| { | |
| "best_metric": 0.30539050698280334, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5810276679841897, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": 11.872172355651855, | |
| "learning_rate": 5e-05, | |
| "loss": 12.4387, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "eval_loss": 13.357632637023926, | |
| "eval_runtime": 14.4094, | |
| "eval_samples_per_second": 14.782, | |
| "eval_steps_per_second": 1.874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": 11.944364547729492, | |
| "learning_rate": 0.0001, | |
| "loss": 12.507, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09486166007905138, | |
| "grad_norm": 12.8162202835083, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.1593, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": 16.479677200317383, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.4681, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15810276679841898, | |
| "grad_norm": 18.85612678527832, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.9714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18972332015810275, | |
| "grad_norm": 13.984392166137695, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9941, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22134387351778656, | |
| "grad_norm": 12.14105224609375, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6446, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25296442687747034, | |
| "grad_norm": 9.039938926696777, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.864, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2845849802371542, | |
| "grad_norm": 27.8907413482666, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5257, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": 19.8009033203125, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9778, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 7.286177158355713, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6243, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3794466403162055, | |
| "grad_norm": 6.214678764343262, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5454, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41106719367588934, | |
| "grad_norm": 6.982287883758545, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5268, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4426877470355731, | |
| "grad_norm": 3.287309169769287, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.446, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4743083003952569, | |
| "grad_norm": 3.5173118114471436, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3369, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5059288537549407, | |
| "grad_norm": 4.333190441131592, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4597, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5375494071146245, | |
| "grad_norm": 3.6946616172790527, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4796, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5691699604743083, | |
| "grad_norm": 8.35791301727295, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5804, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6007905138339921, | |
| "grad_norm": 7.611564636230469, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5395, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": 3.933959484100342, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4075, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6640316205533597, | |
| "grad_norm": 4.536863327026367, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4579, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 3.593409538269043, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3821, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 2.9236183166503906, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3274, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.758893280632411, | |
| "grad_norm": 2.631983518600464, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4191, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "grad_norm": 3.7012534141540527, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4676, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "eval_loss": 0.4884698987007141, | |
| "eval_runtime": 14.4016, | |
| "eval_samples_per_second": 14.79, | |
| "eval_steps_per_second": 1.875, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8221343873517787, | |
| "grad_norm": 4.783064842224121, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4859, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8537549407114624, | |
| "grad_norm": 4.254119873046875, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4126, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8853754940711462, | |
| "grad_norm": 2.574284076690674, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4027, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9169960474308301, | |
| "grad_norm": 2.3480772972106934, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3809, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": 3.1571481227874756, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3606, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9802371541501976, | |
| "grad_norm": 1.2674860954284668, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2237, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0118577075098814, | |
| "grad_norm": 5.936703681945801, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5675, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 2.471944808959961, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.426, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.075098814229249, | |
| "grad_norm": 2.033921957015991, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.346, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1067193675889329, | |
| "grad_norm": 4.3626604080200195, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1383399209486167, | |
| "grad_norm": 4.53350305557251, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3564, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1699604743083003, | |
| "grad_norm": 5.4235334396362305, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3975, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2015810276679841, | |
| "grad_norm": 3.1204311847686768, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2869, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.233201581027668, | |
| "grad_norm": 1.9673261642456055, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1932, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2648221343873518, | |
| "grad_norm": 2.8006744384765625, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.338, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2964426877470356, | |
| "grad_norm": 3.7160491943359375, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4044, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3280632411067192, | |
| "grad_norm": 3.773240566253662, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3934, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.359683794466403, | |
| "grad_norm": 3.711420774459839, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3493, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 1.0964059829711914, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2494, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4229249011857708, | |
| "grad_norm": 1.6332573890686035, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3057, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 1.5418554544448853, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.236, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4861660079051384, | |
| "grad_norm": 1.6449871063232422, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2095, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5177865612648223, | |
| "grad_norm": 3.4557502269744873, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3141, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5494071146245059, | |
| "grad_norm": 2.505995273590088, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4075, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5810276679841897, | |
| "grad_norm": 3.3442437648773193, | |
| "learning_rate": 0.0, | |
| "loss": 0.3577, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5810276679841897, | |
| "eval_loss": 0.30539050698280334, | |
| "eval_runtime": 6.9383, | |
| "eval_samples_per_second": 30.699, | |
| "eval_steps_per_second": 3.891, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |