| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9935483870967743, | |
| "eval_steps": 500, | |
| "global_step": 348, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 0.815339207649231, | |
| "learning_rate": 2.9938918800982563e-05, | |
| "loss": 0.2134, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 0.7794559597969055, | |
| "learning_rate": 2.975617265898004e-05, | |
| "loss": 0.0692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 0.6546903848648071, | |
| "learning_rate": 2.9453249887788343e-05, | |
| "loss": 0.0594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 0.6819568872451782, | |
| "learning_rate": 2.9032617538884018e-05, | |
| "loss": 0.0546, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.6973971128463745, | |
| "learning_rate": 2.84977013093626e-05, | |
| "loss": 0.0511, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.661968469619751, | |
| "learning_rate": 2.7852857642513838e-05, | |
| "loss": 0.0516, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 0.6463760137557983, | |
| "learning_rate": 2.7103338248251055e-05, | |
| "loss": 0.0464, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 0.982441246509552, | |
| "learning_rate": 2.6255247332346036e-05, | |
| "loss": 0.045, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.8698186874389648, | |
| "learning_rate": 2.531549188280135e-05, | |
| "loss": 0.0478, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 0.5412614345550537, | |
| "learning_rate": 2.4291725418235848e-05, | |
| "loss": 0.0397, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "grad_norm": 0.6799947619438171, | |
| "learning_rate": 2.3192285656405456e-05, | |
| "loss": 0.0362, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 0.7903907895088196, | |
| "learning_rate": 2.2026126610496852e-05, | |
| "loss": 0.0428, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.118279569892473, | |
| "grad_norm": 0.811478316783905, | |
| "learning_rate": 2.0802745666212592e-05, | |
| "loss": 0.0334, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2043010752688172, | |
| "grad_norm": 0.6911829710006714, | |
| "learning_rate": 1.953210623354359e-05, | |
| "loss": 0.035, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.6067230105400085, | |
| "learning_rate": 1.8224556603165363e-05, | |
| "loss": 0.0352, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3763440860215055, | |
| "grad_norm": 0.6847725510597229, | |
| "learning_rate": 1.689074566830434e-05, | |
| "loss": 0.0364, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.4623655913978495, | |
| "grad_norm": 0.9747119545936584, | |
| "learning_rate": 1.5541536198449044e-05, | |
| "loss": 0.0332, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 0.48447030782699585, | |
| "learning_rate": 1.4187916371218739e-05, | |
| "loss": 0.0315, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6344086021505375, | |
| "grad_norm": 0.5664235949516296, | |
| "learning_rate": 1.2840910282888211e-05, | |
| "loss": 0.0312, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 0.5801066160202026, | |
| "learning_rate": 1.1511488166385349e-05, | |
| "loss": 0.0324, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 0.7894909977912903, | |
| "learning_rate": 1.0210477047960303e-05, | |
| "loss": 0.0326, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.89247311827957, | |
| "grad_norm": 0.4664723575115204, | |
| "learning_rate": 8.948472570152874e-06, | |
| "loss": 0.0319, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.978494623655914, | |
| "grad_norm": 1.0112488269805908, | |
| "learning_rate": 7.735752699185711e-06, | |
| "loss": 0.0319, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 0.37232428789138794, | |
| "learning_rate": 6.582194019564266e-06, | |
| "loss": 0.0247, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 0.7465298771858215, | |
| "learning_rate": 5.497191297593647e-06, | |
| "loss": 0.0276, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.236559139784946, | |
| "grad_norm": 0.7070090174674988, | |
| "learning_rate": 4.4895809688998655e-06, | |
| "loss": 0.0259, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.3225806451612905, | |
| "grad_norm": 0.48493513464927673, | |
| "learning_rate": 3.567569173085455e-06, | |
| "loss": 0.0213, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.4086021505376345, | |
| "grad_norm": 1.0859829187393188, | |
| "learning_rate": 2.7386649216166233e-06, | |
| "loss": 0.0224, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.4946236559139785, | |
| "grad_norm": 1.0049951076507568, | |
| "learning_rate": 2.0096189432334194e-06, | |
| "loss": 0.0253, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 0.5058858394622803, | |
| "learning_rate": 1.3863687049356465e-06, | |
| "loss": 0.0241, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.7774279117584229, | |
| "learning_rate": 8.7399005630238e-07, | |
| "loss": 0.0268, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.752688172043011, | |
| "grad_norm": 0.5623956918716431, | |
| "learning_rate": 4.766558909615504e-07, | |
| "loss": 0.0222, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.838709677419355, | |
| "grad_norm": 0.6706695556640625, | |
| "learning_rate": 1.9760216187710788e-07, | |
| "loss": 0.0265, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.924731182795699, | |
| "grad_norm": 0.5286621451377869, | |
| "learning_rate": 3.910152723075322e-08, | |
| "loss": 0.0242, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.9935483870967743, | |
| "step": 348, | |
| "total_flos": 1.633496428047237e+17, | |
| "train_loss": 0.0405226307439393, | |
| "train_runtime": 3560.4547, | |
| "train_samples_per_second": 3.131, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 348, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.633496428047237e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |