| { | |
| "best_metric": 0.9388719201087952, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_magiccoder_ortho/checkpoint-12", | |
| "epoch": 0.99836867862969, | |
| "eval_steps": 4, | |
| "global_step": 153, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 4.3915696144104, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.8061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 3.7475483417510986, | |
| "learning_rate": 0.00015, | |
| "loss": 0.931, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 5.367969989776611, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "eval_loss": 1.0883674621582031, | |
| "eval_runtime": 24.5353, | |
| "eval_samples_per_second": 19.931, | |
| "eval_steps_per_second": 2.527, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03915171288743882, | |
| "grad_norm": 11.019035339355469, | |
| "learning_rate": 0.00029986665273697545, | |
| "loss": 1.0003, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": 2.1015965938568115, | |
| "learning_rate": 0.0002994668480344693, | |
| "loss": 0.9776, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "eval_loss": 0.9662861227989197, | |
| "eval_runtime": 24.6827, | |
| "eval_samples_per_second": 19.811, | |
| "eval_steps_per_second": 2.512, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "grad_norm": 1.750746726989746, | |
| "learning_rate": 0.0002988012967306524, | |
| "loss": 0.9319, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "grad_norm": 2.2127320766448975, | |
| "learning_rate": 0.000297871182151455, | |
| "loss": 0.9345, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "eval_loss": 0.9388719201087952, | |
| "eval_runtime": 24.6723, | |
| "eval_samples_per_second": 19.82, | |
| "eval_steps_per_second": 2.513, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09135399673735727, | |
| "grad_norm": 1.6279808282852173, | |
| "learning_rate": 0.00029667815800665635, | |
| "loss": 0.9489, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10440456769983687, | |
| "grad_norm": 1.5321425199508667, | |
| "learning_rate": 0.0002952243454496488, | |
| "loss": 0.9026, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10440456769983687, | |
| "eval_loss": 0.9481999278068542, | |
| "eval_runtime": 24.6231, | |
| "eval_samples_per_second": 19.859, | |
| "eval_steps_per_second": 2.518, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11745513866231648, | |
| "grad_norm": 1.355367660522461, | |
| "learning_rate": 0.0002935123293061047, | |
| "loss": 0.9004, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13050570962479607, | |
| "grad_norm": 1.5347142219543457, | |
| "learning_rate": 0.0002915451534782506, | |
| "loss": 0.9618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13050570962479607, | |
| "eval_loss": 0.957125186920166, | |
| "eval_runtime": 24.5628, | |
| "eval_samples_per_second": 19.908, | |
| "eval_steps_per_second": 2.524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14355628058727568, | |
| "grad_norm": 1.5545670986175537, | |
| "learning_rate": 0.0002893263155329204, | |
| "loss": 0.9457, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1566068515497553, | |
| "grad_norm": 1.4520829916000366, | |
| "learning_rate": 0.00028685976048300875, | |
| "loss": 0.8685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1566068515497553, | |
| "eval_loss": 0.9719114899635315, | |
| "eval_runtime": 24.4752, | |
| "eval_samples_per_second": 19.979, | |
| "eval_steps_per_second": 2.533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16965742251223492, | |
| "grad_norm": 1.3440358638763428, | |
| "learning_rate": 0.00028414987377338235, | |
| "loss": 1.0084, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18270799347471453, | |
| "grad_norm": 1.43779718875885, | |
| "learning_rate": 0.0002812014734837191, | |
| "loss": 0.8834, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18270799347471453, | |
| "eval_loss": 0.9751714468002319, | |
| "eval_runtime": 56.0537, | |
| "eval_samples_per_second": 8.724, | |
| "eval_steps_per_second": 1.106, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19575856443719414, | |
| "grad_norm": 1.4336111545562744, | |
| "learning_rate": 0.0002780198017621379, | |
| "loss": 0.9617, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20880913539967375, | |
| "grad_norm": 1.291685700416565, | |
| "learning_rate": 0.00027461051550485116, | |
| "loss": 1.0185, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20880913539967375, | |
| "eval_loss": 0.987638533115387, | |
| "eval_runtime": 59.7835, | |
| "eval_samples_per_second": 8.18, | |
| "eval_steps_per_second": 1.037, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22185970636215335, | |
| "grad_norm": 1.3673038482666016, | |
| "learning_rate": 0.00027097967629840906, | |
| "loss": 0.9289, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23491027732463296, | |
| "grad_norm": 1.321115255355835, | |
| "learning_rate": 0.0002671337396424204, | |
| "loss": 0.9354, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23491027732463296, | |
| "eval_loss": 0.9922739863395691, | |
| "eval_runtime": 58.5264, | |
| "eval_samples_per_second": 8.355, | |
| "eval_steps_per_second": 1.059, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24796084828711257, | |
| "grad_norm": 1.3209092617034912, | |
| "learning_rate": 0.00026307954347190983, | |
| "loss": 0.9003, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.26101141924959215, | |
| "grad_norm": 1.2740062475204468, | |
| "learning_rate": 0.00025882429599971866, | |
| "loss": 0.9734, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26101141924959215, | |
| "eval_loss": 0.9982444047927856, | |
| "eval_runtime": 56.4488, | |
| "eval_samples_per_second": 8.663, | |
| "eval_steps_per_second": 1.098, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2740619902120718, | |
| "grad_norm": 1.3060563802719116, | |
| "learning_rate": 0.0002543755629005657, | |
| "loss": 0.9583, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28711256117455136, | |
| "grad_norm": 1.2693545818328857, | |
| "learning_rate": 0.0002497412538595537, | |
| "loss": 1.034, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28711256117455136, | |
| "eval_loss": 1.0034517049789429, | |
| "eval_runtime": 57.2987, | |
| "eval_samples_per_second": 8.534, | |
| "eval_steps_per_second": 1.082, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.300163132137031, | |
| "grad_norm": 1.3035016059875488, | |
| "learning_rate": 0.00024492960850903755, | |
| "loss": 0.9648, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3132137030995106, | |
| "grad_norm": 1.4393730163574219, | |
| "learning_rate": 0.00023994918177885902, | |
| "loss": 1.0067, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3132137030995106, | |
| "eval_loss": 1.0048160552978516, | |
| "eval_runtime": 56.3331, | |
| "eval_samples_per_second": 8.681, | |
| "eval_steps_per_second": 1.101, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3262642740619902, | |
| "grad_norm": 1.5344454050064087, | |
| "learning_rate": 0.0002348088286859938, | |
| "loss": 1.0498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33931484502446985, | |
| "grad_norm": 1.2956377267837524, | |
| "learning_rate": 0.00022951768859065402, | |
| "loss": 0.932, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.33931484502446985, | |
| "eval_loss": 1.00808584690094, | |
| "eval_runtime": 56.5841, | |
| "eval_samples_per_second": 8.642, | |
| "eval_steps_per_second": 1.096, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3523654159869494, | |
| "grad_norm": 1.5058661699295044, | |
| "learning_rate": 0.0002240851689468395, | |
| "loss": 0.9455, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.36541598694942906, | |
| "grad_norm": 1.3148020505905151, | |
| "learning_rate": 0.00021852092857622808, | |
| "loss": 0.9407, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.36541598694942906, | |
| "eval_loss": 1.006118655204773, | |
| "eval_runtime": 57.5921, | |
| "eval_samples_per_second": 8.491, | |
| "eval_steps_per_second": 1.077, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.37846655791190864, | |
| "grad_norm": 1.1989065408706665, | |
| "learning_rate": 0.00021283486049514277, | |
| "loss": 1.023, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3915171288743883, | |
| "grad_norm": 1.3775067329406738, | |
| "learning_rate": 0.00020703707432513004, | |
| "loss": 0.9682, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3915171288743883, | |
| "eval_loss": 1.0053811073303223, | |
| "eval_runtime": 57.2201, | |
| "eval_samples_per_second": 8.546, | |
| "eval_steps_per_second": 1.084, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40456769983686786, | |
| "grad_norm": 1.320212960243225, | |
| "learning_rate": 0.00020113787831842152, | |
| "loss": 0.8986, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4176182707993475, | |
| "grad_norm": 1.325500726699829, | |
| "learning_rate": 0.0001951477610302378, | |
| "loss": 1.0224, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4176182707993475, | |
| "eval_loss": 1.0092753171920776, | |
| "eval_runtime": 56.0548, | |
| "eval_samples_per_second": 8.724, | |
| "eval_steps_per_second": 1.106, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.43066884176182707, | |
| "grad_norm": 1.2880396842956543, | |
| "learning_rate": 0.0001890773726705198, | |
| "loss": 0.9943, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4437194127243067, | |
| "grad_norm": 1.237645149230957, | |
| "learning_rate": 0.00018293750616824443, | |
| "loss": 1.0145, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4437194127243067, | |
| "eval_loss": 1.009407639503479, | |
| "eval_runtime": 24.7188, | |
| "eval_samples_per_second": 19.783, | |
| "eval_steps_per_second": 2.508, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4567699836867863, | |
| "grad_norm": 1.1990931034088135, | |
| "learning_rate": 0.00017673907798199052, | |
| "loss": 1.0333, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4698205546492659, | |
| "grad_norm": 1.2862218618392944, | |
| "learning_rate": 0.000170493108690874, | |
| "loss": 0.9756, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4698205546492659, | |
| "eval_loss": 1.010068416595459, | |
| "eval_runtime": 24.7249, | |
| "eval_samples_per_second": 19.778, | |
| "eval_steps_per_second": 2.508, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4828711256117455, | |
| "grad_norm": 1.2775288820266724, | |
| "learning_rate": 0.00016421070340036023, | |
| "loss": 1.0124, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.49592169657422513, | |
| "grad_norm": 1.3676966428756714, | |
| "learning_rate": 0.00015790303199779193, | |
| "loss": 0.9968, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.49592169657422513, | |
| "eval_loss": 1.0086660385131836, | |
| "eval_runtime": 24.6773, | |
| "eval_samples_per_second": 19.816, | |
| "eval_steps_per_second": 2.512, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5089722675367048, | |
| "grad_norm": 1.2739876508712769, | |
| "learning_rate": 0.00015158130929273695, | |
| "loss": 0.9405, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5220228384991843, | |
| "grad_norm": 1.3879481554031372, | |
| "learning_rate": 0.00014525677507746615, | |
| "loss": 0.9566, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5220228384991843, | |
| "eval_loss": 1.0094032287597656, | |
| "eval_runtime": 24.6744, | |
| "eval_samples_per_second": 19.818, | |
| "eval_steps_per_second": 2.513, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5350734094616639, | |
| "grad_norm": 1.246418833732605, | |
| "learning_rate": 0.00013894067414301314, | |
| "loss": 1.0481, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5481239804241436, | |
| "grad_norm": 1.3928742408752441, | |
| "learning_rate": 0.0001326442362863458, | |
| "loss": 1.0394, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5481239804241436, | |
| "eval_loss": 1.008681297302246, | |
| "eval_runtime": 24.6024, | |
| "eval_samples_per_second": 19.876, | |
| "eval_steps_per_second": 2.52, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5611745513866232, | |
| "grad_norm": 1.2170292139053345, | |
| "learning_rate": 0.00012637865634419735, | |
| "loss": 0.9979, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5742251223491027, | |
| "grad_norm": 1.3591171503067017, | |
| "learning_rate": 0.00012015507428905507, | |
| "loss": 0.9546, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5742251223491027, | |
| "eval_loss": 1.0074015855789185, | |
| "eval_runtime": 24.5002, | |
| "eval_samples_per_second": 19.959, | |
| "eval_steps_per_second": 2.531, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5872756933115824, | |
| "grad_norm": 1.336329460144043, | |
| "learning_rate": 0.00011398455542269575, | |
| "loss": 0.9125, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.600326264274062, | |
| "grad_norm": 1.2378321886062622, | |
| "learning_rate": 0.00010787807070248305, | |
| "loss": 1.0347, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.600326264274062, | |
| "eval_loss": 1.0086424350738525, | |
| "eval_runtime": 24.4221, | |
| "eval_samples_per_second": 20.023, | |
| "eval_steps_per_second": 2.539, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6133768352365416, | |
| "grad_norm": 1.3458659648895264, | |
| "learning_rate": 0.00010184647723540557, | |
| "loss": 0.9567, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6264274061990212, | |
| "grad_norm": 1.251621961593628, | |
| "learning_rate": 9.590049897453668e-05, | |
| "loss": 0.9639, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6264274061990212, | |
| "eval_loss": 1.004166841506958, | |
| "eval_runtime": 56.7542, | |
| "eval_samples_per_second": 8.616, | |
| "eval_steps_per_second": 1.092, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6394779771615008, | |
| "grad_norm": 1.15924870967865, | |
| "learning_rate": 9.005070765223768e-05, | |
| "loss": 1.0447, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6525285481239804, | |
| "grad_norm": 1.4097235202789307, | |
| "learning_rate": 8.430750398400308e-05, | |
| "loss": 1.0543, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6525285481239804, | |
| "eval_loss": 1.002665638923645, | |
| "eval_runtime": 55.6845, | |
| "eval_samples_per_second": 8.782, | |
| "eval_steps_per_second": 1.113, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6655791190864601, | |
| "grad_norm": 1.3108314275741577, | |
| "learning_rate": 7.868109917636821e-05, | |
| "loss": 0.9645, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6786296900489397, | |
| "grad_norm": 1.2921593189239502, | |
| "learning_rate": 7.318149677175675e-05, | |
| "loss": 0.9346, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6786296900489397, | |
| "eval_loss": 1.003048300743103, | |
| "eval_runtime": 57.4498, | |
| "eval_samples_per_second": 8.512, | |
| "eval_steps_per_second": 1.079, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6916802610114192, | |
| "grad_norm": 1.2615606784820557, | |
| "learning_rate": 6.781847486254697e-05, | |
| "loss": 0.9565, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7047308319738989, | |
| "grad_norm": 1.3441969156265259, | |
| "learning_rate": 6.260156870598071e-05, | |
| "loss": 0.9744, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7047308319738989, | |
| "eval_loss": 1.0019466876983643, | |
| "eval_runtime": 56.5017, | |
| "eval_samples_per_second": 8.655, | |
| "eval_steps_per_second": 1.097, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7177814029363785, | |
| "grad_norm": 1.1984766721725464, | |
| "learning_rate": 5.7540053770823644e-05, | |
| "loss": 0.9558, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7308319738988581, | |
| "grad_norm": 1.259084701538086, | |
| "learning_rate": 5.264292924592073e-05, | |
| "loss": 0.9546, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7308319738988581, | |
| "eval_loss": 0.9984883069992065, | |
| "eval_runtime": 56.938, | |
| "eval_samples_per_second": 8.588, | |
| "eval_steps_per_second": 1.089, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7438825448613376, | |
| "grad_norm": 1.2619880437850952, | |
| "learning_rate": 4.791890203996634e-05, | |
| "loss": 0.9784, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7569331158238173, | |
| "grad_norm": 1.1600760221481323, | |
| "learning_rate": 4.3376371300938786e-05, | |
| "loss": 0.9138, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7569331158238173, | |
| "eval_loss": 0.9968593716621399, | |
| "eval_runtime": 56.3466, | |
| "eval_samples_per_second": 8.678, | |
| "eval_steps_per_second": 1.1, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7699836867862969, | |
| "grad_norm": 1.2669286727905273, | |
| "learning_rate": 3.9023413482721426e-05, | |
| "loss": 0.9714, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7830342577487766, | |
| "grad_norm": 1.2815442085266113, | |
| "learning_rate": 3.4867767985462507e-05, | |
| "loss": 0.9026, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7830342577487766, | |
| "eval_loss": 0.9961332082748413, | |
| "eval_runtime": 56.6715, | |
| "eval_samples_per_second": 8.629, | |
| "eval_steps_per_second": 1.094, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7960848287112561, | |
| "grad_norm": 1.2086176872253418, | |
| "learning_rate": 3.09168233952042e-05, | |
| "loss": 1.0291, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8091353996737357, | |
| "grad_norm": 1.2728592157363892, | |
| "learning_rate": 2.717760434724613e-05, | |
| "loss": 0.9746, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8091353996737357, | |
| "eval_loss": 0.9953013062477112, | |
| "eval_runtime": 56.695, | |
| "eval_samples_per_second": 8.625, | |
| "eval_steps_per_second": 1.094, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8221859706362153, | |
| "grad_norm": 1.163971185684204, | |
| "learning_rate": 2.3656759036600187e-05, | |
| "loss": 0.9733, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.835236541598695, | |
| "grad_norm": 1.2905343770980835, | |
| "learning_rate": 2.0360547397742523e-05, | |
| "loss": 0.9453, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.835236541598695, | |
| "eval_loss": 0.9950230717658997, | |
| "eval_runtime": 57.4352, | |
| "eval_samples_per_second": 8.514, | |
| "eval_steps_per_second": 1.079, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8482871125611745, | |
| "grad_norm": 1.2126384973526, | |
| "learning_rate": 1.7294829974678338e-05, | |
| "loss": 0.922, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8613376835236541, | |
| "grad_norm": 1.3399946689605713, | |
| "learning_rate": 1.4465057501108546e-05, | |
| "loss": 1.0311, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8613376835236541, | |
| "eval_loss": 0.9933781027793884, | |
| "eval_runtime": 56.8077, | |
| "eval_samples_per_second": 8.608, | |
| "eval_steps_per_second": 1.091, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8743882544861338, | |
| "grad_norm": 1.2741433382034302, | |
| "learning_rate": 1.1876261209224314e-05, | |
| "loss": 0.9365, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8874388254486134, | |
| "grad_norm": 1.1750285625457764, | |
| "learning_rate": 9.533043884359615e-06, | |
| "loss": 0.971, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8874388254486134, | |
| "eval_loss": 0.992695152759552, | |
| "eval_runtime": 24.7252, | |
| "eval_samples_per_second": 19.777, | |
| "eval_steps_per_second": 2.508, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.9004893964110929, | |
| "grad_norm": 1.1639913320541382, | |
| "learning_rate": 7.439571681407053e-06, | |
| "loss": 1.0128, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9135399673735726, | |
| "grad_norm": 1.2708672285079956, | |
| "learning_rate": 5.59956671754635e-06, | |
| "loss": 0.9957, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9135399673735726, | |
| "eval_loss": 0.9919000864028931, | |
| "eval_runtime": 24.7098, | |
| "eval_samples_per_second": 19.79, | |
| "eval_steps_per_second": 2.509, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9265905383360522, | |
| "grad_norm": 1.3160277605056763, | |
| "learning_rate": 4.016300454455945e-06, | |
| "loss": 1.0054, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9396411092985318, | |
| "grad_norm": 1.325445532798767, | |
| "learning_rate": 2.692587881773478e-06, | |
| "loss": 0.9502, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9396411092985318, | |
| "eval_loss": 0.9917099475860596, | |
| "eval_runtime": 24.7029, | |
| "eval_samples_per_second": 19.795, | |
| "eval_steps_per_second": 2.51, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9526916802610114, | |
| "grad_norm": 1.1836706399917603, | |
| "learning_rate": 1.6307825121469164e-06, | |
| "loss": 0.991, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.965742251223491, | |
| "grad_norm": 1.2473053932189941, | |
| "learning_rate": 8.327721967749779e-07, | |
| "loss": 1.0133, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.965742251223491, | |
| "eval_loss": 0.9915127158164978, | |
| "eval_runtime": 24.6188, | |
| "eval_samples_per_second": 19.863, | |
| "eval_steps_per_second": 2.518, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9787928221859706, | |
| "grad_norm": 1.237483024597168, | |
| "learning_rate": 2.9997576887660913e-07, | |
| "loss": 0.9316, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9918433931484503, | |
| "grad_norm": 1.279980182647705, | |
| "learning_rate": 3.334052105728458e-08, | |
| "loss": 0.9684, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9918433931484503, | |
| "eval_loss": 0.9916173219680786, | |
| "eval_runtime": 24.5672, | |
| "eval_samples_per_second": 19.905, | |
| "eval_steps_per_second": 2.524, | |
| "step": 152 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 153, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.85963932651946e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |