| { | |
| "best_metric": 6.898910999298096, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3954522985664854, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007909045971329708, | |
| "grad_norm": 0.2183029055595398, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007909045971329708, | |
| "eval_loss": 6.933599472045898, | |
| "eval_runtime": 0.8145, | |
| "eval_samples_per_second": 1045.986, | |
| "eval_steps_per_second": 131.362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015818091942659415, | |
| "grad_norm": 0.2447008341550827, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023727137913989126, | |
| "grad_norm": 0.26231133937835693, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.9349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03163618388531883, | |
| "grad_norm": 0.26859769225120544, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.039545229856648545, | |
| "grad_norm": 0.2877831757068634, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.9325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04745427582797825, | |
| "grad_norm": 0.25767120718955994, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.9257, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 0.30084553360939026, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.9251, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06327236777063766, | |
| "grad_norm": 0.28055256605148315, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.927, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07118141374196738, | |
| "grad_norm": 0.2949598729610443, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.9243, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07909045971329709, | |
| "grad_norm": 0.28188011050224304, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.9206, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08699950568462679, | |
| "grad_norm": 0.31487512588500977, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.9227, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0949085516559565, | |
| "grad_norm": 0.49723970890045166, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.9181, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1028175976272862, | |
| "grad_norm": 0.22263498604297638, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.9185, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 0.24483245611190796, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9209, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11863568956994562, | |
| "grad_norm": 0.22838473320007324, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.922, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12654473554127532, | |
| "grad_norm": 0.2531282305717468, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.9196, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13445378151260504, | |
| "grad_norm": 0.2712913453578949, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.9153, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14236282748393475, | |
| "grad_norm": 0.2731746733188629, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.9146, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15027187345526447, | |
| "grad_norm": 0.269145131111145, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.9098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15818091942659418, | |
| "grad_norm": 0.2949267625808716, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9123, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 0.2600724995136261, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.9079, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17399901136925358, | |
| "grad_norm": 0.30799850821495056, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.9081, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1819080573405833, | |
| "grad_norm": 0.31406766176223755, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.9061, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.189817103311913, | |
| "grad_norm": 0.4619569480419159, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.8987, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1977261492832427, | |
| "grad_norm": 0.5840259790420532, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.8925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1977261492832427, | |
| "eval_loss": 6.906639575958252, | |
| "eval_runtime": 0.8552, | |
| "eval_samples_per_second": 996.205, | |
| "eval_steps_per_second": 125.11, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2056351952545724, | |
| "grad_norm": 0.23898611962795258, | |
| "learning_rate": 5e-05, | |
| "loss": 6.913, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21354424122590213, | |
| "grad_norm": 0.24483507871627808, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.91, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 0.2554374635219574, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.9055, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22936233316856156, | |
| "grad_norm": 0.25451600551605225, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 6.9067, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23727137913989124, | |
| "grad_norm": 0.24806241691112518, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.9056, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24518042511122096, | |
| "grad_norm": 0.2786078453063965, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.9043, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25308947108255064, | |
| "grad_norm": 0.2686275541782379, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9022, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2609985170538804, | |
| "grad_norm": 0.28562965989112854, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.9028, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2689075630252101, | |
| "grad_norm": 0.25754520297050476, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.9048, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 0.29185619950294495, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.9, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2847256549678695, | |
| "grad_norm": 0.36247000098228455, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.8896, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2926347009391992, | |
| "grad_norm": 0.4971422255039215, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.8883, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30054374691052893, | |
| "grad_norm": 0.24295523762702942, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.9051, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3084527928818586, | |
| "grad_norm": 0.23002846539020538, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.9067, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.31636183885318836, | |
| "grad_norm": 0.268537700176239, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.904, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32427088482451805, | |
| "grad_norm": 0.2638684809207916, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.9044, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 0.2719472348690033, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 6.8985, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3400889767671775, | |
| "grad_norm": 0.2753771245479584, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 6.899, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.34799802273850716, | |
| "grad_norm": 0.26771554350852966, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9031, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.35590706870983685, | |
| "grad_norm": 0.2677645981311798, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 6.8983, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3638161146811666, | |
| "grad_norm": 0.2851794362068176, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 6.8982, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3717251606524963, | |
| "grad_norm": 0.29283037781715393, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 6.8942, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.379634206623826, | |
| "grad_norm": 0.3150050938129425, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.8975, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 0.33673837780952454, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.8925, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3954522985664854, | |
| "grad_norm": 0.6036147475242615, | |
| "learning_rate": 0.0, | |
| "loss": 6.8922, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3954522985664854, | |
| "eval_loss": 6.898910999298096, | |
| "eval_runtime": 0.8985, | |
| "eval_samples_per_second": 948.212, | |
| "eval_steps_per_second": 119.083, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5705957376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |