval_loss": 1.3346147537231445, | |
| "eval_runtime": 47.518, | |
| "eval_samples_per_second": 17.572, | |
| "eval_steps_per_second": 2.21, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3056942444314624e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |