| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9973661106233538, | |
| "eval_steps": 500, | |
| "global_step": 284, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03511852502194908, | |
| "grad_norm": 194.98139599033956, | |
| "learning_rate": 1.724137931034483e-06, | |
| "loss": 2.1612, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07023705004389816, | |
| "grad_norm": 11.574681452175845, | |
| "learning_rate": 3.448275862068966e-06, | |
| "loss": 1.5263, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10535557506584724, | |
| "grad_norm": 4.620556133093483, | |
| "learning_rate": 4.999810275287077e-06, | |
| "loss": 1.1514, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14047410008779632, | |
| "grad_norm": 4.8618300415248425, | |
| "learning_rate": 4.977078132728901e-06, | |
| "loss": 1.0009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17559262510974538, | |
| "grad_norm": 5.039664200269418, | |
| "learning_rate": 4.916796010672969e-06, | |
| "loss": 0.9159, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21071115013169447, | |
| "grad_norm": 4.677695184320373, | |
| "learning_rate": 4.819877724641437e-06, | |
| "loss": 0.8819, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24582967515364354, | |
| "grad_norm": 4.476208091052348, | |
| "learning_rate": 4.687792457057482e-06, | |
| "loss": 0.8205, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28094820017559263, | |
| "grad_norm": 4.076277674081994, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.8138, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3160667251975417, | |
| "grad_norm": 3.706466470362564, | |
| "learning_rate": 4.326632832396733e-06, | |
| "loss": 0.7546, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35118525021949076, | |
| "grad_norm": 3.807926746840706, | |
| "learning_rate": 4.1030332870839466e-06, | |
| "loss": 0.7552, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3863037752414399, | |
| "grad_norm": 4.448525410750735, | |
| "learning_rate": 3.855133391181124e-06, | |
| "loss": 0.742, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.42142230026338895, | |
| "grad_norm": 3.9020262955384557, | |
| "learning_rate": 3.586691054414913e-06, | |
| "loss": 0.7188, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.456540825285338, | |
| "grad_norm": 4.436756217145944, | |
| "learning_rate": 3.3017755889756382e-06, | |
| "loss": 0.7112, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4916593503072871, | |
| "grad_norm": 3.3937208218898154, | |
| "learning_rate": 3.0047060228925256e-06, | |
| "loss": 0.6893, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5267778753292361, | |
| "grad_norm": 5.294699703871525, | |
| "learning_rate": 2.699985627971354e-06, | |
| "loss": 0.6668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5618964003511853, | |
| "grad_norm": 4.373298006073623, | |
| "learning_rate": 2.392233654784262e-06, | |
| "loss": 0.6659, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 4.608979891075067, | |
| "learning_rate": 2.086115309539675e-06, | |
| "loss": 0.643, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6321334503950834, | |
| "grad_norm": 5.305060414443979, | |
| "learning_rate": 1.7862710343116451e-06, | |
| "loss": 0.6655, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6672519754170325, | |
| "grad_norm": 3.420875543474142, | |
| "learning_rate": 1.4972461626682033e-06, | |
| "loss": 0.6251, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7023705004389815, | |
| "grad_norm": 4.603437178273803, | |
| "learning_rate": 1.2234220170477332e-06, | |
| "loss": 0.6449, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7374890254609306, | |
| "grad_norm": 5.3351263316177215, | |
| "learning_rate": 9.689494923768756e-07, | |
| "loss": 0.6284, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7726075504828798, | |
| "grad_norm": 3.607022821385861, | |
| "learning_rate": 7.376861327346325e-07, | |
| "loss": 0.6072, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8077260755048288, | |
| "grad_norm": 4.795667171198547, | |
| "learning_rate": 5.33137654916292e-07, | |
| "loss": 0.6187, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8428446005267779, | |
| "grad_norm": 3.9213724314825216, | |
| "learning_rate": 3.5840480534034355e-07, | |
| "loss": 0.6145, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8779631255487269, | |
| "grad_norm": 5.451274818264296, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.6012, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.913081650570676, | |
| "grad_norm": 4.312276909206807, | |
| "learning_rate": 1.0848895124889819e-07, | |
| "loss": 0.6184, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9482001755926251, | |
| "grad_norm": 4.611522839692978, | |
| "learning_rate": 3.709441633123367e-08, | |
| "loss": 0.5952, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9833187006145742, | |
| "grad_norm": 6.192176760901921, | |
| "learning_rate": 3.035019514275317e-09, | |
| "loss": 0.5973, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9973661106233538, | |
| "step": 284, | |
| "total_flos": 1.1831516853383987e+17, | |
| "train_loss": 0.7974992327287164, | |
| "train_runtime": 7644.4468, | |
| "train_samples_per_second": 4.767, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 284, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.1831516853383987e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |