| { | |
| "best_metric": 0.32497915625572205, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.857142857142857, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 119.95789337158203, | |
| "learning_rate": 5e-05, | |
| "loss": 9.5795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "eval_loss": 10.865592002868652, | |
| "eval_runtime": 8.8509, | |
| "eval_samples_per_second": 13.332, | |
| "eval_steps_per_second": 1.695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 136.3372344970703, | |
| "learning_rate": 0.0001, | |
| "loss": 10.891, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 131.59805297851562, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 178.44557189941406, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.9967, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 150.31954956054688, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.4383, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 164.0292205810547, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.3331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 166.70643615722656, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.9167, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 200.03564453125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8511, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 151.0060272216797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9847, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 101.65083312988281, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 138.01072692871094, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1162, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 228.6566619873047, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6312, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 88.24999237060547, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6337, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 131.8696746826172, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0293, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 40.71337127685547, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5338, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 57.675994873046875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4165, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 121.78327178955078, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3142, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0285714285714285, | |
| "grad_norm": 50.67198944091797, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5551, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0857142857142856, | |
| "grad_norm": 48.584991455078125, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4864, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 47.51475524902344, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3946, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 49.214088439941406, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3408, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2571428571428571, | |
| "grad_norm": 61.9134635925293, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3792, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3142857142857143, | |
| "grad_norm": 43.447425842285156, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4235, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 27.594829559326172, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2305, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 15.006505012512207, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2186, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "eval_loss": 0.32497915625572205, | |
| "eval_runtime": 8.8491, | |
| "eval_samples_per_second": 13.335, | |
| "eval_steps_per_second": 1.695, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4857142857142858, | |
| "grad_norm": 67.27078247070312, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2382, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5428571428571427, | |
| "grad_norm": 67.86185455322266, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6056, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 27.157087326049805, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2472, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.657142857142857, | |
| "grad_norm": 15.01187515258789, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2245, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 92.60913848876953, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3284, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7714285714285714, | |
| "grad_norm": 41.45531463623047, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5279, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 22.579965591430664, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1891, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8857142857142857, | |
| "grad_norm": 24.665771484375, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1994, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9428571428571428, | |
| "grad_norm": 75.00896453857422, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3666, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 60.36460494995117, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.057142857142857, | |
| "grad_norm": 59.28746032714844, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5726, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1142857142857143, | |
| "grad_norm": 10.243675231933594, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1724, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1714285714285713, | |
| "grad_norm": 10.718981742858887, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1655, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2285714285714286, | |
| "grad_norm": 73.86691284179688, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3553, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 47.86000061035156, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5975, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.342857142857143, | |
| "grad_norm": 7.794114112854004, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1582, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 8.669590950012207, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1494, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.4571428571428573, | |
| "grad_norm": 51.95354461669922, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2887, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5142857142857142, | |
| "grad_norm": 33.48137664794922, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5533, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 22.704734802246094, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2776, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6285714285714286, | |
| "grad_norm": 8.269654273986816, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1551, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.685714285714286, | |
| "grad_norm": 54.720680236816406, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.275, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.742857142857143, | |
| "grad_norm": 64.00393676757812, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5011, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 41.11294174194336, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.418, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 9.837096214294434, | |
| "learning_rate": 0.0, | |
| "loss": 0.1549, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_loss": 0.35054242610931396, | |
| "eval_runtime": 8.8484, | |
| "eval_samples_per_second": 13.336, | |
| "eval_steps_per_second": 1.695, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |