| { | |
| "best_metric": 1.0918176174163818, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2059732234809475, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008238928939237899, | |
| "grad_norm": 1.3493034839630127, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008238928939237899, | |
| "eval_loss": 1.754831314086914, | |
| "eval_runtime": 28.9839, | |
| "eval_samples_per_second": 28.223, | |
| "eval_steps_per_second": 3.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 1.0823650360107422, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024716786817713696, | |
| "grad_norm": 1.0006831884384155, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032955715756951595, | |
| "grad_norm": 0.5157923102378845, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1883, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0411946446961895, | |
| "grad_norm": 0.5396899580955505, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04943357363542739, | |
| "grad_norm": 0.5691497921943665, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.057672502574665295, | |
| "grad_norm": 0.4316560626029968, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1932, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06591143151390319, | |
| "grad_norm": 0.38552603125572205, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2687, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07415036045314109, | |
| "grad_norm": 0.3694867491722107, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4062, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.082389289392379, | |
| "grad_norm": 0.4373791515827179, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.569, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09062821833161688, | |
| "grad_norm": 0.7083751559257507, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.857, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09886714727085479, | |
| "grad_norm": 3.521287441253662, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10710607621009269, | |
| "grad_norm": 2.4093360900878906, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9829, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11534500514933059, | |
| "grad_norm": 1.6218130588531494, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0176, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12358393408856849, | |
| "grad_norm": 0.743577778339386, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13182286302780638, | |
| "grad_norm": 0.3841581344604492, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1400617919670443, | |
| "grad_norm": 0.40283846855163574, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.036, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14830072090628219, | |
| "grad_norm": 0.3529587388038635, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0628, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15653964984552007, | |
| "grad_norm": 0.3646421432495117, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0915, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.164778578784758, | |
| "grad_norm": 0.3263953924179077, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17301750772399588, | |
| "grad_norm": 0.296126127243042, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18125643666323377, | |
| "grad_norm": 0.3966723084449768, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3886, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18949536560247168, | |
| "grad_norm": 0.4947672486305237, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5394, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19773429454170957, | |
| "grad_norm": 1.0129477977752686, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "grad_norm": 4.30376672744751, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4598, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "eval_loss": 1.0918176174163818, | |
| "eval_runtime": 27.4744, | |
| "eval_samples_per_second": 29.773, | |
| "eval_steps_per_second": 3.749, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 3.0358346152699494e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |