| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.746268656716418, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 2.403158187866211, | |
| "learning_rate": 4.9998282347929784e-05, | |
| "loss": 3.3875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 2.301710367202759, | |
| "learning_rate": 4.99931296277454e-05, | |
| "loss": 2.9015, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 1.271048665046692, | |
| "learning_rate": 4.998454254749331e-05, | |
| "loss": 2.6229, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 1.069893717765808, | |
| "learning_rate": 4.997252228714279e-05, | |
| "loss": 2.3704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 0.9044906497001648, | |
| "learning_rate": 4.9957070498423854e-05, | |
| "loss": 2.3782, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 0.9635376334190369, | |
| "learning_rate": 4.993818930460026e-05, | |
| "loss": 2.3576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 0.8513979315757751, | |
| "learning_rate": 4.9915881300177725e-05, | |
| "loss": 2.4603, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.845267117023468, | |
| "learning_rate": 4.9890149550547454e-05, | |
| "loss": 2.2033, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 0.6632418036460876, | |
| "learning_rate": 4.98609975915649e-05, | |
| "loss": 2.1851, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 0.6857479810714722, | |
| "learning_rate": 4.982842942906386e-05, | |
| "loss": 2.3592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 0.7204287648200989, | |
| "learning_rate": 4.979244953830608e-05, | |
| "loss": 2.1323, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.6864420175552368, | |
| "learning_rate": 4.9753062863366276e-05, | |
| "loss": 2.2138, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 0.7536088228225708, | |
| "learning_rate": 4.971027481645274e-05, | |
| "loss": 2.2584, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 0.9708526134490967, | |
| "learning_rate": 4.966409127716367e-05, | |
| "loss": 2.2669, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 0.7516190409660339, | |
| "learning_rate": 4.96145185916792e-05, | |
| "loss": 2.2133, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.7864778637886047, | |
| "learning_rate": 4.95615635718894e-05, | |
| "loss": 2.1683, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 0.7846741080284119, | |
| "learning_rate": 4.950523349445824e-05, | |
| "loss": 2.1274, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 0.816838800907135, | |
| "learning_rate": 4.944553609982363e-05, | |
| "loss": 2.2033, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 0.7661916017532349, | |
| "learning_rate": 4.938247959113386e-05, | |
| "loss": 2.1492, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.8964986205101013, | |
| "learning_rate": 4.931607263312032e-05, | |
| "loss": 2.0862, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 0.8603547215461731, | |
| "learning_rate": 4.924632435090696e-05, | |
| "loss": 2.1444, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.8611045479774475, | |
| "learning_rate": 4.917324432875627e-05, | |
| "loss": 2.1202, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 0.9499636888504028, | |
| "learning_rate": 4.909684260875235e-05, | |
| "loss": 2.1285, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.8490393161773682, | |
| "learning_rate": 4.9017129689421e-05, | |
| "loss": 2.236, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 0.9628555178642273, | |
| "learning_rate": 4.893411652428712e-05, | |
| "loss": 2.1219, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 1.1119599342346191, | |
| "learning_rate": 4.8847814520369475e-05, | |
| "loss": 2.2537, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 0.9489665627479553, | |
| "learning_rate": 4.875823553661334e-05, | |
| "loss": 2.1018, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.9434083700180054, | |
| "learning_rate": 4.8665391882260856e-05, | |
| "loss": 2.0809, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 0.8856557607650757, | |
| "learning_rate": 4.856929631515964e-05, | |
| "loss": 2.0807, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 0.8770031929016113, | |
| "learning_rate": 4.846996204000967e-05, | |
| "loss": 2.0843, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 0.8374930620193481, | |
| "learning_rate": 4.8367402706548805e-05, | |
| "loss": 2.1869, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.0829132795333862, | |
| "learning_rate": 4.8261632407677174e-05, | |
| "loss": 2.028, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 0.9735206365585327, | |
| "learning_rate": 4.815266567752059e-05, | |
| "loss": 2.0966, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 1.087944746017456, | |
| "learning_rate": 4.804051748943343e-05, | |
| "loss": 2.0863, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 0.8176729083061218, | |
| "learning_rate": 4.792520325394111e-05, | |
| "loss": 2.1135, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.9173070788383484, | |
| "learning_rate": 4.780673881662242e-05, | |
| "loss": 2.0564, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 0.9463202953338623, | |
| "learning_rate": 4.7685140455932267e-05, | |
| "loss": 2.1579, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 1.149950385093689, | |
| "learning_rate": 4.756042488096471e-05, | |
| "loss": 2.1447, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 0.940965473651886, | |
| "learning_rate": 4.743260922915701e-05, | |
| "loss": 2.0823, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.9384671449661255, | |
| "learning_rate": 4.730171106393466e-05, | |
| "loss": 2.1445, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0891613037461504e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |