| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024198427102238356, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "grad_norm": 4.1465654373168945, | |
| "learning_rate": 2e-05, | |
| "loss": 8.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024198427102238354, | |
| "eval_loss": 1.9028900861740112, | |
| "eval_runtime": 25.5484, | |
| "eval_samples_per_second": 68.106, | |
| "eval_steps_per_second": 34.053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004839685420447671, | |
| "grad_norm": 2.8063485622406006, | |
| "learning_rate": 4e-05, | |
| "loss": 7.5548, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007259528130671506, | |
| "grad_norm": 2.4317469596862793, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1063, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007259528130671506, | |
| "eval_loss": 1.8981304168701172, | |
| "eval_runtime": 24.0281, | |
| "eval_samples_per_second": 72.415, | |
| "eval_steps_per_second": 36.208, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009679370840895341, | |
| "grad_norm": 2.761960744857788, | |
| "learning_rate": 8e-05, | |
| "loss": 7.4454, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012099213551119178, | |
| "grad_norm": 2.2079269886016846, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "grad_norm": 3.3419997692108154, | |
| "learning_rate": 0.00012, | |
| "loss": 7.9704, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014519056261343012, | |
| "eval_loss": 1.8670881986618042, | |
| "eval_runtime": 24.2865, | |
| "eval_samples_per_second": 71.645, | |
| "eval_steps_per_second": 35.822, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016938898971566847, | |
| "grad_norm": 3.5104832649230957, | |
| "learning_rate": 0.00014, | |
| "loss": 7.5518, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019358741681790683, | |
| "grad_norm": 4.050289154052734, | |
| "learning_rate": 0.00016, | |
| "loss": 8.0078, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002177858439201452, | |
| "grad_norm": 2.97609281539917, | |
| "learning_rate": 0.00018, | |
| "loss": 7.3975, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002177858439201452, | |
| "eval_loss": 1.8141168355941772, | |
| "eval_runtime": 24.084, | |
| "eval_samples_per_second": 72.247, | |
| "eval_steps_per_second": 36.124, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024198427102238356, | |
| "grad_norm": 2.461378335952759, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2827, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 395864476483584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |