| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009939369843951893, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019878739687903787, | |
| "grad_norm": 2.414543867111206, | |
| "learning_rate": 5e-06, | |
| "loss": 13.1525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019878739687903787, | |
| "eval_loss": 3.2820167541503906, | |
| "eval_runtime": 75.5342, | |
| "eval_samples_per_second": 28.054, | |
| "eval_steps_per_second": 14.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039757479375807575, | |
| "grad_norm": 2.2050728797912598, | |
| "learning_rate": 1e-05, | |
| "loss": 13.7228, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005963621906371136, | |
| "grad_norm": 2.5719025135040283, | |
| "learning_rate": 1.5e-05, | |
| "loss": 14.2385, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007951495875161515, | |
| "grad_norm": 2.4067375659942627, | |
| "learning_rate": 2e-05, | |
| "loss": 12.0989, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009939369843951894, | |
| "grad_norm": 2.902513027191162, | |
| "learning_rate": 2.5e-05, | |
| "loss": 13.3901, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011927243812742273, | |
| "grad_norm": 2.1985535621643066, | |
| "learning_rate": 3e-05, | |
| "loss": 13.2702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013915117781532651, | |
| "grad_norm": 2.53352427482605, | |
| "learning_rate": 3.5e-05, | |
| "loss": 14.1685, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001590299175032303, | |
| "grad_norm": 2.161381483078003, | |
| "learning_rate": 4e-05, | |
| "loss": 13.6176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017890865719113408, | |
| "grad_norm": 3.1022119522094727, | |
| "learning_rate": 4.5e-05, | |
| "loss": 15.6293, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001987873968790379, | |
| "grad_norm": 2.5830698013305664, | |
| "learning_rate": 5e-05, | |
| "loss": 14.0974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021866613656694165, | |
| "grad_norm": 3.0659115314483643, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 13.9289, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0023854487625484546, | |
| "grad_norm": 3.4623639583587646, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 13.4014, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002584236159427492, | |
| "grad_norm": 2.969046115875244, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 11.8233, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002584236159427492, | |
| "eval_loss": 3.2339165210723877, | |
| "eval_runtime": 74.0873, | |
| "eval_samples_per_second": 28.601, | |
| "eval_steps_per_second": 14.307, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0027830235563065303, | |
| "grad_norm": 3.8479912281036377, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 13.0678, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002981810953185568, | |
| "grad_norm": 4.167858600616455, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 13.3701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003180598350064606, | |
| "grad_norm": 3.2626233100891113, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 12.1547, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0033793857469436436, | |
| "grad_norm": 3.215256690979004, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 12.0763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035781731438226817, | |
| "grad_norm": 5.636133670806885, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 14.4562, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0037769605407017197, | |
| "grad_norm": 3.237064838409424, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 11.2384, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003975747937580758, | |
| "grad_norm": 2.562439203262329, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 12.7868, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004174535334459795, | |
| "grad_norm": 3.096048593521118, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 13.4175, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004373322731338833, | |
| "grad_norm": 3.3756790161132812, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 11.9214, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004572110128217871, | |
| "grad_norm": 3.1741342544555664, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 11.5485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004770897525096909, | |
| "grad_norm": 3.0276670455932617, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 12.0198, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004969684921975946, | |
| "grad_norm": 3.186634063720703, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 11.7737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005168472318854984, | |
| "grad_norm": 2.610215663909912, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 13.0966, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005168472318854984, | |
| "eval_loss": 3.0876364707946777, | |
| "eval_runtime": 74.3552, | |
| "eval_samples_per_second": 28.498, | |
| "eval_steps_per_second": 14.256, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0053672597157340225, | |
| "grad_norm": 3.7985334396362305, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 13.1346, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0055660471126130606, | |
| "grad_norm": 2.66591477394104, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 14.0919, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005764834509492099, | |
| "grad_norm": 3.770318031311035, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 12.0625, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005963621906371136, | |
| "grad_norm": 3.1966161727905273, | |
| "learning_rate": 2.5e-05, | |
| "loss": 13.3168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006162409303250174, | |
| "grad_norm": 3.4274048805236816, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 13.7754, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006361196700129212, | |
| "grad_norm": 3.12906813621521, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 11.2148, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00655998409700825, | |
| "grad_norm": 2.4191653728485107, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 11.369, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006758771493887287, | |
| "grad_norm": 3.0178472995758057, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 11.5686, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006957558890766325, | |
| "grad_norm": 3.4739089012145996, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 13.3696, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007156346287645363, | |
| "grad_norm": 4.477285385131836, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 13.9461, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007355133684524401, | |
| "grad_norm": 3.5579240322113037, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 12.4578, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0075539210814034394, | |
| "grad_norm": 3.2776896953582764, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 11.7642, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007752708478282477, | |
| "grad_norm": 2.8097920417785645, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 11.8259, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007752708478282477, | |
| "eval_loss": 3.0318076610565186, | |
| "eval_runtime": 73.9722, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 14.33, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007951495875161516, | |
| "grad_norm": 3.0600802898406982, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 12.3082, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008150283272040553, | |
| "grad_norm": 2.5751516819000244, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 11.4527, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00834907066891959, | |
| "grad_norm": 3.5589427947998047, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 11.6761, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008547858065798629, | |
| "grad_norm": 4.126989364624023, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 11.1792, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008746645462677666, | |
| "grad_norm": 2.9589903354644775, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 10.7405, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008945432859556703, | |
| "grad_norm": 3.088578224182129, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 12.7116, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009144220256435742, | |
| "grad_norm": 2.728550672531128, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 11.8275, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00934300765331478, | |
| "grad_norm": 3.458416223526001, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 11.6581, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009541795050193818, | |
| "grad_norm": 3.6537857055664062, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 11.4921, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009740582447072856, | |
| "grad_norm": 2.9352803230285645, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 11.6247, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009939369843951893, | |
| "grad_norm": 3.011121988296509, | |
| "learning_rate": 0.0, | |
| "loss": 12.5026, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8184384007962624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |