| { | |
| "best_metric": 1.3522154092788696, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.5092250922509225, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05904059040590406, | |
| "grad_norm": 1.1496527194976807, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05904059040590406, | |
| "eval_loss": 3.892582416534424, | |
| "eval_runtime": 7.6344, | |
| "eval_samples_per_second": 14.932, | |
| "eval_steps_per_second": 1.965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11808118081180811, | |
| "grad_norm": 1.553861141204834, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6531, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17712177121771217, | |
| "grad_norm": 2.0015130043029785, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8439, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23616236162361623, | |
| "grad_norm": 3.1150104999542236, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9066, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2952029520295203, | |
| "grad_norm": 1.5013198852539062, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.0767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.35424354243542433, | |
| "grad_norm": 1.589866042137146, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9593, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4132841328413284, | |
| "grad_norm": 1.7367578744888306, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.667, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47232472324723246, | |
| "grad_norm": 2.3528215885162354, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4693, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5313653136531366, | |
| "grad_norm": 0.885979175567627, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5904059040590406, | |
| "grad_norm": 1.511607050895691, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6494464944649446, | |
| "grad_norm": 1.1623610258102417, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9164, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7084870848708487, | |
| "grad_norm": 1.9204797744750977, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7675276752767528, | |
| "grad_norm": 1.4911789894104004, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.1316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8265682656826568, | |
| "grad_norm": 1.2774314880371094, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6441, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8856088560885609, | |
| "grad_norm": 0.7690659761428833, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5387, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9446494464944649, | |
| "grad_norm": 1.2538986206054688, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5081, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.03690036900369, | |
| "grad_norm": 1.3436284065246582, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.8898, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0959409594095941, | |
| "grad_norm": 0.8974263072013855, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4797, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1549815498154983, | |
| "grad_norm": 0.7638198733329773, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4205, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2140221402214022, | |
| "grad_norm": 0.8817597031593323, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2953, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2730627306273063, | |
| "grad_norm": 0.7933611273765564, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6644, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3321033210332103, | |
| "grad_norm": 0.9345961809158325, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3915, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3911439114391144, | |
| "grad_norm": 0.8286240696907043, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2403, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4501845018450186, | |
| "grad_norm": 1.0293848514556885, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.356, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5092250922509225, | |
| "grad_norm": 0.9351940751075745, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5092250922509225, | |
| "eval_loss": 1.3522154092788696, | |
| "eval_runtime": 7.6404, | |
| "eval_samples_per_second": 14.921, | |
| "eval_steps_per_second": 1.963, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.629578157719552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |