| { | |
| "best_metric": 0.47569820284843445, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.73972602739726, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 2.1911723613739014, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1243, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "eval_loss": 2.322556972503662, | |
| "eval_runtime": 1.4644, | |
| "eval_samples_per_second": 83.993, | |
| "eval_steps_per_second": 10.926, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 2.2915894985198975, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2102, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 2.287838935852051, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 2.2436702251434326, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8866, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 2.225752592086792, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 2.5399177074432373, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1843, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3835616438356164, | |
| "grad_norm": 2.1273326873779297, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9053, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 1.2077769041061401, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7413, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4931506849315068, | |
| "grad_norm": 0.8515187501907349, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.6145463585853577, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5881, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6027397260273972, | |
| "grad_norm": 0.6945990920066833, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.6183176636695862, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6014, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7123287671232876, | |
| "grad_norm": 0.7185230255126953, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5301, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7671232876712328, | |
| "grad_norm": 0.587353527545929, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5003, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.5427547097206116, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.551, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.4918208420276642, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4888, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9315068493150684, | |
| "grad_norm": 0.5143556594848633, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6516, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9863013698630136, | |
| "grad_norm": 0.5198273062705994, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5301, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0410958904109588, | |
| "grad_norm": 0.7991119623184204, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8473, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.44308751821517944, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4874, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1506849315068493, | |
| "grad_norm": 0.3959720730781555, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5215, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2054794520547945, | |
| "grad_norm": 0.4689987897872925, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5615, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2602739726027397, | |
| "grad_norm": 0.41961339116096497, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4448, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3150684931506849, | |
| "grad_norm": 0.4268343448638916, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4324, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "grad_norm": 0.38932234048843384, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4158, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "eval_loss": 0.5110846757888794, | |
| "eval_runtime": 1.4625, | |
| "eval_samples_per_second": 84.104, | |
| "eval_steps_per_second": 10.94, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4246575342465753, | |
| "grad_norm": 0.41463303565979004, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4533, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4794520547945205, | |
| "grad_norm": 0.38293758034706116, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4532, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5342465753424657, | |
| "grad_norm": 0.3628367483615875, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4094, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.589041095890411, | |
| "grad_norm": 0.42759907245635986, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4622, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 0.36563095450401306, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4902, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6986301369863015, | |
| "grad_norm": 0.4586554765701294, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4133, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7534246575342465, | |
| "grad_norm": 0.32642537355422974, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3652, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.808219178082192, | |
| "grad_norm": 0.3642094135284424, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3965, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8630136986301369, | |
| "grad_norm": 0.36974775791168213, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4403, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.9178082191780823, | |
| "grad_norm": 0.37709006667137146, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4803, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9726027397260273, | |
| "grad_norm": 0.4891318380832672, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5114, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0273972602739727, | |
| "grad_norm": 0.8724299073219299, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7102, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.0821917808219177, | |
| "grad_norm": 0.4001636207103729, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4218, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.136986301369863, | |
| "grad_norm": 0.3491167426109314, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4221, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 0.37197569012641907, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4686, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2465753424657535, | |
| "grad_norm": 0.4310151934623718, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3679, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.3013698630136985, | |
| "grad_norm": 0.396329790353775, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4621, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.356164383561644, | |
| "grad_norm": 0.35895678400993347, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4256, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.410958904109589, | |
| "grad_norm": 0.3557685911655426, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4232, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.4657534246575343, | |
| "grad_norm": 0.3738231658935547, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4006, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.5205479452054793, | |
| "grad_norm": 0.36462685465812683, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.395, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.5753424657534247, | |
| "grad_norm": 0.3373780846595764, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3644, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.6301369863013697, | |
| "grad_norm": 0.3781304955482483, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4711, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.684931506849315, | |
| "grad_norm": 0.3349582254886627, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4397, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 0.3511578440666199, | |
| "learning_rate": 0.0, | |
| "loss": 0.415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "eval_loss": 0.47569820284843445, | |
| "eval_runtime": 1.4632, | |
| "eval_samples_per_second": 84.064, | |
| "eval_steps_per_second": 10.935, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |