| { | |
| "best_metric": 1.9367903470993042, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7117437722419929, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014234875444839857, | |
| "grad_norm": 3.987726926803589, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "eval_loss": 5.259206295013428, | |
| "eval_runtime": 22.4487, | |
| "eval_samples_per_second": 21.07, | |
| "eval_steps_per_second": 2.673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028469750889679714, | |
| "grad_norm": 4.957414627075195, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7682, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.042704626334519574, | |
| "grad_norm": 7.8210248947143555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.6014, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "grad_norm": 3.681251287460327, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.3953, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0711743772241993, | |
| "grad_norm": 3.565408706665039, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.7114, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08540925266903915, | |
| "grad_norm": 3.3629918098449707, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.099644128113879, | |
| "grad_norm": 2.452725648880005, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.6223, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11387900355871886, | |
| "grad_norm": 1.597943902015686, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3872, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12811387900355872, | |
| "grad_norm": 1.974350094795227, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1423487544483986, | |
| "grad_norm": 1.6135342121124268, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15658362989323843, | |
| "grad_norm": 1.2702614068984985, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1566, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1708185053380783, | |
| "grad_norm": 1.438144564628601, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.2743, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18505338078291814, | |
| "grad_norm": 1.0113654136657715, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.199288256227758, | |
| "grad_norm": 1.0551536083221436, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8847, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21352313167259787, | |
| "grad_norm": 0.9735572338104248, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7829, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2277580071174377, | |
| "grad_norm": 0.8158897757530212, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7687, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24199288256227758, | |
| "grad_norm": 0.8722501993179321, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8711, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25622775800711745, | |
| "grad_norm": 0.8626693487167358, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.924, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2704626334519573, | |
| "grad_norm": 1.0108652114868164, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0751, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2846975088967972, | |
| "grad_norm": 1.1322764158248901, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.298932384341637, | |
| "grad_norm": 0.7352483868598938, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0273, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.31316725978647686, | |
| "grad_norm": 0.8529086112976074, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.0648, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3274021352313167, | |
| "grad_norm": 0.8490323424339294, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.0244, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3416370106761566, | |
| "grad_norm": 0.8629425764083862, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35587188612099646, | |
| "grad_norm": 0.9219096899032593, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3233, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35587188612099646, | |
| "eval_loss": 1.9761757850646973, | |
| "eval_runtime": 22.5157, | |
| "eval_samples_per_second": 21.008, | |
| "eval_steps_per_second": 2.665, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3701067615658363, | |
| "grad_norm": 0.9723377227783203, | |
| "learning_rate": 5e-05, | |
| "loss": 1.843, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38434163701067614, | |
| "grad_norm": 0.883572518825531, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7424, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.398576512455516, | |
| "grad_norm": 0.7840570211410522, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8546, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4128113879003559, | |
| "grad_norm": 0.8222391605377197, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8556, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.42704626334519574, | |
| "grad_norm": 0.7635681629180908, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4412811387900356, | |
| "grad_norm": 0.863717794418335, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.8744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4555160142348754, | |
| "grad_norm": 0.8257912397384644, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9853, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4697508896797153, | |
| "grad_norm": 0.7964351177215576, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9543, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.48398576512455516, | |
| "grad_norm": 0.8466922044754028, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.9271, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.498220640569395, | |
| "grad_norm": 0.7582820057868958, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.0414, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5124555160142349, | |
| "grad_norm": 0.7933133244514465, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.1764, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5266903914590747, | |
| "grad_norm": 1.0502933263778687, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.2742, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5409252669039146, | |
| "grad_norm": 0.7502277493476868, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0152, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5551601423487544, | |
| "grad_norm": 0.6980727314949036, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.8224, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5693950177935944, | |
| "grad_norm": 0.6420523524284363, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7978, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5836298932384342, | |
| "grad_norm": 0.6218376755714417, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8147, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.597864768683274, | |
| "grad_norm": 0.666327714920044, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.953, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6120996441281139, | |
| "grad_norm": 0.6272517442703247, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.7463, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6263345195729537, | |
| "grad_norm": 0.6795321106910706, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7496, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6405693950177936, | |
| "grad_norm": 0.6798703670501709, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.884, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6548042704626335, | |
| "grad_norm": 0.7086116075515747, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9659, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6690391459074733, | |
| "grad_norm": 0.7290291786193848, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.049, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6832740213523132, | |
| "grad_norm": 0.7203341126441956, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.976, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.697508896797153, | |
| "grad_norm": 0.7907271981239319, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.172, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "grad_norm": 0.8677495718002319, | |
| "learning_rate": 0.0, | |
| "loss": 2.2552, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "eval_loss": 1.9367903470993042, | |
| "eval_runtime": 22.4882, | |
| "eval_samples_per_second": 21.033, | |
| "eval_steps_per_second": 2.668, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |