| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 0, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014285714285714285, | |
| "grad_norm": 13.95046329498291, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 7.364729404449463, | |
| "learning_rate": 9.994965332706574e-06, | |
| "loss": 0.9016, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04285714285714286, | |
| "grad_norm": 2.002855062484741, | |
| "learning_rate": 9.979871469976197e-06, | |
| "loss": 0.5845, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 0.7593860030174255, | |
| "learning_rate": 9.954748808839675e-06, | |
| "loss": 0.4902, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.1937320232391357, | |
| "learning_rate": 9.91964794299315e-06, | |
| "loss": 0.686, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 1.0137990713119507, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.8306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.3848375380039215, | |
| "learning_rate": 9.819814303479268e-06, | |
| "loss": 0.4122, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 0.46849027276039124, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 0.5049, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12857142857142856, | |
| "grad_norm": 0.49745646119117737, | |
| "learning_rate": 9.681174353198687e-06, | |
| "loss": 0.4528, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.43694353103637695, | |
| "learning_rate": 9.597638862757255e-06, | |
| "loss": 0.5232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15714285714285714, | |
| "grad_norm": 0.3639129400253296, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.5254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 0.4034217596054077, | |
| "learning_rate": 9.40297765928369e-06, | |
| "loss": 0.5156, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18571428571428572, | |
| "grad_norm": 0.23296697437763214, | |
| "learning_rate": 9.292243968009332e-06, | |
| "loss": 0.3333, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.23207895457744598, | |
| "learning_rate": 9.172866268606514e-06, | |
| "loss": 0.344, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.32032573223114014, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.4497, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.3064661920070648, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.4669, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24285714285714285, | |
| "grad_norm": 0.26603952050209045, | |
| "learning_rate": 8.765357330018056e-06, | |
| "loss": 0.3826, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2571428571428571, | |
| "grad_norm": 0.46684619784355164, | |
| "learning_rate": 8.613974319136959e-06, | |
| "loss": 0.521, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2714285714285714, | |
| "grad_norm": 0.16946260631084442, | |
| "learning_rate": 8.455313244934324e-06, | |
| "loss": 0.2927, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.28428971767425537, | |
| "learning_rate": 8.289693629698564e-06, | |
| "loss": 0.4561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.25102052092552185, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.4253, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3142857142857143, | |
| "grad_norm": 0.25125229358673096, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 0.4783, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32857142857142857, | |
| "grad_norm": 0.2102043479681015, | |
| "learning_rate": 7.754484907260513e-06, | |
| "loss": 0.4528, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.27247658371925354, | |
| "learning_rate": 7.564496387029532e-06, | |
| "loss": 0.4516, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.23549969494342804, | |
| "learning_rate": 7.369343312364994e-06, | |
| "loss": 0.4624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37142857142857144, | |
| "grad_norm": 0.20365270972251892, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.4146, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38571428571428573, | |
| "grad_norm": 0.2122325897216797, | |
| "learning_rate": 6.965125158269619e-06, | |
| "loss": 0.3929, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.24025917053222656, | |
| "learning_rate": 6.7568741204067145e-06, | |
| "loss": 0.4916, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4142857142857143, | |
| "grad_norm": 0.1978403925895691, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.397, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.1869862973690033, | |
| "learning_rate": 6.330184227833376e-06, | |
| "loss": 0.3752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.44285714285714284, | |
| "grad_norm": 0.2698259651660919, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.5356, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.20620207488536835, | |
| "learning_rate": 5.892784473993184e-06, | |
| "loss": 0.451, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4714285714285714, | |
| "grad_norm": 0.21425208449363708, | |
| "learning_rate": 5.671166329088278e-06, | |
| "loss": 0.4462, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4857142857142857, | |
| "grad_norm": 0.20794828236103058, | |
| "learning_rate": 5.448196544517168e-06, | |
| "loss": 0.3861, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.20094285905361176, | |
| "learning_rate": 5.224324151752575e-06, | |
| "loss": 0.4329, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 0.22768181562423706, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4241, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5285714285714286, | |
| "grad_norm": 0.1947719156742096, | |
| "learning_rate": 4.775675848247427e-06, | |
| "loss": 0.4438, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5428571428571428, | |
| "grad_norm": 0.1121949627995491, | |
| "learning_rate": 4.551803455482833e-06, | |
| "loss": 0.2496, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5571428571428572, | |
| "grad_norm": 0.22327466309070587, | |
| "learning_rate": 4.3288336709117246e-06, | |
| "loss": 0.4263, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.1415957361459732, | |
| "learning_rate": 4.107215526006818e-06, | |
| "loss": 0.3452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5857142857142857, | |
| "grad_norm": 0.19680169224739075, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.3565, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.17308759689331055, | |
| "learning_rate": 3.669815772166625e-06, | |
| "loss": 0.4069, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6142857142857143, | |
| "grad_norm": 0.16297246515750885, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.3318, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 0.21384504437446594, | |
| "learning_rate": 3.2431258795932863e-06, | |
| "loss": 0.5471, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.19756601750850677, | |
| "learning_rate": 3.0348748417303826e-06, | |
| "loss": 0.4227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6571428571428571, | |
| "grad_norm": 0.19723856449127197, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.5024, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6714285714285714, | |
| "grad_norm": 0.1522265076637268, | |
| "learning_rate": 2.6306566876350072e-06, | |
| "loss": 0.3423, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.13345520198345184, | |
| "learning_rate": 2.43550361297047e-06, | |
| "loss": 0.324, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.1821710169315338, | |
| "learning_rate": 2.245515092739488e-06, | |
| "loss": 0.4275, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.16270925104618073, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.3002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7285714285714285, | |
| "grad_norm": 0.19576554000377655, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.4633, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 0.17611368000507355, | |
| "learning_rate": 1.7103063703014372e-06, | |
| "loss": 0.4321, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7571428571428571, | |
| "grad_norm": 0.7469434142112732, | |
| "learning_rate": 1.544686755065677e-06, | |
| "loss": 0.4329, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7714285714285715, | |
| "grad_norm": 0.15975451469421387, | |
| "learning_rate": 1.3860256808630429e-06, | |
| "loss": 0.4003, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.18538609147071838, | |
| "learning_rate": 1.234642669981946e-06, | |
| "loss": 0.2932, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.16250595450401306, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.3491, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8142857142857143, | |
| "grad_norm": 0.1673540472984314, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.372, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8285714285714286, | |
| "grad_norm": 0.1421898752450943, | |
| "learning_rate": 8.271337313934869e-07, | |
| "loss": 0.3331, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8428571428571429, | |
| "grad_norm": 0.19801075756549835, | |
| "learning_rate": 7.077560319906696e-07, | |
| "loss": 0.4457, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.1651347577571869, | |
| "learning_rate": 5.9702234071631e-07, | |
| "loss": 0.3937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8714285714285714, | |
| "grad_norm": 0.18938225507736206, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.4161, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8857142857142857, | |
| "grad_norm": 0.17801089584827423, | |
| "learning_rate": 4.0236113724274716e-07, | |
| "loss": 0.4535, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.22428573668003082, | |
| "learning_rate": 3.18825646801314e-07, | |
| "loss": 0.4029, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.2184993475675583, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 0.4751, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.24975807964801788, | |
| "learning_rate": 1.801856965207338e-07, | |
| "loss": 0.342, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9428571428571428, | |
| "grad_norm": 0.14422230422496796, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.2876, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9571428571428572, | |
| "grad_norm": 0.2161719799041748, | |
| "learning_rate": 8.035205700685167e-08, | |
| "loss": 0.5471, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 0.26302093267440796, | |
| "learning_rate": 4.52511911603265e-08, | |
| "loss": 0.4727, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.9857142857142858, | |
| "grad_norm": 0.18196949362754822, | |
| "learning_rate": 2.012853002380466e-08, | |
| "loss": 0.4177, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1553524136543274, | |
| "learning_rate": 5.034667293427053e-09, | |
| "loss": 0.4099, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.999757231102362e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |