| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25460956377173916, | |
| "eval_steps": 500, | |
| "global_step": 3800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.700251678203663e-05, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3034, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0067002516782036625, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 0.00019867336683417085, | |
| "loss": 1.0562, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013400503356407325, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 0.00019733333333333335, | |
| "loss": 0.9729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02010075503461099, | |
| "grad_norm": 0.75, | |
| "learning_rate": 0.00019599329983249582, | |
| "loss": 0.9693, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02680100671281465, | |
| "grad_norm": 0.78125, | |
| "learning_rate": 0.00019465326633165831, | |
| "loss": 0.9563, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.033501258391018314, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 0.00019331323283082078, | |
| "loss": 0.9593, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04020151006922198, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 0.00019197319932998325, | |
| "loss": 0.9478, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.046901761747425635, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 0.00019063316582914575, | |
| "loss": 0.9474, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0536020134256293, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 0.00018929313232830821, | |
| "loss": 0.9438, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.060302265103832964, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 0.0001879530988274707, | |
| "loss": 0.9297, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.06700251678203663, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 0.00018661306532663318, | |
| "loss": 0.9297, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07370276846024029, | |
| "grad_norm": 0.69140625, | |
| "learning_rate": 0.00018527303182579565, | |
| "loss": 0.9218, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.08040302013844396, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 0.00018393299832495814, | |
| "loss": 0.9129, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.0871032718166476, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 0.0001825929648241206, | |
| "loss": 0.9156, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.09380352349485127, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 0.00018125293132328308, | |
| "loss": 0.9151, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.10050377517305494, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 0.00017991289782244557, | |
| "loss": 0.9115, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1072040268512586, | |
| "grad_norm": 0.796875, | |
| "learning_rate": 0.00017857286432160804, | |
| "loss": 0.9114, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.11390427852946226, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 0.00017723283082077054, | |
| "loss": 0.9064, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.12060453020766593, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 0.000175892797319933, | |
| "loss": 0.9039, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.12730478188586958, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 0.00017455276381909548, | |
| "loss": 0.8975, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.13400503356407326, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 0.00017321273031825794, | |
| "loss": 0.8919, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1407052852422769, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 0.00017187269681742044, | |
| "loss": 0.8902, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.14740553692048058, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 0.00017053266331658293, | |
| "loss": 0.8941, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.15410578859868423, | |
| "grad_norm": 0.6875, | |
| "learning_rate": 0.0001691926298157454, | |
| "loss": 0.8928, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.1608060402768879, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 0.00016785259631490787, | |
| "loss": 0.8889, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.16750629195509156, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 0.00016651256281407034, | |
| "loss": 0.8825, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1742065436332952, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 0.00016517252931323284, | |
| "loss": 0.8742, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.1809067953114989, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 0.00016383249581239533, | |
| "loss": 0.878, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.18760704698970254, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 0.0001624924623115578, | |
| "loss": 0.8679, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.19430729866790622, | |
| "grad_norm": 0.6796875, | |
| "learning_rate": 0.00016115242881072027, | |
| "loss": 0.8618, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.20100755034610987, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 0.00015981239530988274, | |
| "loss": 0.8695, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.20770780202431355, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 0.00015847236180904523, | |
| "loss": 0.8769, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.2144080537025172, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 0.00015713232830820773, | |
| "loss": 0.8665, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.22110830538072088, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 0.0001557922948073702, | |
| "loss": 0.8572, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.22780855705892453, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 0.00015445226130653266, | |
| "loss": 0.8696, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.23450880873712818, | |
| "grad_norm": 0.7578125, | |
| "learning_rate": 0.00015311222780569513, | |
| "loss": 0.8543, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.24120906041533186, | |
| "grad_norm": 0.66015625, | |
| "learning_rate": 0.00015177219430485763, | |
| "loss": 0.8618, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.2479093120935355, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.00015043216080402012, | |
| "loss": 0.8553, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.25460956377173916, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 0.0001490921273031826, | |
| "loss": 0.8541, | |
| "step": 3800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 14925, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0541408970364707e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |