| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7857142857142856, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 0.2544403374195099, | |
| "learning_rate": 9.970149253731344e-05, | |
| "loss": 1.4916, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.17301955819129944, | |
| "learning_rate": 9.91044776119403e-05, | |
| "loss": 0.908, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 0.11398938298225403, | |
| "learning_rate": 9.850746268656717e-05, | |
| "loss": 0.4285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.08889368921518326, | |
| "learning_rate": 9.791044776119404e-05, | |
| "loss": 0.3305, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 0.07145170122385025, | |
| "learning_rate": 9.731343283582089e-05, | |
| "loss": 0.3709, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.08652878552675247, | |
| "learning_rate": 9.671641791044777e-05, | |
| "loss": 0.3822, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0885363519191742, | |
| "learning_rate": 9.611940298507464e-05, | |
| "loss": 0.3799, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.07026822865009308, | |
| "learning_rate": 9.552238805970149e-05, | |
| "loss": 0.4085, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 0.07123386859893799, | |
| "learning_rate": 9.492537313432837e-05, | |
| "loss": 0.2925, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.07839447259902954, | |
| "learning_rate": 9.432835820895522e-05, | |
| "loss": 0.3455, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 0.0755082443356514, | |
| "learning_rate": 9.373134328358209e-05, | |
| "loss": 0.3406, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.0823201835155487, | |
| "learning_rate": 9.313432835820896e-05, | |
| "loss": 0.3259, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 0.08403510600328445, | |
| "learning_rate": 9.253731343283582e-05, | |
| "loss": 0.3017, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.10145727545022964, | |
| "learning_rate": 9.194029850746269e-05, | |
| "loss": 0.3473, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.07516448199748993, | |
| "learning_rate": 9.134328358208956e-05, | |
| "loss": 0.2865, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.07223515212535858, | |
| "learning_rate": 9.074626865671642e-05, | |
| "loss": 0.3045, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 0.07799769937992096, | |
| "learning_rate": 9.014925373134329e-05, | |
| "loss": 0.3306, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.08388201892375946, | |
| "learning_rate": 8.955223880597016e-05, | |
| "loss": 0.309, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 0.0838930755853653, | |
| "learning_rate": 8.895522388059702e-05, | |
| "loss": 0.3356, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.07891852408647537, | |
| "learning_rate": 8.835820895522389e-05, | |
| "loss": 0.3048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.07239601761102676, | |
| "learning_rate": 8.776119402985074e-05, | |
| "loss": 0.3601, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.07549150288105011, | |
| "learning_rate": 8.716417910447762e-05, | |
| "loss": 0.3415, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 0.08595260232686996, | |
| "learning_rate": 8.656716417910447e-05, | |
| "loss": 0.3521, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.08356776833534241, | |
| "learning_rate": 8.597014925373134e-05, | |
| "loss": 0.2898, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 0.07699938863515854, | |
| "learning_rate": 8.537313432835822e-05, | |
| "loss": 0.3038, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.07691926509141922, | |
| "learning_rate": 8.477611940298507e-05, | |
| "loss": 0.3403, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 0.07808340340852737, | |
| "learning_rate": 8.417910447761194e-05, | |
| "loss": 0.3164, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07639653235673904, | |
| "learning_rate": 8.358208955223881e-05, | |
| "loss": 0.2872, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0357142857142858, | |
| "grad_norm": 0.07973363250494003, | |
| "learning_rate": 8.298507462686567e-05, | |
| "loss": 0.3111, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.08878948539495468, | |
| "learning_rate": 8.238805970149254e-05, | |
| "loss": 0.317, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1071428571428572, | |
| "grad_norm": 0.07322458922863007, | |
| "learning_rate": 8.179104477611941e-05, | |
| "loss": 0.2999, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.08571141958236694, | |
| "learning_rate": 8.119402985074627e-05, | |
| "loss": 0.2642, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.1785714285714286, | |
| "grad_norm": 0.10807636380195618, | |
| "learning_rate": 8.059701492537314e-05, | |
| "loss": 0.3024, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.2142857142857142, | |
| "grad_norm": 0.1146746426820755, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2788, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.10096397995948792, | |
| "learning_rate": 7.940298507462687e-05, | |
| "loss": 0.278, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.08820641040802002, | |
| "learning_rate": 7.880597014925374e-05, | |
| "loss": 0.3123, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.3214285714285714, | |
| "grad_norm": 0.09731289744377136, | |
| "learning_rate": 7.820895522388059e-05, | |
| "loss": 0.2962, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.3571428571428572, | |
| "grad_norm": 0.09726134687662125, | |
| "learning_rate": 7.761194029850747e-05, | |
| "loss": 0.2723, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.3928571428571428, | |
| "grad_norm": 0.1366291046142578, | |
| "learning_rate": 7.701492537313433e-05, | |
| "loss": 0.2549, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.09392824023962021, | |
| "learning_rate": 7.641791044776119e-05, | |
| "loss": 0.2785, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4642857142857144, | |
| "grad_norm": 0.10537943243980408, | |
| "learning_rate": 7.582089552238806e-05, | |
| "loss": 0.2692, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.11430277675390244, | |
| "learning_rate": 7.522388059701493e-05, | |
| "loss": 0.2787, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.5357142857142856, | |
| "grad_norm": 0.1093386635184288, | |
| "learning_rate": 7.46268656716418e-05, | |
| "loss": 0.2953, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.10960441827774048, | |
| "learning_rate": 7.402985074626866e-05, | |
| "loss": 0.2906, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 0.11768423765897751, | |
| "learning_rate": 7.343283582089552e-05, | |
| "loss": 0.3433, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": 0.10420206189155579, | |
| "learning_rate": 7.283582089552239e-05, | |
| "loss": 0.2769, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.6785714285714286, | |
| "grad_norm": 0.090525321662426, | |
| "learning_rate": 7.223880597014926e-05, | |
| "loss": 0.2859, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.11874176561832428, | |
| "learning_rate": 7.164179104477612e-05, | |
| "loss": 0.3243, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.08634401112794876, | |
| "learning_rate": 7.104477611940299e-05, | |
| "loss": 0.2398, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 0.10205753147602081, | |
| "learning_rate": 7.044776119402984e-05, | |
| "loss": 0.3725, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1680, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0775686821482496e+17, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |