| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 738, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.040774719673802244, |
| "grad_norm": 18.189022064208984, |
| "learning_rate": 9.000000000000001e-07, |
| "loss": 0.8515, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08154943934760449, |
| "grad_norm": 9.354066848754883, |
| "learning_rate": 1.9000000000000002e-06, |
| "loss": 0.905, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12232415902140673, |
| "grad_norm": 10.508342742919922, |
| "learning_rate": 2.9e-06, |
| "loss": 0.8879, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.16309887869520898, |
| "grad_norm": 9.291099548339844, |
| "learning_rate": 3.900000000000001e-06, |
| "loss": 0.8905, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2038735983690112, |
| "grad_norm": 13.063141822814941, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 0.8604, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.24464831804281345, |
| "grad_norm": 7.156795024871826, |
| "learning_rate": 5.9e-06, |
| "loss": 0.7997, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2854230377166157, |
| "grad_norm": 12.09440803527832, |
| "learning_rate": 6.9e-06, |
| "loss": 0.7996, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.32619775739041795, |
| "grad_norm": 14.44044303894043, |
| "learning_rate": 7.9e-06, |
| "loss": 0.8254, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3669724770642202, |
| "grad_norm": 12.786622047424316, |
| "learning_rate": 8.900000000000001e-06, |
| "loss": 0.8999, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4077471967380224, |
| "grad_norm": 14.936609268188477, |
| "learning_rate": 9.9e-06, |
| "loss": 0.7893, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.44852191641182465, |
| "grad_norm": 12.025712013244629, |
| "learning_rate": 9.961864406779662e-06, |
| "loss": 0.8599, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.4892966360856269, |
| "grad_norm": 18.530860900878906, |
| "learning_rate": 9.91949152542373e-06, |
| "loss": 0.7895, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5300713557594292, |
| "grad_norm": 10.44506549835205, |
| "learning_rate": 9.877118644067798e-06, |
| "loss": 0.8066, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5708460754332314, |
| "grad_norm": 18.924278259277344, |
| "learning_rate": 9.834745762711865e-06, |
| "loss": 0.8618, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6116207951070336, |
| "grad_norm": 18.275020599365234, |
| "learning_rate": 9.792372881355933e-06, |
| "loss": 0.8419, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6523955147808359, |
| "grad_norm": 11.579925537109375, |
| "learning_rate": 9.75e-06, |
| "loss": 0.8823, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.6931702344546381, |
| "grad_norm": 13.954208374023438, |
| "learning_rate": 9.707627118644068e-06, |
| "loss": 0.8893, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7339449541284404, |
| "grad_norm": 11.016424179077148, |
| "learning_rate": 9.665254237288136e-06, |
| "loss": 0.9281, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7747196738022426, |
| "grad_norm": 9.621957778930664, |
| "learning_rate": 9.622881355932205e-06, |
| "loss": 0.8009, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8154943934760448, |
| "grad_norm": 17.310779571533203, |
| "learning_rate": 9.580508474576273e-06, |
| "loss": 0.8456, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8562691131498471, |
| "grad_norm": 10.48460578918457, |
| "learning_rate": 9.53813559322034e-06, |
| "loss": 0.7, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.8970438328236493, |
| "grad_norm": 10.495179176330566, |
| "learning_rate": 9.495762711864408e-06, |
| "loss": 0.6497, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.9378185524974516, |
| "grad_norm": 19.09280776977539, |
| "learning_rate": 9.453389830508474e-06, |
| "loss": 0.8303, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.9785932721712538, |
| "grad_norm": 18.26506233215332, |
| "learning_rate": 9.411016949152543e-06, |
| "loss": 0.736, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_general_loss": 0.7072561979293823, |
| "eval_general_runtime": 258.0411, |
| "eval_general_samples_per_second": 3.546, |
| "eval_general_steps_per_second": 0.887, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_code_loss": 0.8012194037437439, |
| "eval_code_runtime": 301.035, |
| "eval_code_samples_per_second": 3.049, |
| "eval_code_steps_per_second": 0.764, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_stem_loss": 0.7626175284385681, |
| "eval_stem_runtime": 254.1723, |
| "eval_stem_samples_per_second": 3.596, |
| "eval_stem_steps_per_second": 0.901, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.016309887869521, |
| "grad_norm": 14.707352638244629, |
| "learning_rate": 9.368644067796611e-06, |
| "loss": 0.6495, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0570846075433231, |
| "grad_norm": 14.996277809143066, |
| "learning_rate": 9.32627118644068e-06, |
| "loss": 0.6753, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.0978593272171253, |
| "grad_norm": 16.44031524658203, |
| "learning_rate": 9.283898305084746e-06, |
| "loss": 0.6465, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.1386340468909277, |
| "grad_norm": 12.770790100097656, |
| "learning_rate": 9.241525423728814e-06, |
| "loss": 0.7006, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.17940876656473, |
| "grad_norm": 9.644815444946289, |
| "learning_rate": 9.199152542372882e-06, |
| "loss": 0.7345, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.2201834862385321, |
| "grad_norm": 12.410354614257812, |
| "learning_rate": 9.15677966101695e-06, |
| "loss": 0.5812, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.2609582059123343, |
| "grad_norm": 14.592584609985352, |
| "learning_rate": 9.114406779661017e-06, |
| "loss": 0.7479, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.3017329255861365, |
| "grad_norm": 8.983531951904297, |
| "learning_rate": 9.072033898305086e-06, |
| "loss": 0.6735, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.3425076452599387, |
| "grad_norm": 10.594444274902344, |
| "learning_rate": 9.029661016949152e-06, |
| "loss": 0.6125, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.3832823649337411, |
| "grad_norm": 8.827781677246094, |
| "learning_rate": 8.98728813559322e-06, |
| "loss": 0.5886, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.4240570846075433, |
| "grad_norm": 8.48524284362793, |
| "learning_rate": 8.944915254237289e-06, |
| "loss": 0.6677, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.4648318042813455, |
| "grad_norm": 14.892068862915039, |
| "learning_rate": 8.902542372881357e-06, |
| "loss": 0.6921, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.505606523955148, |
| "grad_norm": 13.356966018676758, |
| "learning_rate": 8.860169491525424e-06, |
| "loss": 0.7095, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.5463812436289501, |
| "grad_norm": 10.22076416015625, |
| "learning_rate": 8.817796610169492e-06, |
| "loss": 0.6031, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.5871559633027523, |
| "grad_norm": 9.876967430114746, |
| "learning_rate": 8.77542372881356e-06, |
| "loss": 0.5818, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.6279306829765545, |
| "grad_norm": 9.625609397888184, |
| "learning_rate": 8.733050847457629e-06, |
| "loss": 0.5913, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.6687054026503567, |
| "grad_norm": 8.925414085388184, |
| "learning_rate": 8.690677966101695e-06, |
| "loss": 0.578, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.709480122324159, |
| "grad_norm": 7.93916130065918, |
| "learning_rate": 8.648305084745763e-06, |
| "loss": 0.6955, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.750254841997961, |
| "grad_norm": 7.942169666290283, |
| "learning_rate": 8.60593220338983e-06, |
| "loss": 0.5284, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.7910295616717635, |
| "grad_norm": 9.36421012878418, |
| "learning_rate": 8.563559322033898e-06, |
| "loss": 0.7499, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.8318042813455657, |
| "grad_norm": 12.293156623840332, |
| "learning_rate": 8.521186440677967e-06, |
| "loss": 0.6923, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.8725790010193681, |
| "grad_norm": 9.337946891784668, |
| "learning_rate": 8.478813559322035e-06, |
| "loss": 0.6138, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.9133537206931703, |
| "grad_norm": 10.548377990722656, |
| "learning_rate": 8.436440677966102e-06, |
| "loss": 0.6029, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.9541284403669725, |
| "grad_norm": 17.341978073120117, |
| "learning_rate": 8.39406779661017e-06, |
| "loss": 0.624, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.9949031600407747, |
| "grad_norm": 13.546788215637207, |
| "learning_rate": 8.351694915254238e-06, |
| "loss": 0.6197, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_general_loss": 0.6272298097610474, |
| "eval_general_runtime": 255.3018, |
| "eval_general_samples_per_second": 3.584, |
| "eval_general_steps_per_second": 0.897, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_code_loss": 0.69377201795578, |
| "eval_code_runtime": 298.208, |
| "eval_code_samples_per_second": 3.078, |
| "eval_code_steps_per_second": 0.771, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_stem_loss": 0.7002437710762024, |
| "eval_stem_runtime": 251.7134, |
| "eval_stem_samples_per_second": 3.631, |
| "eval_stem_steps_per_second": 0.91, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.032619775739042, |
| "grad_norm": 8.038460731506348, |
| "learning_rate": 8.309322033898306e-06, |
| "loss": 0.4989, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.073394495412844, |
| "grad_norm": 11.866241455078125, |
| "learning_rate": 8.266949152542375e-06, |
| "loss": 0.6914, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.1141692150866462, |
| "grad_norm": 6.622210502624512, |
| "learning_rate": 8.224576271186441e-06, |
| "loss": 0.5043, |
| "step": 520 |
| }, |
| { |
| "epoch": 2.1549439347604484, |
| "grad_norm": 11.639506340026855, |
| "learning_rate": 8.182203389830508e-06, |
| "loss": 0.6054, |
| "step": 530 |
| }, |
| { |
| "epoch": 2.1957186544342506, |
| "grad_norm": 8.884720802307129, |
| "learning_rate": 8.139830508474576e-06, |
| "loss": 0.5524, |
| "step": 540 |
| }, |
| { |
| "epoch": 2.236493374108053, |
| "grad_norm": 12.228666305541992, |
| "learning_rate": 8.097457627118644e-06, |
| "loss": 0.6011, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.2772680937818555, |
| "grad_norm": 10.770685195922852, |
| "learning_rate": 8.055084745762713e-06, |
| "loss": 0.5481, |
| "step": 560 |
| }, |
| { |
| "epoch": 2.3180428134556577, |
| "grad_norm": 12.777567863464355, |
| "learning_rate": 8.012711864406781e-06, |
| "loss": 0.496, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.35881753312946, |
| "grad_norm": 12.713486671447754, |
| "learning_rate": 7.970338983050848e-06, |
| "loss": 0.4764, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.399592252803262, |
| "grad_norm": 15.633949279785156, |
| "learning_rate": 7.927966101694916e-06, |
| "loss": 0.6179, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.4403669724770642, |
| "grad_norm": 10.710966110229492, |
| "learning_rate": 7.885593220338984e-06, |
| "loss": 0.5726, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.4811416921508664, |
| "grad_norm": 10.519601821899414, |
| "learning_rate": 7.843220338983052e-06, |
| "loss": 0.4988, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.5219164118246686, |
| "grad_norm": 7.1472392082214355, |
| "learning_rate": 7.800847457627119e-06, |
| "loss": 0.5648, |
| "step": 620 |
| }, |
| { |
| "epoch": 2.562691131498471, |
| "grad_norm": 13.704323768615723, |
| "learning_rate": 7.758474576271187e-06, |
| "loss": 0.6488, |
| "step": 630 |
| }, |
| { |
| "epoch": 2.603465851172273, |
| "grad_norm": 8.187666893005371, |
| "learning_rate": 7.716101694915254e-06, |
| "loss": 0.5047, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.6442405708460752, |
| "grad_norm": 8.175298690795898, |
| "learning_rate": 7.673728813559322e-06, |
| "loss": 0.5948, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.6850152905198774, |
| "grad_norm": 11.140478134155273, |
| "learning_rate": 7.63135593220339e-06, |
| "loss": 0.5212, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.72579001019368, |
| "grad_norm": 10.118830680847168, |
| "learning_rate": 7.588983050847458e-06, |
| "loss": 0.506, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.7665647298674823, |
| "grad_norm": 12.593578338623047, |
| "learning_rate": 7.546610169491526e-06, |
| "loss": 0.5584, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.8073394495412844, |
| "grad_norm": 8.544402122497559, |
| "learning_rate": 7.504237288135594e-06, |
| "loss": 0.5202, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.8481141692150866, |
| "grad_norm": 11.403071403503418, |
| "learning_rate": 7.461864406779662e-06, |
| "loss": 0.6049, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.888888888888889, |
| "grad_norm": 12.620019912719727, |
| "learning_rate": 7.41949152542373e-06, |
| "loss": 0.5484, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.929663608562691, |
| "grad_norm": 8.751862525939941, |
| "learning_rate": 7.377118644067798e-06, |
| "loss": 0.5454, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.9704383282364932, |
| "grad_norm": 10.521064758300781, |
| "learning_rate": 7.334745762711864e-06, |
| "loss": 0.5242, |
| "step": 730 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_general_loss": 0.5933007597923279, |
| "eval_general_runtime": 255.4722, |
| "eval_general_samples_per_second": 3.582, |
| "eval_general_steps_per_second": 0.896, |
| "step": 738 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_code_loss": 0.6812524795532227, |
| "eval_code_runtime": 299.2052, |
| "eval_code_samples_per_second": 3.068, |
| "eval_code_steps_per_second": 0.769, |
| "step": 738 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_stem_loss": 0.6883611679077148, |
| "eval_stem_runtime": 251.705, |
| "eval_stem_samples_per_second": 3.631, |
| "eval_stem_steps_per_second": 0.91, |
| "step": 738 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2460, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6233005486340833e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
