| { | |
| "best_metric": 0.6969178318977356, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4383561643835616, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008767123287671232, | |
| "grad_norm": 20.05573272705078, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9854, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008767123287671232, | |
| "eval_loss": 7.201192855834961, | |
| "eval_runtime": 23.5294, | |
| "eval_samples_per_second": 32.683, | |
| "eval_steps_per_second": 4.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017534246575342465, | |
| "grad_norm": 17.615022659301758, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0263013698630137, | |
| "grad_norm": 14.698570251464844, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.9672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03506849315068493, | |
| "grad_norm": 14.905780792236328, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.043835616438356165, | |
| "grad_norm": 13.3781099319458, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0526027397260274, | |
| "grad_norm": 4.5874924659729, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9954, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06136986301369863, | |
| "grad_norm": 3.978563070297241, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8675, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07013698630136986, | |
| "grad_norm": 2.2998287677764893, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7723, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0789041095890411, | |
| "grad_norm": 3.281687021255493, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7537, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08767123287671233, | |
| "grad_norm": 1.4720951318740845, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09643835616438357, | |
| "grad_norm": 1.1521276235580444, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7025, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1052054794520548, | |
| "grad_norm": 1.9535162448883057, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6964, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11397260273972602, | |
| "grad_norm": 1.1660391092300415, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6992, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12273972602739726, | |
| "grad_norm": 2.2504096031188965, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7409, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13150684931506848, | |
| "grad_norm": 1.188321828842163, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.709, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14027397260273972, | |
| "grad_norm": 0.5811285972595215, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6904, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14904109589041095, | |
| "grad_norm": 1.6429232358932495, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.707, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1578082191780822, | |
| "grad_norm": 2.918581247329712, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16657534246575342, | |
| "grad_norm": 0.7487760782241821, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6948, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17534246575342466, | |
| "grad_norm": 1.080714225769043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7048, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1841095890410959, | |
| "grad_norm": 0.9710987210273743, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7044, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19287671232876713, | |
| "grad_norm": 0.5480700135231018, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7005, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20164383561643837, | |
| "grad_norm": 0.9117023348808289, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7057, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2104109589041096, | |
| "grad_norm": 0.7569409012794495, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.3170976936817169, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "eval_loss": 0.7007076144218445, | |
| "eval_runtime": 23.4954, | |
| "eval_samples_per_second": 32.73, | |
| "eval_steps_per_second": 4.128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22794520547945205, | |
| "grad_norm": 1.066445231437683, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7141, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23671232876712328, | |
| "grad_norm": 0.6127803325653076, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6957, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24547945205479452, | |
| "grad_norm": 0.7028255462646484, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6946, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25424657534246575, | |
| "grad_norm": 0.7202122211456299, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6816, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26301369863013696, | |
| "grad_norm": 0.2293580323457718, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2717808219178082, | |
| "grad_norm": 1.1750402450561523, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7183, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28054794520547943, | |
| "grad_norm": 0.39852091670036316, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7003, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2893150684931507, | |
| "grad_norm": 0.5287603735923767, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6979, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2980821917808219, | |
| "grad_norm": 0.6953926086425781, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7014, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30684931506849317, | |
| "grad_norm": 0.5524169206619263, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6915, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3156164383561644, | |
| "grad_norm": 0.7208291888237, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6864, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32438356164383564, | |
| "grad_norm": 0.28683096170425415, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33315068493150685, | |
| "grad_norm": 0.3897854685783386, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6978, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3419178082191781, | |
| "grad_norm": 0.2978964149951935, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6946, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3506849315068493, | |
| "grad_norm": 0.4156556725502014, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.691, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3594520547945205, | |
| "grad_norm": 0.15310971438884735, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6926, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3682191780821918, | |
| "grad_norm": 0.3335914611816406, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6923, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.376986301369863, | |
| "grad_norm": 0.14917869865894318, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6942, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38575342465753426, | |
| "grad_norm": 0.7024045586585999, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6965, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39452054794520547, | |
| "grad_norm": 0.7428992390632629, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7004, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40328767123287673, | |
| "grad_norm": 0.44110044836997986, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6889, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41205479452054794, | |
| "grad_norm": 0.3936268091201782, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6905, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4208219178082192, | |
| "grad_norm": 0.5188143253326416, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6922, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4295890410958904, | |
| "grad_norm": 0.46438923478126526, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6922, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.21112455427646637, | |
| "learning_rate": 0.0, | |
| "loss": 0.6954, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "eval_loss": 0.6969178318977356, | |
| "eval_runtime": 23.5116, | |
| "eval_samples_per_second": 32.707, | |
| "eval_steps_per_second": 4.126, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.9736786926882e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |