| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10552975939214859, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005276487969607429, | |
| "grad_norm": 0.18370409309864044, | |
| "learning_rate": 2.9947235120303926e-05, | |
| "loss": 1.1735, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010552975939214858, | |
| "grad_norm": 0.30922940373420715, | |
| "learning_rate": 2.989447024060785e-05, | |
| "loss": 0.2337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.015829463908822287, | |
| "grad_norm": 0.8381773829460144, | |
| "learning_rate": 2.9841705360911777e-05, | |
| "loss": 0.0379, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.021105951878429716, | |
| "grad_norm": 0.05767253041267395, | |
| "learning_rate": 2.9788940481215702e-05, | |
| "loss": 0.0066, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026382439848037148, | |
| "grad_norm": 0.012116221711039543, | |
| "learning_rate": 2.9736175601519628e-05, | |
| "loss": 0.0012, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.031658927817644573, | |
| "grad_norm": 0.016889669001102448, | |
| "learning_rate": 2.9683410721823553e-05, | |
| "loss": 0.0005, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.036935415787252006, | |
| "grad_norm": 0.0024384360294789076, | |
| "learning_rate": 2.9630645842127478e-05, | |
| "loss": 0.0004, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04221190375685943, | |
| "grad_norm": 0.0030085756443440914, | |
| "learning_rate": 2.9577880962431404e-05, | |
| "loss": 0.0007, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.047488391726466864, | |
| "grad_norm": 0.15239033102989197, | |
| "learning_rate": 2.952511608273533e-05, | |
| "loss": 0.0006, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.052764879696074296, | |
| "grad_norm": 0.008578498847782612, | |
| "learning_rate": 2.947235120303926e-05, | |
| "loss": 0.0002, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05804136766568172, | |
| "grad_norm": 0.0026750785764306784, | |
| "learning_rate": 2.9419586323343186e-05, | |
| "loss": 0.0002, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.06331785563528915, | |
| "grad_norm": 0.0012680699583142996, | |
| "learning_rate": 2.9366821443647112e-05, | |
| "loss": 0.0002, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06859434360489658, | |
| "grad_norm": 0.0009559642057865858, | |
| "learning_rate": 2.9314056563951037e-05, | |
| "loss": 0.0002, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.07387083157450401, | |
| "grad_norm": 0.0017577861435711384, | |
| "learning_rate": 2.9261291684254962e-05, | |
| "loss": 0.0002, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.07914731954411144, | |
| "grad_norm": 0.0010916043538600206, | |
| "learning_rate": 2.9208526804558888e-05, | |
| "loss": 0.0002, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.08442380751371886, | |
| "grad_norm": 0.006868909113109112, | |
| "learning_rate": 2.9155761924862813e-05, | |
| "loss": 0.0002, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0897002954833263, | |
| "grad_norm": 0.004868048708885908, | |
| "learning_rate": 2.910299704516674e-05, | |
| "loss": 0.0011, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.09497678345293373, | |
| "grad_norm": 0.0061646196991205215, | |
| "learning_rate": 2.9050232165470664e-05, | |
| "loss": 0.0007, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.10025327142254116, | |
| "grad_norm": 0.0006258169887587428, | |
| "learning_rate": 2.899746728577459e-05, | |
| "loss": 0.0002, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.10552975939214859, | |
| "grad_norm": 0.002904047491028905, | |
| "learning_rate": 2.8944702406078515e-05, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 28428, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |