| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 67, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 4.677140235900879, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 4.6858649253845215, | |
| "learning_rate": 9.850746268656717e-06, | |
| "loss": 2.496, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04477611940298507, | |
| "grad_norm": 3.9940388202667236, | |
| "learning_rate": 9.701492537313434e-06, | |
| "loss": 2.582, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 3.8767054080963135, | |
| "learning_rate": 9.552238805970149e-06, | |
| "loss": 2.215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 2.339372396469116, | |
| "learning_rate": 9.402985074626867e-06, | |
| "loss": 1.9616, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 2.0336525440216064, | |
| "learning_rate": 9.253731343283582e-06, | |
| "loss": 1.9218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1044776119402985, | |
| "grad_norm": 2.4649195671081543, | |
| "learning_rate": 9.104477611940299e-06, | |
| "loss": 2.5598, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 1.7558526992797852, | |
| "learning_rate": 8.955223880597016e-06, | |
| "loss": 2.1746, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13432835820895522, | |
| "grad_norm": 1.5009433031082153, | |
| "learning_rate": 8.805970149253732e-06, | |
| "loss": 2.1801, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 1.7307460308074951, | |
| "learning_rate": 8.656716417910447e-06, | |
| "loss": 2.2179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16417910447761194, | |
| "grad_norm": 1.31997811794281, | |
| "learning_rate": 8.507462686567165e-06, | |
| "loss": 1.9017, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 1.0102890729904175, | |
| "learning_rate": 8.35820895522388e-06, | |
| "loss": 1.6226, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19402985074626866, | |
| "grad_norm": 1.1635653972625732, | |
| "learning_rate": 8.208955223880599e-06, | |
| "loss": 2.0264, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.9142751097679138, | |
| "learning_rate": 8.059701492537314e-06, | |
| "loss": 1.9922, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 1.1939051151275635, | |
| "learning_rate": 7.91044776119403e-06, | |
| "loss": 2.205, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.7413591742515564, | |
| "learning_rate": 7.761194029850747e-06, | |
| "loss": 1.9766, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2537313432835821, | |
| "grad_norm": 1.400302767753601, | |
| "learning_rate": 7.611940298507463e-06, | |
| "loss": 2.3456, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 0.9068132042884827, | |
| "learning_rate": 7.46268656716418e-06, | |
| "loss": 2.2168, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2835820895522388, | |
| "grad_norm": 0.865298867225647, | |
| "learning_rate": 7.313432835820896e-06, | |
| "loss": 1.9891, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 1.2902920246124268, | |
| "learning_rate": 7.164179104477612e-06, | |
| "loss": 2.1995, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31343283582089554, | |
| "grad_norm": 0.7621744871139526, | |
| "learning_rate": 7.014925373134329e-06, | |
| "loss": 2.1563, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 0.7494510412216187, | |
| "learning_rate": 6.865671641791045e-06, | |
| "loss": 1.9338, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34328358208955223, | |
| "grad_norm": 0.6722490191459656, | |
| "learning_rate": 6.7164179104477625e-06, | |
| "loss": 1.9195, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.5672370195388794, | |
| "learning_rate": 6.567164179104478e-06, | |
| "loss": 2.1004, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.5260008573532104, | |
| "learning_rate": 6.417910447761194e-06, | |
| "loss": 2.0207, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 0.6754623651504517, | |
| "learning_rate": 6.2686567164179116e-06, | |
| "loss": 2.0735, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.40298507462686567, | |
| "grad_norm": 0.5878338813781738, | |
| "learning_rate": 6.119402985074627e-06, | |
| "loss": 1.9148, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.531120240688324, | |
| "learning_rate": 5.970149253731343e-06, | |
| "loss": 1.9395, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.43283582089552236, | |
| "grad_norm": 0.667667806148529, | |
| "learning_rate": 5.820895522388061e-06, | |
| "loss": 2.038, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.7480222582817078, | |
| "learning_rate": 5.671641791044776e-06, | |
| "loss": 2.0045, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4626865671641791, | |
| "grad_norm": 0.9849134683609009, | |
| "learning_rate": 5.522388059701493e-06, | |
| "loss": 2.1881, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.6533071398735046, | |
| "learning_rate": 5.37313432835821e-06, | |
| "loss": 1.849, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4925373134328358, | |
| "grad_norm": 0.5160700082778931, | |
| "learning_rate": 5.2238805970149255e-06, | |
| "loss": 2.0241, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 0.5143930912017822, | |
| "learning_rate": 5.074626865671642e-06, | |
| "loss": 1.9619, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.6003533005714417, | |
| "learning_rate": 4.925373134328359e-06, | |
| "loss": 1.9579, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.49033546447753906, | |
| "learning_rate": 4.7761194029850745e-06, | |
| "loss": 2.1126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5522388059701493, | |
| "grad_norm": 0.5822514891624451, | |
| "learning_rate": 4.626865671641791e-06, | |
| "loss": 1.8489, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 0.5790143013000488, | |
| "learning_rate": 4.477611940298508e-06, | |
| "loss": 2.0096, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.582089552238806, | |
| "grad_norm": 0.41039204597473145, | |
| "learning_rate": 4.3283582089552236e-06, | |
| "loss": 1.775, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.820061206817627, | |
| "learning_rate": 4.17910447761194e-06, | |
| "loss": 2.1653, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6119402985074627, | |
| "grad_norm": 0.6350656151771545, | |
| "learning_rate": 4.029850746268657e-06, | |
| "loss": 1.982, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 0.41239652037620544, | |
| "learning_rate": 3.8805970149253735e-06, | |
| "loss": 1.8828, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6417910447761194, | |
| "grad_norm": 0.5652564764022827, | |
| "learning_rate": 3.73134328358209e-06, | |
| "loss": 2.0692, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.6621966361999512, | |
| "learning_rate": 3.582089552238806e-06, | |
| "loss": 2.2952, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.4039974510669708, | |
| "learning_rate": 3.4328358208955225e-06, | |
| "loss": 1.7934, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 0.5079028606414795, | |
| "learning_rate": 3.283582089552239e-06, | |
| "loss": 2.0361, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7014925373134329, | |
| "grad_norm": 0.41614365577697754, | |
| "learning_rate": 3.1343283582089558e-06, | |
| "loss": 1.7775, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.3995169699192047, | |
| "learning_rate": 2.9850746268656716e-06, | |
| "loss": 1.9167, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7313432835820896, | |
| "grad_norm": 0.5954918265342712, | |
| "learning_rate": 2.835820895522388e-06, | |
| "loss": 2.0694, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.5778793692588806, | |
| "learning_rate": 2.686567164179105e-06, | |
| "loss": 2.0297, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7611940298507462, | |
| "grad_norm": 0.5707228183746338, | |
| "learning_rate": 2.537313432835821e-06, | |
| "loss": 2.201, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 0.6407202482223511, | |
| "learning_rate": 2.3880597014925373e-06, | |
| "loss": 2.4394, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7910447761194029, | |
| "grad_norm": 0.3686445355415344, | |
| "learning_rate": 2.238805970149254e-06, | |
| "loss": 2.2426, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8059701492537313, | |
| "grad_norm": 0.4780975580215454, | |
| "learning_rate": 2.08955223880597e-06, | |
| "loss": 1.888, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.5346677303314209, | |
| "learning_rate": 1.9402985074626867e-06, | |
| "loss": 1.9405, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.4024548828601837, | |
| "learning_rate": 1.791044776119403e-06, | |
| "loss": 1.6834, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8507462686567164, | |
| "grad_norm": 0.501626193523407, | |
| "learning_rate": 1.6417910447761196e-06, | |
| "loss": 2.2497, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8656716417910447, | |
| "grad_norm": 0.44980672001838684, | |
| "learning_rate": 1.4925373134328358e-06, | |
| "loss": 1.8196, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8805970149253731, | |
| "grad_norm": 0.8795580863952637, | |
| "learning_rate": 1.3432835820895524e-06, | |
| "loss": 2.1529, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.5534031987190247, | |
| "learning_rate": 1.1940298507462686e-06, | |
| "loss": 2.1861, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9104477611940298, | |
| "grad_norm": 0.3944064676761627, | |
| "learning_rate": 1.044776119402985e-06, | |
| "loss": 1.7992, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9253731343283582, | |
| "grad_norm": 0.3771931231021881, | |
| "learning_rate": 8.955223880597015e-07, | |
| "loss": 1.6866, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9402985074626866, | |
| "grad_norm": 0.5111584067344666, | |
| "learning_rate": 7.462686567164179e-07, | |
| "loss": 1.995, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.5018301606178284, | |
| "learning_rate": 5.970149253731343e-07, | |
| "loss": 1.8922, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.3669991195201874, | |
| "learning_rate": 4.4776119402985074e-07, | |
| "loss": 2.0702, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "grad_norm": 0.45055946707725525, | |
| "learning_rate": 2.9850746268656716e-07, | |
| "loss": 2.0245, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5369859337806702, | |
| "learning_rate": 1.4925373134328358e-07, | |
| "loss": 2.2499, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8387645483016968, | |
| "eval_runtime": 0.8427, | |
| "eval_samples_per_second": 43.907, | |
| "eval_steps_per_second": 5.933, | |
| "step": 67 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3350387805388800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |