| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.1652542372881356, | |
| "eval_steps": 500, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00211864406779661, | |
| "grad_norm": 6772.94736433113, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 5.4426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0211864406779661, | |
| "grad_norm": 43.76552598391156, | |
| "learning_rate": 5.263157894736842e-05, | |
| "loss": 6.5697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 1.4214989301078385, | |
| "learning_rate": 0.00010526315789473683, | |
| "loss": 5.8015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0635593220338983, | |
| "grad_norm": 1.8559172078320925, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 4.6978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.9523887604864526, | |
| "learning_rate": 0.00021052631578947367, | |
| "loss": 3.9616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1059322033898305, | |
| "grad_norm": 0.5313592686196623, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 3.2816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1271186440677966, | |
| "grad_norm": 0.9882421975844679, | |
| "learning_rate": 0.00031578947368421053, | |
| "loss": 2.9453, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1483050847457627, | |
| "grad_norm": 1.3764980998221854, | |
| "learning_rate": 0.00036842105263157896, | |
| "loss": 2.7478, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.6188567319965684, | |
| "learning_rate": 0.00042105263157894734, | |
| "loss": 2.6778, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1906779661016949, | |
| "grad_norm": 0.45391127998861047, | |
| "learning_rate": 0.00047368421052631577, | |
| "loss": 2.6651, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.211864406779661, | |
| "grad_norm": 0.3359651886818045, | |
| "learning_rate": 0.0004999904062938913, | |
| "loss": 2.6871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2330508474576271, | |
| "grad_norm": 0.2538059916992196, | |
| "learning_rate": 0.0004999136610628463, | |
| "loss": 2.6047, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 0.7420239318499638, | |
| "learning_rate": 0.0004997601941609823, | |
| "loss": 2.6122, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2754237288135593, | |
| "grad_norm": 1.0130312150097984, | |
| "learning_rate": 0.0004995300527015189, | |
| "loss": 2.8314, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2966101694915254, | |
| "grad_norm": 0.45185267289061176, | |
| "learning_rate": 0.0004992233073362051, | |
| "loss": 2.7241, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3177966101694915, | |
| "grad_norm": 1.2647337895757225, | |
| "learning_rate": 0.0004988400522336304, | |
| "loss": 2.6269, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 1.8112639454685833, | |
| "learning_rate": 0.0004983804050503152, | |
| "loss": 2.5217, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3601694915254237, | |
| "grad_norm": 3.7153319991642295, | |
| "learning_rate": 0.0004978445068945918, | |
| "loss": 2.6363, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3813559322033898, | |
| "grad_norm": 1.791954534899048, | |
| "learning_rate": 0.0004972325222832848, | |
| "loss": 2.6156, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4025423728813559, | |
| "grad_norm": 0.30066185600399886, | |
| "learning_rate": 0.0004965446390912051, | |
| "loss": 2.5443, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 0.155337614316216, | |
| "learning_rate": 0.0004957810684934746, | |
| "loss": 2.4791, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4449152542372881, | |
| "grad_norm": 0.10527493629733332, | |
| "learning_rate": 0.0004949420449006968, | |
| "loss": 2.4345, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4661016949152542, | |
| "grad_norm": 0.06207368975658736, | |
| "learning_rate": 0.0004940278258869937, | |
| "loss": 2.4284, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4872881355932203, | |
| "grad_norm": 0.06174468192832609, | |
| "learning_rate": 0.0004930386921109333, | |
| "loss": 2.3855, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 0.04921797570119065, | |
| "learning_rate": 0.0004919749472293693, | |
| "loss": 2.3648, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5296610169491526, | |
| "grad_norm": 0.06272467077360039, | |
| "learning_rate": 0.00049083691780422, | |
| "loss": 2.3618, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5508474576271186, | |
| "grad_norm": 0.06952127682493715, | |
| "learning_rate": 0.0004896249532022172, | |
| "loss": 2.3344, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5720338983050848, | |
| "grad_norm": 0.05291425745739597, | |
| "learning_rate": 0.0004883394254876522, | |
| "loss": 2.3401, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5932203389830508, | |
| "grad_norm": 0.09403878675057362, | |
| "learning_rate": 0.0004869807293081555, | |
| "loss": 2.3351, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.614406779661017, | |
| "grad_norm": 0.07509078154330293, | |
| "learning_rate": 0.00048554928177354254, | |
| "loss": 2.3067, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.635593220338983, | |
| "grad_norm": 0.1705698396439175, | |
| "learning_rate": 0.0004840455223277639, | |
| "loss": 2.3114, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6567796610169492, | |
| "grad_norm": 0.09664349408312269, | |
| "learning_rate": 0.0004824699126139995, | |
| "loss": 2.3059, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.08308196121963289, | |
| "learning_rate": 0.0004808229363329374, | |
| "loss": 2.2926, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6991525423728814, | |
| "grad_norm": 0.0669444065304248, | |
| "learning_rate": 0.0004791050990942811, | |
| "loss": 2.2862, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7203389830508474, | |
| "grad_norm": 0.05853715985139967, | |
| "learning_rate": 0.0004773169282615311, | |
| "loss": 2.2736, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7415254237288136, | |
| "grad_norm": 0.056477614254721926, | |
| "learning_rate": 0.00047545897279008845, | |
| "loss": 2.2715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "grad_norm": 0.0870456690332402, | |
| "learning_rate": 0.000473531803058729, | |
| "loss": 2.2543, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7838983050847458, | |
| "grad_norm": 0.0954901066459511, | |
| "learning_rate": 0.0004715360106945015, | |
| "loss": 2.2752, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8050847457627118, | |
| "grad_norm": 0.06902843103766237, | |
| "learning_rate": 0.00046947220839110225, | |
| "loss": 2.2698, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.826271186440678, | |
| "grad_norm": 0.10925884550477084, | |
| "learning_rate": 0.00046734102972078326, | |
| "loss": 2.2433, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 0.0659931072508813, | |
| "learning_rate": 0.0004651431289398489, | |
| "loss": 2.2415, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8686440677966102, | |
| "grad_norm": 0.06263383305001168, | |
| "learning_rate": 0.00046287918078780554, | |
| "loss": 2.2388, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8898305084745762, | |
| "grad_norm": 0.09782328625398208, | |
| "learning_rate": 0.00046054988028022007, | |
| "loss": 2.2408, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9110169491525424, | |
| "grad_norm": 0.10848225540509068, | |
| "learning_rate": 0.000458155942495356, | |
| "loss": 2.2337, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9322033898305084, | |
| "grad_norm": 0.07281471757622568, | |
| "learning_rate": 0.0004556981023546495, | |
| "loss": 2.2173, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9533898305084746, | |
| "grad_norm": 0.06260737865841007, | |
| "learning_rate": 0.00045317711439709377, | |
| "loss": 2.2175, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9745762711864406, | |
| "grad_norm": 0.05780118722032544, | |
| "learning_rate": 0.00045059375254760106, | |
| "loss": 2.2194, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9957627118644068, | |
| "grad_norm": 0.07389833905985468, | |
| "learning_rate": 0.0004479488098794134, | |
| "loss": 2.222, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 0.08596309367450944, | |
| "learning_rate": 0.0004452430983706351, | |
| "loss": 2.138, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0381355932203389, | |
| "grad_norm": 0.0716327488863897, | |
| "learning_rate": 0.0004424774486549611, | |
| "loss": 2.1209, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.0593220338983051, | |
| "grad_norm": 0.1035432059054005, | |
| "learning_rate": 0.0004396527097666786, | |
| "loss": 2.129, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0805084745762712, | |
| "grad_norm": 0.09433176908109482, | |
| "learning_rate": 0.0004367697488800197, | |
| "loss": 2.1266, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1016949152542372, | |
| "grad_norm": 0.03811729650126105, | |
| "learning_rate": 0.00043382945104294534, | |
| "loss": 2.1261, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1228813559322033, | |
| "grad_norm": 0.04741201646286949, | |
| "learning_rate": 0.0004308327189054421, | |
| "loss": 2.1076, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.1440677966101696, | |
| "grad_norm": 0.053484019027130486, | |
| "learning_rate": 0.0004277804724424146, | |
| "loss": 2.1056, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1652542372881356, | |
| "grad_norm": 0.07045317524776837, | |
| "learning_rate": 0.0004246736486712611, | |
| "loss": 2.1283, | |
| "step": 550 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3631704358977536e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |