| { | |
| "best_metric": 0.420650452375412, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.016949152542373, | |
| "eval_steps": 50, | |
| "global_step": 89, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 0.6644117832183838, | |
| "learning_rate": 1.0500000000000001e-05, | |
| "loss": 1.2728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "eval_loss": 1.325829029083252, | |
| "eval_runtime": 0.8828, | |
| "eval_samples_per_second": 450.827, | |
| "eval_steps_per_second": 14.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 0.7109208106994629, | |
| "learning_rate": 2.1000000000000002e-05, | |
| "loss": 1.3144, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 0.715027928352356, | |
| "learning_rate": 3.15e-05, | |
| "loss": 1.3375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.7128281593322754, | |
| "learning_rate": 4.2000000000000004e-05, | |
| "loss": 1.326, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.719323992729187, | |
| "learning_rate": 5.25e-05, | |
| "loss": 1.3235, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 0.7542026042938232, | |
| "learning_rate": 6.3e-05, | |
| "loss": 1.348, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23728813559322035, | |
| "grad_norm": 0.6400342583656311, | |
| "learning_rate": 7.35e-05, | |
| "loss": 1.2302, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.6019027829170227, | |
| "learning_rate": 8.400000000000001e-05, | |
| "loss": 1.1686, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3050847457627119, | |
| "grad_norm": 0.5761123299598694, | |
| "learning_rate": 9.45e-05, | |
| "loss": 1.0889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 0.5195322036743164, | |
| "learning_rate": 0.000105, | |
| "loss": 1.0254, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3728813559322034, | |
| "grad_norm": 0.5309574604034424, | |
| "learning_rate": 0.00010495849335443335, | |
| "loss": 0.9455, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.5846827030181885, | |
| "learning_rate": 0.00010483403904827154, | |
| "loss": 0.886, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4406779661016949, | |
| "grad_norm": 0.5385061502456665, | |
| "learning_rate": 0.0001046268338693536, | |
| "loss": 0.8475, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4745762711864407, | |
| "grad_norm": 0.34226641058921814, | |
| "learning_rate": 0.0001043372054516575, | |
| "loss": 0.7105, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 0.5354804992675781, | |
| "learning_rate": 0.0001039656117572434, | |
| "loss": 0.681, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.7758191227912903, | |
| "learning_rate": 0.00010351264035212153, | |
| "loss": 0.6268, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.576271186440678, | |
| "grad_norm": 0.4772910475730896, | |
| "learning_rate": 0.00010297900747718958, | |
| "loss": 0.6068, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6101694915254238, | |
| "grad_norm": 0.39711692929267883, | |
| "learning_rate": 0.0001023655569157086, | |
| "loss": 0.5645, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6440677966101694, | |
| "grad_norm": 0.6140002608299255, | |
| "learning_rate": 0.00010167325865910821, | |
| "loss": 0.5802, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.24760758876800537, | |
| "learning_rate": 0.00010090320737323084, | |
| "loss": 0.5746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.711864406779661, | |
| "grad_norm": 0.20960871875286102, | |
| "learning_rate": 0.00010005662066743998, | |
| "loss": 0.5206, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7457627118644068, | |
| "grad_norm": 0.20185863971710205, | |
| "learning_rate": 9.913483716932943e-05, | |
| "loss": 0.489, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7796610169491526, | |
| "grad_norm": 0.1934608370065689, | |
| "learning_rate": 9.81393144080781e-05, | |
| "loss": 0.4544, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.2110586315393448, | |
| "learning_rate": 9.707162650979662e-05, | |
| "loss": 0.4844, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 0.4501343071460724, | |
| "learning_rate": 9.593346170851051e-05, | |
| "loss": 0.4708, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8813559322033898, | |
| "grad_norm": 0.8199589848518372, | |
| "learning_rate": 9.472661967671516e-05, | |
| "loss": 0.5096, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9152542372881356, | |
| "grad_norm": 0.42125675082206726, | |
| "learning_rate": 9.345300867972365e-05, | |
| "loss": 0.4668, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.1957239806652069, | |
| "learning_rate": 9.211464255830708e-05, | |
| "loss": 0.4379, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9830508474576272, | |
| "grad_norm": 0.46031802892684937, | |
| "learning_rate": 9.071363754439846e-05, | |
| "loss": 0.4519, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 0.7945327758789062, | |
| "learning_rate": 8.925220891489483e-05, | |
| "loss": 0.7032, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0508474576271187, | |
| "grad_norm": 0.13100884854793549, | |
| "learning_rate": 8.773266748884944e-05, | |
| "loss": 0.4579, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.3228919804096222, | |
| "learning_rate": 8.615741597359156e-05, | |
| "loss": 0.4398, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.11864406779661, | |
| "grad_norm": 0.35424545407295227, | |
| "learning_rate": 8.452894516555253e-05, | |
| "loss": 0.4465, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.152542372881356, | |
| "grad_norm": 0.22786343097686768, | |
| "learning_rate": 8.284983001180455e-05, | |
| "loss": 0.4068, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1864406779661016, | |
| "grad_norm": 0.16856859624385834, | |
| "learning_rate": 8.112272553854005e-05, | |
| "loss": 0.4109, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.29634520411491394, | |
| "learning_rate": 7.935036265292968e-05, | |
| "loss": 0.4125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2542372881355932, | |
| "grad_norm": 0.2798968553543091, | |
| "learning_rate": 7.753554382499657e-05, | |
| "loss": 0.4788, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.288135593220339, | |
| "grad_norm": 0.11876481026411057, | |
| "learning_rate": 7.568113865633538e-05, | |
| "loss": 0.4387, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3220338983050848, | |
| "grad_norm": 0.08868218213319778, | |
| "learning_rate": 7.379007934268217e-05, | |
| "loss": 0.4091, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.22629207372665405, | |
| "learning_rate": 7.18653560375104e-05, | |
| "loss": 0.4052, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3898305084745763, | |
| "grad_norm": 0.3182011842727661, | |
| "learning_rate": 6.991001212398357e-05, | |
| "loss": 0.4155, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.423728813559322, | |
| "grad_norm": 0.48684900999069214, | |
| "learning_rate": 6.792713940274086e-05, | |
| "loss": 0.3487, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.457627118644068, | |
| "grad_norm": 0.7674040198326111, | |
| "learning_rate": 6.591987320312492e-05, | |
| "loss": 0.5046, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.5276405811309814, | |
| "learning_rate": 6.38913874255817e-05, | |
| "loss": 0.4545, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5254237288135593, | |
| "grad_norm": 0.12091302126646042, | |
| "learning_rate": 6.184488952307141e-05, | |
| "loss": 0.4387, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.559322033898305, | |
| "grad_norm": 0.17123517394065857, | |
| "learning_rate": 5.9783615429426096e-05, | |
| "loss": 0.4108, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5932203389830508, | |
| "grad_norm": 0.4185921251773834, | |
| "learning_rate": 5.7710824442673244e-05, | |
| "loss": 0.407, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.5745218992233276, | |
| "learning_rate": 5.562979407141554e-05, | |
| "loss": 0.4002, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6610169491525424, | |
| "grad_norm": 0.09879444539546967, | |
| "learning_rate": 5.3543814852416186e-05, | |
| "loss": 0.4583, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 0.29606881737709045, | |
| "learning_rate": 5.145618514758382e-05, | |
| "loss": 0.4399, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "eval_loss": 0.420650452375412, | |
| "eval_runtime": 1.3705, | |
| "eval_samples_per_second": 290.407, | |
| "eval_steps_per_second": 9.486, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7288135593220337, | |
| "grad_norm": 0.2548205256462097, | |
| "learning_rate": 4.9370205928584464e-05, | |
| "loss": 0.4107, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 0.24160364270210266, | |
| "learning_rate": 4.728917555732678e-05, | |
| "loss": 0.4312, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.7966101694915255, | |
| "grad_norm": 0.06337052583694458, | |
| "learning_rate": 4.521638457057392e-05, | |
| "loss": 0.4052, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.8305084745762712, | |
| "grad_norm": 0.26108115911483765, | |
| "learning_rate": 4.315511047692862e-05, | |
| "loss": 0.3744, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.8644067796610169, | |
| "grad_norm": 0.18919679522514343, | |
| "learning_rate": 4.11086125744183e-05, | |
| "loss": 0.4286, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.24806950986385345, | |
| "learning_rate": 3.908012679687508e-05, | |
| "loss": 0.4354, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.9322033898305084, | |
| "grad_norm": 0.16577477753162384, | |
| "learning_rate": 3.707286059725916e-05, | |
| "loss": 0.4216, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.9661016949152543, | |
| "grad_norm": 0.07274139672517776, | |
| "learning_rate": 3.5089987876016445e-05, | |
| "loss": 0.3875, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.7141322493553162, | |
| "learning_rate": 3.313464396248959e-05, | |
| "loss": 0.5832, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.3955691158771515, | |
| "learning_rate": 3.1209920657317824e-05, | |
| "loss": 0.4751, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.0677966101694913, | |
| "grad_norm": 0.37002313137054443, | |
| "learning_rate": 2.9318861343664646e-05, | |
| "loss": 0.4308, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.1016949152542375, | |
| "grad_norm": 0.15991376340389252, | |
| "learning_rate": 2.746445617500344e-05, | |
| "loss": 0.4005, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.135593220338983, | |
| "grad_norm": 0.08792717754840851, | |
| "learning_rate": 2.5649637347070338e-05, | |
| "loss": 0.3849, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.14280790090560913, | |
| "learning_rate": 2.3877274461459966e-05, | |
| "loss": 0.3955, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.2033898305084745, | |
| "grad_norm": 0.40407660603523254, | |
| "learning_rate": 2.2150169988195452e-05, | |
| "loss": 0.3807, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.23728813559322, | |
| "grad_norm": 0.05895840376615524, | |
| "learning_rate": 2.0471054834447473e-05, | |
| "loss": 0.4356, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.2711864406779663, | |
| "grad_norm": 0.20810866355895996, | |
| "learning_rate": 1.884258402640846e-05, | |
| "loss": 0.4502, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.305084745762712, | |
| "grad_norm": 0.10166915506124496, | |
| "learning_rate": 1.7267332511150564e-05, | |
| "loss": 0.4194, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.3389830508474576, | |
| "grad_norm": 0.059947896748781204, | |
| "learning_rate": 1.5747791085105175e-05, | |
| "loss": 0.4241, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": 0.08675111830234528, | |
| "learning_rate": 1.428636245560156e-05, | |
| "loss": 0.4057, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.406779661016949, | |
| "grad_norm": 0.2886503040790558, | |
| "learning_rate": 1.2885357441692914e-05, | |
| "loss": 0.3794, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.440677966101695, | |
| "grad_norm": 0.11011155694723129, | |
| "learning_rate": 1.154699132027637e-05, | |
| "loss": 0.4224, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.4745762711864407, | |
| "grad_norm": 0.23668210208415985, | |
| "learning_rate": 1.027338032328485e-05, | |
| "loss": 0.4624, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.5084745762711864, | |
| "grad_norm": 0.1450003683567047, | |
| "learning_rate": 9.066538291489505e-06, | |
| "loss": 0.4063, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "grad_norm": 0.0950573980808258, | |
| "learning_rate": 7.928373490203387e-06, | |
| "loss": 0.3955, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.576271186440678, | |
| "grad_norm": 0.1254480630159378, | |
| "learning_rate": 6.86068559192192e-06, | |
| "loss": 0.4191, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.610169491525424, | |
| "grad_norm": 0.2626599371433258, | |
| "learning_rate": 5.865162830670588e-06, | |
| "loss": 0.3544, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.6440677966101696, | |
| "grad_norm": 0.38685888051986694, | |
| "learning_rate": 4.9433793325600285e-06, | |
| "loss": 0.4176, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.6779661016949152, | |
| "grad_norm": 0.3029015362262726, | |
| "learning_rate": 4.096792626769155e-06, | |
| "loss": 0.42, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.17327213287353516, | |
| "learning_rate": 3.326741340891792e-06, | |
| "loss": 0.4334, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.7457627118644066, | |
| "grad_norm": 0.10987525433301926, | |
| "learning_rate": 2.6344430842914096e-06, | |
| "loss": 0.4149, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.7796610169491527, | |
| "grad_norm": 0.12840408086776733, | |
| "learning_rate": 2.020992522810428e-06, | |
| "loss": 0.3796, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.8135593220338984, | |
| "grad_norm": 0.19848020374774933, | |
| "learning_rate": 1.487359647878472e-06, | |
| "loss": 0.3997, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 2.847457627118644, | |
| "grad_norm": 0.4496248960494995, | |
| "learning_rate": 1.0343882427566057e-06, | |
| "loss": 0.3558, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.8813559322033897, | |
| "grad_norm": 0.34108394384384155, | |
| "learning_rate": 6.627945483424986e-07, | |
| "loss": 0.4417, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.915254237288136, | |
| "grad_norm": 0.1465616226196289, | |
| "learning_rate": 3.73166130646396e-07, | |
| "loss": 0.4156, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.9491525423728815, | |
| "grad_norm": 0.08617256581783295, | |
| "learning_rate": 1.6596095172846882e-07, | |
| "loss": 0.4077, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 2.983050847457627, | |
| "grad_norm": 0.2514786422252655, | |
| "learning_rate": 4.1506645566653235e-08, | |
| "loss": 0.4062, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.016949152542373, | |
| "grad_norm": 0.42695701122283936, | |
| "learning_rate": 0.0, | |
| "loss": 0.6505, | |
| "step": 89 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 89, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 4.890642232639488e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |