| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.975903614457831, | |
| "eval_steps": 500, | |
| "global_step": 162, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 2.8209025859832764, | |
| "learning_rate": 5.882352941176471e-07, | |
| "loss": 0.7616, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 2.7777888774871826, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.7427, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 2.813636064529419, | |
| "learning_rate": 1.7647058823529414e-06, | |
| "loss": 0.744, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 2.675807476043701, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 0.7432, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 2.662332773208618, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 0.7608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 2.7628424167633057, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 0.7493, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 2.4826860427856445, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.7395, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 2.5429294109344482, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 0.7363, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 1.8845857381820679, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.7224, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.3661439418792725, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.7079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 1.1115751266479492, | |
| "learning_rate": 6.470588235294119e-06, | |
| "loss": 0.6976, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 0.9719029068946838, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.6877, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 1.5337737798690796, | |
| "learning_rate": 7.647058823529411e-06, | |
| "loss": 0.6651, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 1.6938939094543457, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.6765, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 1.6760753393173218, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.6804, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 1.392161250114441, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.6565, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6144578313253012, | |
| "grad_norm": 1.2017204761505127, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6346, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6506024096385542, | |
| "grad_norm": 1.2758034467697144, | |
| "learning_rate": 9.99882649009242e-06, | |
| "loss": 0.669, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6867469879518072, | |
| "grad_norm": 0.9672208428382874, | |
| "learning_rate": 9.995306511219885e-06, | |
| "loss": 0.6494, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.7265082597732544, | |
| "learning_rate": 9.989441715674422e-06, | |
| "loss": 0.6397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7590361445783133, | |
| "grad_norm": 0.605043351650238, | |
| "learning_rate": 9.981234856414306e-06, | |
| "loss": 0.645, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7951807228915663, | |
| "grad_norm": 0.6995558142662048, | |
| "learning_rate": 9.970689785771798e-06, | |
| "loss": 0.6516, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8313253012048193, | |
| "grad_norm": 0.7498184442520142, | |
| "learning_rate": 9.957811453644848e-06, | |
| "loss": 0.6296, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.7003129124641418, | |
| "learning_rate": 9.942605905173593e-06, | |
| "loss": 0.6335, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.721664309501648, | |
| "learning_rate": 9.925080277902743e-06, | |
| "loss": 0.641, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9397590361445783, | |
| "grad_norm": 0.5983788371086121, | |
| "learning_rate": 9.905242798431196e-06, | |
| "loss": 0.6236, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9759036144578314, | |
| "grad_norm": 0.5488296747207642, | |
| "learning_rate": 9.883102778550434e-06, | |
| "loss": 0.6434, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.036144578313253, | |
| "grad_norm": 1.0052872896194458, | |
| "learning_rate": 9.858670610873528e-06, | |
| "loss": 1.2338, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.072289156626506, | |
| "grad_norm": 0.4585392475128174, | |
| "learning_rate": 9.831957763956814e-06, | |
| "loss": 0.5655, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.108433734939759, | |
| "grad_norm": 0.5069596767425537, | |
| "learning_rate": 9.802976776916493e-06, | |
| "loss": 0.5669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.144578313253012, | |
| "grad_norm": 0.5148389935493469, | |
| "learning_rate": 9.771741253542742e-06, | |
| "loss": 0.5765, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.180722891566265, | |
| "grad_norm": 0.5303863883018494, | |
| "learning_rate": 9.738265855914014e-06, | |
| "loss": 0.5701, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.216867469879518, | |
| "grad_norm": 0.5023403763771057, | |
| "learning_rate": 9.70256629751462e-06, | |
| "loss": 0.5825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.37979233264923096, | |
| "learning_rate": 9.664659335858755e-06, | |
| "loss": 0.5575, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2891566265060241, | |
| "grad_norm": 0.46085426211357117, | |
| "learning_rate": 9.624562764624445e-06, | |
| "loss": 0.5377, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3253012048192772, | |
| "grad_norm": 0.5160898566246033, | |
| "learning_rate": 9.582295405301131e-06, | |
| "loss": 0.5801, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3614457831325302, | |
| "grad_norm": 0.4731687903404236, | |
| "learning_rate": 9.537877098354787e-06, | |
| "loss": 0.5462, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3975903614457832, | |
| "grad_norm": 0.37070778012275696, | |
| "learning_rate": 9.491328693914723e-06, | |
| "loss": 0.5689, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4337349397590362, | |
| "grad_norm": 0.3897731900215149, | |
| "learning_rate": 9.442672041986456e-06, | |
| "loss": 0.5429, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4698795180722892, | |
| "grad_norm": 0.3995729684829712, | |
| "learning_rate": 9.391929982195233e-06, | |
| "loss": 0.5554, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5060240963855422, | |
| "grad_norm": 0.4201774299144745, | |
| "learning_rate": 9.339126333065008e-06, | |
| "loss": 0.5513, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.4044627249240875, | |
| "learning_rate": 9.284285880837947e-06, | |
| "loss": 0.5419, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5783132530120483, | |
| "grad_norm": 0.38670021295547485, | |
| "learning_rate": 9.22743436783966e-06, | |
| "loss": 0.5504, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6144578313253013, | |
| "grad_norm": 0.3694572150707245, | |
| "learning_rate": 9.168598480395653e-06, | |
| "loss": 0.5435, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6506024096385543, | |
| "grad_norm": 0.37926754355430603, | |
| "learning_rate": 9.107805836304658e-06, | |
| "loss": 0.5437, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6867469879518073, | |
| "grad_norm": 0.33715763688087463, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.5485, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7228915662650603, | |
| "grad_norm": 0.373822420835495, | |
| "learning_rate": 8.98046532852822e-06, | |
| "loss": 0.5498, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7590361445783134, | |
| "grad_norm": 0.37885019183158875, | |
| "learning_rate": 8.91397723898178e-06, | |
| "loss": 0.54, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7951807228915664, | |
| "grad_norm": 0.3432829976081848, | |
| "learning_rate": 8.845651913008145e-06, | |
| "loss": 0.5558, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8313253012048194, | |
| "grad_norm": 0.34714093804359436, | |
| "learning_rate": 8.775521422786104e-06, | |
| "loss": 0.5356, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8674698795180724, | |
| "grad_norm": 0.34533223509788513, | |
| "learning_rate": 8.703618687845697e-06, | |
| "loss": 0.532, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.9036144578313254, | |
| "grad_norm": 0.33921247720718384, | |
| "learning_rate": 8.629977459615655e-06, | |
| "loss": 0.5414, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9397590361445785, | |
| "grad_norm": 0.3631800413131714, | |
| "learning_rate": 8.554632305580355e-06, | |
| "loss": 0.5625, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.9759036144578315, | |
| "grad_norm": 0.3610064685344696, | |
| "learning_rate": 8.477618593053693e-06, | |
| "loss": 0.5483, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.036144578313253, | |
| "grad_norm": 0.6465901136398315, | |
| "learning_rate": 8.39897247257754e-06, | |
| "loss": 0.9698, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.072289156626506, | |
| "grad_norm": 0.4273433983325958, | |
| "learning_rate": 8.318730860952523e-06, | |
| "loss": 0.4964, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.108433734939759, | |
| "grad_norm": 0.3399488031864166, | |
| "learning_rate": 8.23693142390914e-06, | |
| "loss": 0.468, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.144578313253012, | |
| "grad_norm": 0.36461561918258667, | |
| "learning_rate": 8.153612558427311e-06, | |
| "loss": 0.4674, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.180722891566265, | |
| "grad_norm": 0.41741812229156494, | |
| "learning_rate": 8.068813374712689e-06, | |
| "loss": 0.46, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.216867469879518, | |
| "grad_norm": 0.539730966091156, | |
| "learning_rate": 7.982573677838172e-06, | |
| "loss": 0.4591, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.253012048192771, | |
| "grad_norm": 0.3364892303943634, | |
| "learning_rate": 7.894933949059245e-06, | |
| "loss": 0.4656, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.289156626506024, | |
| "grad_norm": 0.3342113196849823, | |
| "learning_rate": 7.805935326811913e-06, | |
| "loss": 0.4669, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.325301204819277, | |
| "grad_norm": 0.4477402865886688, | |
| "learning_rate": 7.715619587402165e-06, | |
| "loss": 0.4774, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.36144578313253, | |
| "grad_norm": 0.4410865902900696, | |
| "learning_rate": 7.624029125396004e-06, | |
| "loss": 0.4386, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.397590361445783, | |
| "grad_norm": 0.3660714328289032, | |
| "learning_rate": 7.53120693371927e-06, | |
| "loss": 0.4412, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.433734939759036, | |
| "grad_norm": 0.3396703898906708, | |
| "learning_rate": 7.437196583476597e-06, | |
| "loss": 0.4442, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.4698795180722892, | |
| "grad_norm": 0.352255254983902, | |
| "learning_rate": 7.342042203498952e-06, | |
| "loss": 0.4664, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.5060240963855422, | |
| "grad_norm": 0.39523279666900635, | |
| "learning_rate": 7.245788459629397e-06, | |
| "loss": 0.4386, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.5421686746987953, | |
| "grad_norm": 0.42037248611450195, | |
| "learning_rate": 7.148480533756759e-06, | |
| "loss": 0.4406, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.5783132530120483, | |
| "grad_norm": 0.3557772636413574, | |
| "learning_rate": 7.050164102607081e-06, | |
| "loss": 0.4568, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.6144578313253013, | |
| "grad_norm": 0.3083244562149048, | |
| "learning_rate": 6.950885316302773e-06, | |
| "loss": 0.4193, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.6506024096385543, | |
| "grad_norm": 0.3360963463783264, | |
| "learning_rate": 6.850690776699574e-06, | |
| "loss": 0.4265, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.6867469879518073, | |
| "grad_norm": 0.3748219907283783, | |
| "learning_rate": 6.749627515511443e-06, | |
| "loss": 0.4544, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.7228915662650603, | |
| "grad_norm": 0.3778473436832428, | |
| "learning_rate": 6.647742972233703e-06, | |
| "loss": 0.435, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.7590361445783134, | |
| "grad_norm": 0.3551197946071625, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.4466, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.7951807228915664, | |
| "grad_norm": 0.35094714164733887, | |
| "learning_rate": 6.441701702506755e-06, | |
| "loss": 0.4189, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.8313253012048194, | |
| "grad_norm": 0.32956451177597046, | |
| "learning_rate": 6.337641692646106e-06, | |
| "loss": 0.419, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.8674698795180724, | |
| "grad_norm": 0.36045852303504944, | |
| "learning_rate": 6.2329537884738115e-06, | |
| "loss": 0.4361, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.9036144578313254, | |
| "grad_norm": 0.3273407816886902, | |
| "learning_rate": 6.127687130906972e-06, | |
| "loss": 0.4588, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.9397590361445785, | |
| "grad_norm": 0.3656028211116791, | |
| "learning_rate": 6.021891132531825e-06, | |
| "loss": 0.4462, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.9759036144578315, | |
| "grad_norm": 0.35299059748649597, | |
| "learning_rate": 5.915615454409281e-06, | |
| "loss": 0.4599, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.036144578313253, | |
| "grad_norm": 0.5190630555152893, | |
| "learning_rate": 5.808909982763825e-06, | |
| "loss": 0.8681, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.072289156626506, | |
| "grad_norm": 0.40097540616989136, | |
| "learning_rate": 5.701824805566722e-06, | |
| "loss": 0.387, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.108433734939759, | |
| "grad_norm": 0.37181419134140015, | |
| "learning_rate": 5.594410189024533e-06, | |
| "loss": 0.3973, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.144578313253012, | |
| "grad_norm": 0.36105361580848694, | |
| "learning_rate": 5.4867165539839505e-06, | |
| "loss": 0.3706, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.180722891566265, | |
| "grad_norm": 0.32242706418037415, | |
| "learning_rate": 5.378794452264053e-06, | |
| "loss": 0.3647, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.216867469879518, | |
| "grad_norm": 0.37879207730293274, | |
| "learning_rate": 5.270694542927089e-06, | |
| "loss": 0.3568, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.253012048192771, | |
| "grad_norm": 0.3197579085826874, | |
| "learning_rate": 5.1624675684989035e-06, | |
| "loss": 0.3512, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.289156626506024, | |
| "grad_norm": 0.3562887907028198, | |
| "learning_rate": 5.054164331150199e-06, | |
| "loss": 0.3561, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.325301204819277, | |
| "grad_norm": 0.343924343585968, | |
| "learning_rate": 4.945835668849801e-06, | |
| "loss": 0.358, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.36144578313253, | |
| "grad_norm": 0.35644856095314026, | |
| "learning_rate": 4.837532431501098e-06, | |
| "loss": 0.3673, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.397590361445783, | |
| "grad_norm": 0.4029666781425476, | |
| "learning_rate": 4.729305457072913e-06, | |
| "loss": 0.3534, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.433734939759036, | |
| "grad_norm": 0.3742657005786896, | |
| "learning_rate": 4.621205547735949e-06, | |
| "loss": 0.3623, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.4698795180722892, | |
| "grad_norm": 0.3467872142791748, | |
| "learning_rate": 4.513283446016052e-06, | |
| "loss": 0.3408, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.5060240963855422, | |
| "grad_norm": 0.36237695813179016, | |
| "learning_rate": 4.4055898109754684e-06, | |
| "loss": 0.3612, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.5421686746987953, | |
| "grad_norm": 0.3537854254245758, | |
| "learning_rate": 4.298175194433279e-06, | |
| "loss": 0.3696, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.5783132530120483, | |
| "grad_norm": 0.35789230465888977, | |
| "learning_rate": 4.191090017236177e-06, | |
| "loss": 0.3652, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.6144578313253013, | |
| "grad_norm": 0.34432247281074524, | |
| "learning_rate": 4.0843845455907195e-06, | |
| "loss": 0.3422, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.6506024096385543, | |
| "grad_norm": 0.36375707387924194, | |
| "learning_rate": 3.9781088674681764e-06, | |
| "loss": 0.3717, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.6867469879518073, | |
| "grad_norm": 0.34923499822616577, | |
| "learning_rate": 3.87231286909303e-06, | |
| "loss": 0.3436, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.7228915662650603, | |
| "grad_norm": 0.35821905732154846, | |
| "learning_rate": 3.767046211526191e-06, | |
| "loss": 0.3584, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 3.7590361445783134, | |
| "grad_norm": 0.3310084640979767, | |
| "learning_rate": 3.662358307353897e-06, | |
| "loss": 0.3751, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.7951807228915664, | |
| "grad_norm": 0.3326928913593292, | |
| "learning_rate": 3.5582982974932467e-06, | |
| "loss": 0.3578, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 3.8313253012048194, | |
| "grad_norm": 0.3595709502696991, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.3504, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 3.8674698795180724, | |
| "grad_norm": 0.3628636598587036, | |
| "learning_rate": 3.3522570277662986e-06, | |
| "loss": 0.3371, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.9036144578313254, | |
| "grad_norm": 0.2951819896697998, | |
| "learning_rate": 3.250372484488558e-06, | |
| "loss": 0.3565, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 3.9397590361445785, | |
| "grad_norm": 0.3485693037509918, | |
| "learning_rate": 3.149309223300428e-06, | |
| "loss": 0.3649, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 3.9759036144578315, | |
| "grad_norm": 0.3397277891635895, | |
| "learning_rate": 3.0491146836972273e-06, | |
| "loss": 0.3413, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.036144578313253, | |
| "grad_norm": 0.5771328210830688, | |
| "learning_rate": 2.9498358973929197e-06, | |
| "loss": 0.6546, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.072289156626506, | |
| "grad_norm": 0.377215176820755, | |
| "learning_rate": 2.8515194662432423e-06, | |
| "loss": 0.32, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.108433734939759, | |
| "grad_norm": 0.39817994832992554, | |
| "learning_rate": 2.7542115403706067e-06, | |
| "loss": 0.3009, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.144578313253012, | |
| "grad_norm": 0.3676982820034027, | |
| "learning_rate": 2.65795779650105e-06, | |
| "loss": 0.2888, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.180722891566265, | |
| "grad_norm": 0.34246042370796204, | |
| "learning_rate": 2.562803416523405e-06, | |
| "loss": 0.3289, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.216867469879518, | |
| "grad_norm": 0.3002203702926636, | |
| "learning_rate": 2.46879306628073e-06, | |
| "loss": 0.2918, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.253012048192771, | |
| "grad_norm": 0.3316577672958374, | |
| "learning_rate": 2.375970874603998e-06, | |
| "loss": 0.2918, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.289156626506024, | |
| "grad_norm": 0.36060383915901184, | |
| "learning_rate": 2.2843804125978356e-06, | |
| "loss": 0.3083, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.325301204819277, | |
| "grad_norm": 0.3468538522720337, | |
| "learning_rate": 2.1940646731880887e-06, | |
| "loss": 0.2965, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.36144578313253, | |
| "grad_norm": 0.33555057644844055, | |
| "learning_rate": 2.105066050940758e-06, | |
| "loss": 0.2753, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.397590361445783, | |
| "grad_norm": 0.3662334680557251, | |
| "learning_rate": 2.0174263221618307e-06, | |
| "loss": 0.3069, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.433734939759036, | |
| "grad_norm": 0.3135122060775757, | |
| "learning_rate": 1.931186625287313e-06, | |
| "loss": 0.2963, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.469879518072289, | |
| "grad_norm": 0.3595134913921356, | |
| "learning_rate": 1.8463874415726918e-06, | |
| "loss": 0.2941, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.506024096385542, | |
| "grad_norm": 0.3410852551460266, | |
| "learning_rate": 1.7630685760908623e-06, | |
| "loss": 0.2933, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.542168674698795, | |
| "grad_norm": 0.3322881758213043, | |
| "learning_rate": 1.6812691390474788e-06, | |
| "loss": 0.312, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.578313253012048, | |
| "grad_norm": 0.3299103379249573, | |
| "learning_rate": 1.6010275274224607e-06, | |
| "loss": 0.2687, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.614457831325301, | |
| "grad_norm": 0.3352324366569519, | |
| "learning_rate": 1.5223814069463077e-06, | |
| "loss": 0.2856, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.650602409638554, | |
| "grad_norm": 0.3284769356250763, | |
| "learning_rate": 1.4453676944196477e-06, | |
| "loss": 0.2624, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 4.686746987951807, | |
| "grad_norm": 0.2953889071941376, | |
| "learning_rate": 1.370022540384347e-06, | |
| "loss": 0.295, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 4.72289156626506, | |
| "grad_norm": 0.30767425894737244, | |
| "learning_rate": 1.296381312154305e-06, | |
| "loss": 0.2872, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 4.759036144578313, | |
| "grad_norm": 0.3192180395126343, | |
| "learning_rate": 1.2244785772138972e-06, | |
| "loss": 0.289, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.795180722891566, | |
| "grad_norm": 0.3239184319972992, | |
| "learning_rate": 1.1543480869918555e-06, | |
| "loss": 0.2843, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.831325301204819, | |
| "grad_norm": 0.34262704849243164, | |
| "learning_rate": 1.0860227610182222e-06, | |
| "loss": 0.2841, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 4.867469879518072, | |
| "grad_norm": 0.3087993562221527, | |
| "learning_rate": 1.0195346714717813e-06, | |
| "loss": 0.2949, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 4.903614457831325, | |
| "grad_norm": 0.3130486011505127, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.2935, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 4.9397590361445785, | |
| "grad_norm": 0.34729984402656555, | |
| "learning_rate": 8.921941636953435e-07, | |
| "loss": 0.2852, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 4.975903614457831, | |
| "grad_norm": 0.2952175736427307, | |
| "learning_rate": 8.314015196043501e-07, | |
| "loss": 0.3026, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 5.036144578313253, | |
| "grad_norm": 0.33559635281562805, | |
| "learning_rate": 7.725656321603414e-07, | |
| "loss": 0.5577, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.072289156626506, | |
| "grad_norm": 0.30693137645721436, | |
| "learning_rate": 7.157141191620548e-07, | |
| "loss": 0.2559, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 5.108433734939759, | |
| "grad_norm": 0.3629642724990845, | |
| "learning_rate": 6.60873666934993e-07, | |
| "loss": 0.2612, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 5.144578313253012, | |
| "grad_norm": 0.36669614911079407, | |
| "learning_rate": 6.080700178047688e-07, | |
| "loss": 0.2997, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 5.180722891566265, | |
| "grad_norm": 0.314728707075119, | |
| "learning_rate": 5.573279580135438e-07, | |
| "loss": 0.2893, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.216867469879518, | |
| "grad_norm": 0.29658058285713196, | |
| "learning_rate": 5.086713060852788e-07, | |
| "loss": 0.2676, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 5.253012048192771, | |
| "grad_norm": 0.33411288261413574, | |
| "learning_rate": 4.6212290164521554e-07, | |
| "loss": 0.2433, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 5.289156626506024, | |
| "grad_norm": 0.3197992742061615, | |
| "learning_rate": 4.1770459469887003e-07, | |
| "loss": 0.2898, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 5.325301204819277, | |
| "grad_norm": 0.30660751461982727, | |
| "learning_rate": 3.754372353755559e-07, | |
| "loss": 0.2554, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 5.36144578313253, | |
| "grad_norm": 0.2993546724319458, | |
| "learning_rate": 3.35340664141246e-07, | |
| "loss": 0.2363, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.397590361445783, | |
| "grad_norm": 0.3170936107635498, | |
| "learning_rate": 2.974337024853802e-07, | |
| "loss": 0.2471, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 5.433734939759036, | |
| "grad_norm": 0.3209405541419983, | |
| "learning_rate": 2.617341440859883e-07, | |
| "loss": 0.2399, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 5.469879518072289, | |
| "grad_norm": 0.29624640941619873, | |
| "learning_rate": 2.2825874645725942e-07, | |
| "loss": 0.2651, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 5.506024096385542, | |
| "grad_norm": 0.30279141664505005, | |
| "learning_rate": 1.9702322308350675e-07, | |
| "loss": 0.2525, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 5.542168674698795, | |
| "grad_norm": 0.3102453351020813, | |
| "learning_rate": 1.6804223604318825e-07, | |
| "loss": 0.2871, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.578313253012048, | |
| "grad_norm": 0.27690696716308594, | |
| "learning_rate": 1.413293891264722e-07, | |
| "loss": 0.242, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 5.614457831325301, | |
| "grad_norm": 0.2901451885700226, | |
| "learning_rate": 1.1689722144956672e-07, | |
| "loss": 0.2704, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.650602409638554, | |
| "grad_norm": 0.3027832508087158, | |
| "learning_rate": 9.475720156880419e-08, | |
| "loss": 0.2681, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 5.686746987951807, | |
| "grad_norm": 0.3067132830619812, | |
| "learning_rate": 7.491972209725807e-08, | |
| "loss": 0.2789, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 5.72289156626506, | |
| "grad_norm": 0.2636028826236725, | |
| "learning_rate": 5.739409482640956e-08, | |
| "loss": 0.239, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.759036144578313, | |
| "grad_norm": 0.2763376533985138, | |
| "learning_rate": 4.2188546355153016e-08, | |
| "loss": 0.2624, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.795180722891566, | |
| "grad_norm": 0.2844434082508087, | |
| "learning_rate": 2.9310214228202016e-08, | |
| "loss": 0.2616, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 5.831325301204819, | |
| "grad_norm": 0.30939143896102905, | |
| "learning_rate": 1.8765143585693924e-08, | |
| "loss": 0.2651, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 5.867469879518072, | |
| "grad_norm": 0.2921662926673889, | |
| "learning_rate": 1.0558284325578038e-08, | |
| "loss": 0.2655, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 5.903614457831325, | |
| "grad_norm": 0.2594563364982605, | |
| "learning_rate": 4.69348878011644e-09, | |
| "loss": 0.2887, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.9397590361445785, | |
| "grad_norm": 0.2833521068096161, | |
| "learning_rate": 1.173509907579362e-09, | |
| "loss": 0.278, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 5.975903614457831, | |
| "grad_norm": 0.2993119955062866, | |
| "learning_rate": 0.0, | |
| "loss": 0.2823, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 5.975903614457831, | |
| "step": 162, | |
| "total_flos": 212201928261632.0, | |
| "train_loss": 0.4494376038143664, | |
| "train_runtime": 18091.5652, | |
| "train_samples_per_second": 0.439, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 162, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 28, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 212201928261632.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |