| { | |
| "best_metric": 0.9440848231315613, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13183915622940012, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026367831245880024, | |
| "grad_norm": 2.840853452682495, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026367831245880024, | |
| "eval_loss": 1.734526515007019, | |
| "eval_runtime": 124.8601, | |
| "eval_samples_per_second": 20.463, | |
| "eval_steps_per_second": 2.563, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005273566249176005, | |
| "grad_norm": 3.5962321758270264, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3219, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007910349373764008, | |
| "grad_norm": 3.732879400253296, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.3727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01054713249835201, | |
| "grad_norm": 4.844780921936035, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3763, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013183915622940013, | |
| "grad_norm": 6.486969470977783, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3032, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015820698747528016, | |
| "grad_norm": 6.895390033721924, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2952, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01845748187211602, | |
| "grad_norm": 7.021610260009766, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.2004, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02109426499670402, | |
| "grad_norm": 8.559478759765625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1234, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023731048121292023, | |
| "grad_norm": 9.841951370239258, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1619, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026367831245880026, | |
| "grad_norm": 9.573534965515137, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0597, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02900461437046803, | |
| "grad_norm": 10.767778396606445, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0368, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03164139749505603, | |
| "grad_norm": 17.224395751953125, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034278180619644036, | |
| "grad_norm": 13.874789237976074, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3775, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03691496374423204, | |
| "grad_norm": 6.476630687713623, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0851, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03955174686882004, | |
| "grad_norm": 6.1668477058410645, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1948, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04218852999340804, | |
| "grad_norm": 5.449673652648926, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1321, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04482531311799604, | |
| "grad_norm": 4.996151447296143, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.047462096242584045, | |
| "grad_norm": 4.24849271774292, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1233, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05009887936717205, | |
| "grad_norm": 4.225758075714111, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0395, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05273566249176005, | |
| "grad_norm": 4.2424845695495605, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055372445616348055, | |
| "grad_norm": 4.8217926025390625, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9152, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05800922874093606, | |
| "grad_norm": 4.882667541503906, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9311, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06064601186552406, | |
| "grad_norm": 5.357641696929932, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7931, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06328279499011207, | |
| "grad_norm": 8.169944763183594, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7887, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06591957811470006, | |
| "grad_norm": 17.7220516204834, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9647, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06591957811470006, | |
| "eval_loss": 0.9688600897789001, | |
| "eval_runtime": 125.1137, | |
| "eval_samples_per_second": 20.421, | |
| "eval_steps_per_second": 2.558, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06855636123928807, | |
| "grad_norm": 1.7932987213134766, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9886, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07119314436387607, | |
| "grad_norm": 2.4545319080352783, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1235, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07382992748846408, | |
| "grad_norm": 2.206700325012207, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.088, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07646671061305207, | |
| "grad_norm": 2.3057193756103516, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0664, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07910349373764008, | |
| "grad_norm": 2.116140842437744, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.0877, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08174027686222808, | |
| "grad_norm": 1.8481568098068237, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0048, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08437705998681608, | |
| "grad_norm": 2.556462287902832, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0342, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08701384311140409, | |
| "grad_norm": 2.689141035079956, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.929, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08965062623599208, | |
| "grad_norm": 3.946350336074829, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8648, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0922874093605801, | |
| "grad_norm": 3.916400671005249, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7134, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09492419248516809, | |
| "grad_norm": 5.732182502746582, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7544, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 8.657495498657227, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8536, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1001977587343441, | |
| "grad_norm": 9.490399360656738, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0348, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10283454185893211, | |
| "grad_norm": 1.175460934638977, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0276, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1054713249835201, | |
| "grad_norm": 1.179926872253418, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0622, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 1.2721707820892334, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0583, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11074489123269611, | |
| "grad_norm": 1.4001848697662354, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0218, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1133816743572841, | |
| "grad_norm": 1.6390767097473145, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0694, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11601845748187212, | |
| "grad_norm": 2.0891051292419434, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.02, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11865524060646011, | |
| "grad_norm": 2.4620070457458496, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9383, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12129202373104812, | |
| "grad_norm": 2.9754490852355957, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9056, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12392880685563612, | |
| "grad_norm": 4.956353664398193, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8469, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12656558998022413, | |
| "grad_norm": 4.547539234161377, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8408, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12920237310481214, | |
| "grad_norm": 6.952060222625732, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7187, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13183915622940012, | |
| "grad_norm": 14.889754295349121, | |
| "learning_rate": 0.0, | |
| "loss": 0.9862, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13183915622940012, | |
| "eval_loss": 0.9440848231315613, | |
| "eval_runtime": 125.0915, | |
| "eval_samples_per_second": 20.425, | |
| "eval_steps_per_second": 2.558, | |
| "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": 1.0952750720352256e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |