| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9473684210526314, | |
| "eval_steps": 500, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.16158132255077362, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.1697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.23232614994049072, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.0677, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.6332467794418335, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1094, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.20283149182796478, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.16047315299510956, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1455, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.25979065895080566, | |
| "learning_rate": 6e-06, | |
| "loss": 1.0156, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 0.6384983658790588, | |
| "learning_rate": 7e-06, | |
| "loss": 1.0898, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.2785204350948334, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1775, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.1755814254283905, | |
| "learning_rate": 9e-06, | |
| "loss": 1.1433, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.15501971542835236, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0474, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.20616310834884644, | |
| "learning_rate": 9.975923633360985e-06, | |
| "loss": 1.1525, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.19258467853069305, | |
| "learning_rate": 9.903926402016153e-06, | |
| "loss": 1.1751, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.17972850799560547, | |
| "learning_rate": 9.784701678661045e-06, | |
| "loss": 1.0257, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.1997150182723999, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 1.0966, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.3143484890460968, | |
| "learning_rate": 9.409606321741776e-06, | |
| "loss": 1.0757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1228070175438596, | |
| "grad_norm": 0.22367651760578156, | |
| "learning_rate": 9.157348061512728e-06, | |
| "loss": 1.13, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1929824561403508, | |
| "grad_norm": 0.1776750087738037, | |
| "learning_rate": 8.865052266813686e-06, | |
| "loss": 1.1016, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.20438158512115479, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 1.0679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.17933902144432068, | |
| "learning_rate": 8.171966420818227e-06, | |
| "loss": 1.0008, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4035087719298245, | |
| "grad_norm": 0.380353182554245, | |
| "learning_rate": 7.777851165098012e-06, | |
| "loss": 1.0633, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.2018684595823288, | |
| "learning_rate": 7.3569836841299905e-06, | |
| "loss": 1.0194, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.543859649122807, | |
| "grad_norm": 0.1978669911623001, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 1.0731, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6140350877192984, | |
| "grad_norm": 0.184524804353714, | |
| "learning_rate": 6.451423386272312e-06, | |
| "loss": 1.2068, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.14888142049312592, | |
| "learning_rate": 5.975451610080643e-06, | |
| "loss": 1.0679, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7543859649122808, | |
| "grad_norm": 0.20023825764656067, | |
| "learning_rate": 5.490085701647805e-06, | |
| "loss": 1.1036, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8245614035087718, | |
| "grad_norm": 0.22208057343959808, | |
| "learning_rate": 5e-06, | |
| "loss": 1.1104, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.16171608865261078, | |
| "learning_rate": 4.509914298352197e-06, | |
| "loss": 0.977, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9649122807017543, | |
| "grad_norm": 0.2245715856552124, | |
| "learning_rate": 4.02454838991936e-06, | |
| "loss": 1.1625, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0350877192982457, | |
| "grad_norm": 0.18339820206165314, | |
| "learning_rate": 3.5485766137276894e-06, | |
| "loss": 1.1417, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.19552159309387207, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 1.0769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.175438596491228, | |
| "grad_norm": 0.19760830700397491, | |
| "learning_rate": 2.6430163158700116e-06, | |
| "loss": 1.0757, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.245614035087719, | |
| "grad_norm": 0.22335992753505707, | |
| "learning_rate": 2.2221488349019903e-06, | |
| "loss": 1.019, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 0.212983638048172, | |
| "learning_rate": 1.8280335791817733e-06, | |
| "loss": 1.0443, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.3859649122807016, | |
| "grad_norm": 0.1910511553287506, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 1.1274, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.456140350877193, | |
| "grad_norm": 0.18892121315002441, | |
| "learning_rate": 1.134947733186315e-06, | |
| "loss": 1.0718, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 0.1792212426662445, | |
| "learning_rate": 8.426519384872733e-07, | |
| "loss": 1.0533, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.5964912280701755, | |
| "grad_norm": 0.16358457505702972, | |
| "learning_rate": 5.903936782582253e-07, | |
| "loss": 0.9888, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.17399802803993225, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 0.8769, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 0.1843033879995346, | |
| "learning_rate": 2.152983213389559e-07, | |
| "loss": 1.1146, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.807017543859649, | |
| "grad_norm": 0.2474985271692276, | |
| "learning_rate": 9.607359798384785e-08, | |
| "loss": 1.2433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.8771929824561404, | |
| "grad_norm": 0.2398868203163147, | |
| "learning_rate": 2.4076366639015914e-08, | |
| "loss": 1.0449, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 0.19562916457653046, | |
| "learning_rate": 0.0, | |
| "loss": 1.1418, | |
| "step": 42 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.9136378493952e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |