| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014285714285714285, | |
| "grad_norm": 2.0519802570343018, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.6996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 1.7261061668395996, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.3304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04285714285714286, | |
| "grad_norm": 1.7338988780975342, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.7885, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 1.7217185497283936, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.3166, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.3501018285751343, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.0478, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 1.5291894674301147, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.9373, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.4568425416946411, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9081, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 1.4048289060592651, | |
| "learning_rate": 9.841269841269841e-05, | |
| "loss": 0.8858, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12857142857142856, | |
| "grad_norm": 1.7233399152755737, | |
| "learning_rate": 9.682539682539682e-05, | |
| "loss": 0.8073, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 1.5269458293914795, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.7158, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15714285714285714, | |
| "grad_norm": 1.5483397245407104, | |
| "learning_rate": 9.365079365079366e-05, | |
| "loss": 0.657, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 1.9205348491668701, | |
| "learning_rate": 9.206349206349206e-05, | |
| "loss": 0.6408, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18571428571428572, | |
| "grad_norm": 1.5036839246749878, | |
| "learning_rate": 9.047619047619048e-05, | |
| "loss": 0.6243, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.7199879884719849, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.6431, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 1.2218741178512573, | |
| "learning_rate": 8.730158730158731e-05, | |
| "loss": 0.6107, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 1.5014203786849976, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.6196, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.24285714285714285, | |
| "grad_norm": 1.4846688508987427, | |
| "learning_rate": 8.412698412698413e-05, | |
| "loss": 0.59, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2571428571428571, | |
| "grad_norm": 1.5421117544174194, | |
| "learning_rate": 8.253968253968255e-05, | |
| "loss": 0.6098, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2714285714285714, | |
| "grad_norm": 1.4997822046279907, | |
| "learning_rate": 8.095238095238096e-05, | |
| "loss": 0.619, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.3502991199493408, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.5888, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.4312520027160645, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.6342, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3142857142857143, | |
| "grad_norm": 1.266749620437622, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 0.6067, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.32857142857142857, | |
| "grad_norm": 1.6904637813568115, | |
| "learning_rate": 7.460317460317461e-05, | |
| "loss": 0.5881, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.4418789148330688, | |
| "learning_rate": 7.301587301587302e-05, | |
| "loss": 0.5817, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 1.2780711650848389, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 0.5889, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37142857142857144, | |
| "grad_norm": 1.3194115161895752, | |
| "learning_rate": 6.984126984126984e-05, | |
| "loss": 0.5439, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.38571428571428573, | |
| "grad_norm": 1.5982288122177124, | |
| "learning_rate": 6.825396825396825e-05, | |
| "loss": 0.5592, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.9103999137878418, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.5605, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4142857142857143, | |
| "grad_norm": 1.3091933727264404, | |
| "learning_rate": 6.507936507936509e-05, | |
| "loss": 0.5336, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.3348157405853271, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.5348, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44285714285714284, | |
| "grad_norm": 1.6273038387298584, | |
| "learning_rate": 6.19047619047619e-05, | |
| "loss": 0.5619, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 1.4445629119873047, | |
| "learning_rate": 6.0317460317460316e-05, | |
| "loss": 0.5461, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4714285714285714, | |
| "grad_norm": 1.283087968826294, | |
| "learning_rate": 5.873015873015873e-05, | |
| "loss": 0.5357, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4857142857142857, | |
| "grad_norm": 1.588865876197815, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.538, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.6756633520126343, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.5332, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 1.5023857355117798, | |
| "learning_rate": 5.396825396825397e-05, | |
| "loss": 0.5277, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5285714285714286, | |
| "grad_norm": 1.2289636135101318, | |
| "learning_rate": 5.2380952380952384e-05, | |
| "loss": 0.5256, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5428571428571428, | |
| "grad_norm": 1.2656893730163574, | |
| "learning_rate": 5.0793650793650794e-05, | |
| "loss": 0.527, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5571428571428572, | |
| "grad_norm": 1.212711215019226, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 0.5081, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.3681621551513672, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.5228, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5857142857142857, | |
| "grad_norm": 1.3375431299209595, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 0.529, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.5025509595870972, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.485, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6142857142857143, | |
| "grad_norm": 1.2895201444625854, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.5289, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 1.6998639106750488, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.5191, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 1.6661393642425537, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.5349, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6571428571428571, | |
| "grad_norm": 1.3605777025222778, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.5027, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6714285714285714, | |
| "grad_norm": 1.4422497749328613, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.5255, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 1.6996279954910278, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.5478, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.4645757675170898, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5033, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.393202304840088, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.5164, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7285714285714285, | |
| "grad_norm": 1.3778272867202759, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 0.5085, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 1.4783354997634888, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.5163, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7571428571428571, | |
| "grad_norm": 1.3363853693008423, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.4665, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.7714285714285715, | |
| "grad_norm": 1.5860188007354736, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.4866, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 1.8180590867996216, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.4759, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.7527533769607544, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.472, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.8142857142857143, | |
| "grad_norm": 1.4881120920181274, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.5039, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.8285714285714286, | |
| "grad_norm": 1.8002556562423706, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.4958, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.8428571428571429, | |
| "grad_norm": 1.5485780239105225, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.4949, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.7183849811553955, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.4683, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8714285714285714, | |
| "grad_norm": 1.4343849420547485, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.485, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.8857142857142857, | |
| "grad_norm": 1.3092949390411377, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.48, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.3735129833221436, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4757, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 1.3683648109436035, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.451, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 2.0582668781280518, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.486, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.9428571428571428, | |
| "grad_norm": 1.4949898719787598, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.4937, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.9571428571428572, | |
| "grad_norm": 1.3742563724517822, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.4677, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 1.5607844591140747, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.478, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.9857142857142858, | |
| "grad_norm": 1.609473705291748, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.4865, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.4834121465682983, | |
| "learning_rate": 0.0, | |
| "loss": 0.4945, | |
| "step": 1400 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 1400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8419093040332800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |