| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.677777777777778, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 0.15547114610671997, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.9596, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 0.13959258794784546, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.9643, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1348314606741573, | |
| "grad_norm": 0.14470240473747253, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1562, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 0.16597306728363037, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.1067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2247191011235955, | |
| "grad_norm": 0.14703088998794556, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 0.15088129043579102, | |
| "learning_rate": 6e-06, | |
| "loss": 1.0045, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3146067415730337, | |
| "grad_norm": 0.16761414706707, | |
| "learning_rate": 7e-06, | |
| "loss": 0.9547, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 0.14696507155895233, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.0284, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4044943820224719, | |
| "grad_norm": 0.19629372656345367, | |
| "learning_rate": 9e-06, | |
| "loss": 0.9615, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "grad_norm": 0.18038448691368103, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4943820224719101, | |
| "grad_norm": 0.22929255664348602, | |
| "learning_rate": 9.992134075089085e-06, | |
| "loss": 1.0329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 0.2177729308605194, | |
| "learning_rate": 9.968561049466214e-06, | |
| "loss": 0.9876, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5842696629213483, | |
| "grad_norm": 0.2739273011684418, | |
| "learning_rate": 9.92935509259118e-06, | |
| "loss": 0.9326, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6292134831460674, | |
| "grad_norm": 0.2714334726333618, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 1.0127, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6741573033707865, | |
| "grad_norm": 0.318387508392334, | |
| "learning_rate": 9.804586609725499e-06, | |
| "loss": 1.1761, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "grad_norm": 0.2760864198207855, | |
| "learning_rate": 9.719416651541839e-06, | |
| "loss": 0.9729, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7640449438202247, | |
| "grad_norm": 0.27431851625442505, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 0.9192, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "grad_norm": 0.24467918276786804, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.8674, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8539325842696629, | |
| "grad_norm": 0.25415292382240295, | |
| "learning_rate": 9.376117109543769e-06, | |
| "loss": 0.9619, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.898876404494382, | |
| "grad_norm": 0.26627272367477417, | |
| "learning_rate": 9.233620996141421e-06, | |
| "loss": 0.8804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9438202247191011, | |
| "grad_norm": 0.24633091688156128, | |
| "learning_rate": 9.077804344796302e-06, | |
| "loss": 0.8213, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9887640449438202, | |
| "grad_norm": 0.21531835198402405, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.8679, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0224719101123596, | |
| "grad_norm": 0.20492973923683167, | |
| "learning_rate": 8.728210824415829e-06, | |
| "loss": 0.7908, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0674157303370786, | |
| "grad_norm": 0.23310156166553497, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 0.9771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1123595505617978, | |
| "grad_norm": 0.17484751343727112, | |
| "learning_rate": 8.331732889760021e-06, | |
| "loss": 0.8474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1573033707865168, | |
| "grad_norm": 0.14636008441448212, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.8394, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.202247191011236, | |
| "grad_norm": 0.11921321600675583, | |
| "learning_rate": 7.89335648089903e-06, | |
| "loss": 0.9378, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.247191011235955, | |
| "grad_norm": 0.11381018161773682, | |
| "learning_rate": 7.660160382576683e-06, | |
| "loss": 0.7725, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2921348314606742, | |
| "grad_norm": 0.10614118725061417, | |
| "learning_rate": 7.4185944355261996e-06, | |
| "loss": 0.8286, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3370786516853932, | |
| "grad_norm": 0.10510330647230148, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.8442, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3820224719101124, | |
| "grad_norm": 0.11109460890293121, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 0.7933, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4269662921348314, | |
| "grad_norm": 0.10454461723566055, | |
| "learning_rate": 6.651395309775837e-06, | |
| "loss": 0.8542, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4719101123595506, | |
| "grad_norm": 0.1184382364153862, | |
| "learning_rate": 6.384177557124247e-06, | |
| "loss": 0.9169, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5168539325842696, | |
| "grad_norm": 0.10408931970596313, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.833, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5617977528089888, | |
| "grad_norm": 0.10440591722726822, | |
| "learning_rate": 5.837531116523683e-06, | |
| "loss": 0.7474, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.606741573033708, | |
| "grad_norm": 0.11137595772743225, | |
| "learning_rate": 5.559822380516539e-06, | |
| "loss": 0.7383, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.651685393258427, | |
| "grad_norm": 0.10157899558544159, | |
| "learning_rate": 5.2803522361859596e-06, | |
| "loss": 0.8452, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.696629213483146, | |
| "grad_norm": 0.09816641360521317, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7933, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7415730337078652, | |
| "grad_norm": 0.1001896858215332, | |
| "learning_rate": 4.719647763814041e-06, | |
| "loss": 0.7623, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7865168539325844, | |
| "grad_norm": 0.0913764163851738, | |
| "learning_rate": 4.4401776194834615e-06, | |
| "loss": 0.795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8314606741573034, | |
| "grad_norm": 0.09084523469209671, | |
| "learning_rate": 4.162468883476319e-06, | |
| "loss": 0.8777, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8764044943820224, | |
| "grad_norm": 0.09484092146158218, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.8205, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9213483146067416, | |
| "grad_norm": 0.09379491209983826, | |
| "learning_rate": 3.6158224428757538e-06, | |
| "loss": 0.7922, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9662921348314608, | |
| "grad_norm": 0.09965093433856964, | |
| "learning_rate": 3.3486046902241663e-06, | |
| "loss": 0.76, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.011111111111111, | |
| "grad_norm": 0.09761062264442444, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 0.6824, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0555555555555554, | |
| "grad_norm": 0.10253206640481949, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.7704, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 0.09422764182090759, | |
| "learning_rate": 2.5814055644738013e-06, | |
| "loss": 0.7789, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1444444444444444, | |
| "grad_norm": 0.09672325849533081, | |
| "learning_rate": 2.339839617423318e-06, | |
| "loss": 0.7831, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.188888888888889, | |
| "grad_norm": 0.10218799114227295, | |
| "learning_rate": 2.1066435191009717e-06, | |
| "loss": 0.7368, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2333333333333334, | |
| "grad_norm": 0.08994019776582718, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.8044, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2777777777777777, | |
| "grad_norm": 0.08405563980340958, | |
| "learning_rate": 1.6682671102399806e-06, | |
| "loss": 0.7778, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.3222222222222224, | |
| "grad_norm": 0.10619189590215683, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 0.7012, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.3666666666666667, | |
| "grad_norm": 0.10291200876235962, | |
| "learning_rate": 1.2717891755841722e-06, | |
| "loss": 0.7836, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.411111111111111, | |
| "grad_norm": 0.07774698734283447, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.8796, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.4555555555555557, | |
| "grad_norm": 0.09576702117919922, | |
| "learning_rate": 9.221956552036992e-07, | |
| "loss": 0.7232, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.0880877748131752, | |
| "learning_rate": 7.663790038585794e-07, | |
| "loss": 0.8087, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.5444444444444443, | |
| "grad_norm": 0.08929711580276489, | |
| "learning_rate": 6.238828904562316e-07, | |
| "loss": 0.7278, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.588888888888889, | |
| "grad_norm": 0.08319777995347977, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.7033, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.6333333333333333, | |
| "grad_norm": 0.08942956477403641, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 0.8097, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.677777777777778, | |
| "grad_norm": 0.09436023980379105, | |
| "learning_rate": 2.8058334845816214e-07, | |
| "loss": 0.7641, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 66, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.035992262870303e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |