| { | |
| "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": 2.279883623123169, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.5982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 1.5012547969818115, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 2.3142, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04285714285714286, | |
| "grad_norm": 1.7552474737167358, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.7833, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 1.8790605068206787, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.2697, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.6815859079360962, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.049, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 1.561714768409729, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.9491, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.4625489711761475, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8847, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 2.1226258277893066, | |
| "learning_rate": 9.841269841269841e-05, | |
| "loss": 0.8167, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12857142857142856, | |
| "grad_norm": 1.3709640502929688, | |
| "learning_rate": 9.682539682539682e-05, | |
| "loss": 0.7321, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 1.2312499284744263, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.693, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15714285714285714, | |
| "grad_norm": 1.4416557550430298, | |
| "learning_rate": 9.365079365079366e-05, | |
| "loss": 0.6389, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 1.7498096227645874, | |
| "learning_rate": 9.206349206349206e-05, | |
| "loss": 0.6421, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18571428571428572, | |
| "grad_norm": 1.6708226203918457, | |
| "learning_rate": 9.047619047619048e-05, | |
| "loss": 0.6309, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.7032530307769775, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.6388, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 1.1614326238632202, | |
| "learning_rate": 8.730158730158731e-05, | |
| "loss": 0.5888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 1.7418193817138672, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.5878, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.24285714285714285, | |
| "grad_norm": 1.3387174606323242, | |
| "learning_rate": 8.412698412698413e-05, | |
| "loss": 0.5962, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2571428571428571, | |
| "grad_norm": 1.1994811296463013, | |
| "learning_rate": 8.253968253968255e-05, | |
| "loss": 0.6093, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2714285714285714, | |
| "grad_norm": 1.5204330682754517, | |
| "learning_rate": 8.095238095238096e-05, | |
| "loss": 0.6045, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.2687711715698242, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.5934, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.4332380294799805, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.5883, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3142857142857143, | |
| "grad_norm": 1.5756443738937378, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 0.5605, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.32857142857142857, | |
| "grad_norm": 1.405213713645935, | |
| "learning_rate": 7.460317460317461e-05, | |
| "loss": 0.5993, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.480230450630188, | |
| "learning_rate": 7.301587301587302e-05, | |
| "loss": 0.5896, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 1.472406029701233, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 0.5661, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37142857142857144, | |
| "grad_norm": 1.408607006072998, | |
| "learning_rate": 6.984126984126984e-05, | |
| "loss": 0.545, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.38571428571428573, | |
| "grad_norm": 1.3194152116775513, | |
| "learning_rate": 6.825396825396825e-05, | |
| "loss": 0.5366, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.5078984498977661, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.5236, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4142857142857143, | |
| "grad_norm": 1.3387917280197144, | |
| "learning_rate": 6.507936507936509e-05, | |
| "loss": 0.5545, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.1835085153579712, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.563, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44285714285714284, | |
| "grad_norm": 1.424862027168274, | |
| "learning_rate": 6.19047619047619e-05, | |
| "loss": 0.5369, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 1.3369919061660767, | |
| "learning_rate": 6.0317460317460316e-05, | |
| "loss": 0.576, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4714285714285714, | |
| "grad_norm": 1.2523393630981445, | |
| "learning_rate": 5.873015873015873e-05, | |
| "loss": 0.5245, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4857142857142857, | |
| "grad_norm": 1.6725609302520752, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.5047, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.3288273811340332, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.5396, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 1.492069125175476, | |
| "learning_rate": 5.396825396825397e-05, | |
| "loss": 0.5099, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5285714285714286, | |
| "grad_norm": 1.508617639541626, | |
| "learning_rate": 5.2380952380952384e-05, | |
| "loss": 0.503, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5428571428571428, | |
| "grad_norm": 1.6115648746490479, | |
| "learning_rate": 5.0793650793650794e-05, | |
| "loss": 0.5571, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5571428571428572, | |
| "grad_norm": 1.4812785387039185, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 0.5036, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.555457353591919, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.518, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5857142857142857, | |
| "grad_norm": 1.6743320226669312, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 0.523, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.6365365982055664, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5112, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6142857142857143, | |
| "grad_norm": 1.4804445505142212, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.5177, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 1.5929114818572998, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.4895, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 1.512065052986145, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.5158, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6571428571428571, | |
| "grad_norm": 1.5385123491287231, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.5188, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6714285714285714, | |
| "grad_norm": 1.7010993957519531, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.5039, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 1.4756510257720947, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.5004, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.407616376876831, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4947, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.376063346862793, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.4797, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7285714285714285, | |
| "grad_norm": 1.6061830520629883, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 0.4872, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 1.4005217552185059, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.4648, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7571428571428571, | |
| "grad_norm": 1.4235899448394775, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.463, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.7714285714285715, | |
| "grad_norm": 1.210481882095337, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.4728, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 1.6099470853805542, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.485, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.6083734035491943, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.4594, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.8142857142857143, | |
| "grad_norm": 1.350246548652649, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.4763, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.8285714285714286, | |
| "grad_norm": 1.3000835180282593, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.4705, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.8428571428571429, | |
| "grad_norm": 1.2059348821640015, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.4876, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.3652459383010864, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.4919, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8714285714285714, | |
| "grad_norm": 1.451910376548767, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.463, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.8857142857142857, | |
| "grad_norm": 1.4704546928405762, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.4768, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 1.5009324550628662, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4516, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 1.5519717931747437, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.4517, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 1.5606343746185303, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.4732, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.9428571428571428, | |
| "grad_norm": 1.3639295101165771, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.4791, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.9571428571428572, | |
| "grad_norm": 1.6867655515670776, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.4968, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 1.4185600280761719, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.4902, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.9857142857142858, | |
| "grad_norm": 1.7370814085006714, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.4564, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.6167285442352295, | |
| "learning_rate": 0.0, | |
| "loss": 0.4652, | |
| "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 | |
| } | |