| { | |
| "best_metric": 6.682973861694336, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.96, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0064, | |
| "grad_norm": 0.9495358467102051, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 6.9341, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0064, | |
| "eval_loss": 6.940670013427734, | |
| "eval_runtime": 0.4624, | |
| "eval_samples_per_second": 108.123, | |
| "eval_steps_per_second": 15.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0128, | |
| "grad_norm": 0.8018835186958313, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 6.9556, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 0.9049068093299866, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 6.9653, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0256, | |
| "grad_norm": 0.7154098749160767, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 6.9551, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.7742681503295898, | |
| "learning_rate": 0.00015, | |
| "loss": 6.9498, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 0.8399883508682251, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 6.94, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0448, | |
| "grad_norm": 0.5200990438461304, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 6.9413, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0512, | |
| "grad_norm": 0.6034143567085266, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.9438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 0.5844438672065735, | |
| "learning_rate": 0.00027, | |
| "loss": 6.9437, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.6551675796508789, | |
| "learning_rate": 0.0003, | |
| "loss": 6.943, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0704, | |
| "grad_norm": 0.6681671142578125, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 6.9383, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 0.6732079386711121, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 6.9406, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0832, | |
| "grad_norm": 0.6102283596992493, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 6.9383, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0896, | |
| "grad_norm": 0.6549004912376404, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 6.9284, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.5962654948234558, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 6.9047, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1024, | |
| "grad_norm": 0.649928867816925, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 6.9212, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1088, | |
| "grad_norm": 0.504554808139801, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 6.9179, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1152, | |
| "grad_norm": 0.597122848033905, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 6.9112, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1216, | |
| "grad_norm": 0.5620957612991333, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 6.9046, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.6724961400032043, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 6.8993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1344, | |
| "grad_norm": 0.5969198346138, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 6.8979, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1408, | |
| "grad_norm": 0.5506598949432373, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 6.8887, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1472, | |
| "grad_norm": 0.7546066641807556, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 6.8619, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1536, | |
| "grad_norm": 0.6300695538520813, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 6.8506, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5741549134254456, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 6.8638, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 6.874875545501709, | |
| "eval_runtime": 0.047, | |
| "eval_samples_per_second": 1063.777, | |
| "eval_steps_per_second": 148.929, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1664, | |
| "grad_norm": 0.5633116364479065, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 6.8588, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1728, | |
| "grad_norm": 0.6096696853637695, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 6.8797, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1792, | |
| "grad_norm": 0.5343248844146729, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 6.8702, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1856, | |
| "grad_norm": 0.6776606440544128, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 6.84, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.5798454880714417, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 6.8618, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1984, | |
| "grad_norm": 0.6195558905601501, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 6.8286, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2048, | |
| "grad_norm": 0.556268036365509, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 6.8496, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2112, | |
| "grad_norm": 0.5736655592918396, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 6.8319, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2176, | |
| "grad_norm": 0.5479353666305542, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 6.8609, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.8071677684783936, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 6.9076, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2304, | |
| "grad_norm": 0.775070071220398, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 6.9059, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2368, | |
| "grad_norm": 0.7527448534965515, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 6.8908, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2432, | |
| "grad_norm": 0.911148726940155, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 6.8912, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2496, | |
| "grad_norm": 1.4041032791137695, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 6.8862, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.9864165186882019, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 6.9131, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2624, | |
| "grad_norm": 0.8453418612480164, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 6.9059, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2688, | |
| "grad_norm": 0.77274489402771, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 6.8597, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2752, | |
| "grad_norm": 0.7312727570533752, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 6.8523, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2816, | |
| "grad_norm": 0.7589954137802124, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 6.8514, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.588603138923645, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 6.7881, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2944, | |
| "grad_norm": 0.632996678352356, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 6.7755, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3008, | |
| "grad_norm": 0.575196385383606, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 6.79, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3072, | |
| "grad_norm": 0.5218028426170349, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 6.7852, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3136, | |
| "grad_norm": 0.5754166841506958, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 6.7727, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.5350818634033203, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 6.7583, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6.796112060546875, | |
| "eval_runtime": 0.0455, | |
| "eval_samples_per_second": 1098.877, | |
| "eval_steps_per_second": 153.843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3264, | |
| "grad_norm": 0.4826822578907013, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 6.7629, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3328, | |
| "grad_norm": 0.508161187171936, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 6.7403, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3392, | |
| "grad_norm": 0.5200028419494629, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 6.7561, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3456, | |
| "grad_norm": 0.49363598227500916, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 6.7514, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.46784576773643494, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 6.7524, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3584, | |
| "grad_norm": 0.46129316091537476, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 6.7433, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3648, | |
| "grad_norm": 0.5088637471199036, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 6.7277, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3712, | |
| "grad_norm": 0.5694301724433899, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 6.7277, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3776, | |
| "grad_norm": 0.41760918498039246, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 6.7531, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.4982942044734955, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 6.729, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3904, | |
| "grad_norm": 0.4909391701221466, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 6.7228, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3968, | |
| "grad_norm": 0.5273060202598572, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 6.7134, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4032, | |
| "grad_norm": 0.4253634512424469, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 6.7223, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4096, | |
| "grad_norm": 0.47950324416160583, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 6.718, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.46385979652404785, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 6.725, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4224, | |
| "grad_norm": 0.540244996547699, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 6.7151, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4288, | |
| "grad_norm": 0.4589102864265442, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 6.7114, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4352, | |
| "grad_norm": 0.4630209505558014, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 6.7337, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4416, | |
| "grad_norm": 0.47441697120666504, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 6.7308, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.49404001235961914, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 6.7455, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4544, | |
| "grad_norm": 0.44997942447662354, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 6.739, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4608, | |
| "grad_norm": 0.45261090993881226, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 6.7068, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4672, | |
| "grad_norm": 0.44797801971435547, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 6.7162, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4736, | |
| "grad_norm": 0.6951871514320374, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 6.7901, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.7108526825904846, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 6.8099, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 6.746245861053467, | |
| "eval_runtime": 0.0445, | |
| "eval_samples_per_second": 1123.84, | |
| "eval_steps_per_second": 157.338, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4864, | |
| "grad_norm": 0.7808616161346436, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 6.8143, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4928, | |
| "grad_norm": 0.7759772539138794, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 6.8032, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.4992, | |
| "grad_norm": 1.509546160697937, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 6.7856, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5056, | |
| "grad_norm": 1.1290587186813354, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 6.8949, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 0.9573540687561035, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 6.887, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5184, | |
| "grad_norm": 1.0016741752624512, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 6.8455, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5248, | |
| "grad_norm": 0.7958142161369324, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 6.7827, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5312, | |
| "grad_norm": 0.6969197392463684, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 6.7816, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5376, | |
| "grad_norm": 0.8457598090171814, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 6.7871, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 0.5099653005599976, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 6.6791, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5504, | |
| "grad_norm": 0.5534845590591431, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 6.685, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5568, | |
| "grad_norm": 0.5635961294174194, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 6.694, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5632, | |
| "grad_norm": 0.5438621640205383, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 6.6969, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5696, | |
| "grad_norm": 0.5128461122512817, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 6.6693, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 0.6132482290267944, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 6.6821, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5824, | |
| "grad_norm": 0.5470501184463501, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 6.6796, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5888, | |
| "grad_norm": 0.5392007231712341, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 6.6488, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5952, | |
| "grad_norm": 0.6648130416870117, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 6.6436, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6016, | |
| "grad_norm": 0.6511263847351074, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 6.6311, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 0.6294538974761963, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 6.627, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6144, | |
| "grad_norm": 0.48442429304122925, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 6.6497, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6208, | |
| "grad_norm": 0.5661095976829529, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 6.6348, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6272, | |
| "grad_norm": 0.47108545899391174, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 6.6478, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6336, | |
| "grad_norm": 0.43120548129081726, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 6.6553, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.47978243231773376, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 6.6235, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 6.714487075805664, | |
| "eval_runtime": 0.0452, | |
| "eval_samples_per_second": 1106.805, | |
| "eval_steps_per_second": 154.953, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6464, | |
| "grad_norm": 0.442552387714386, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 6.6315, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6528, | |
| "grad_norm": 0.4487893283367157, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 6.641, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6592, | |
| "grad_norm": 0.4315354824066162, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 6.6571, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.6656, | |
| "grad_norm": 0.44835346937179565, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 6.6217, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 0.38457152247428894, | |
| "learning_rate": 0.00015, | |
| "loss": 6.6733, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6784, | |
| "grad_norm": 0.44234663248062134, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 6.6458, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6848, | |
| "grad_norm": 0.5025720000267029, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 6.6981, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6912, | |
| "grad_norm": 0.467263400554657, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 6.6535, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6976, | |
| "grad_norm": 0.4463280141353607, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 6.6794, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 0.5022115111351013, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 6.6662, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7104, | |
| "grad_norm": 0.47702935338020325, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 6.6882, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7168, | |
| "grad_norm": 0.6275339722633362, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 6.7397, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7232, | |
| "grad_norm": 0.8845940828323364, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 6.7815, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7296, | |
| "grad_norm": 0.8113049864768982, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 6.7837, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 0.8991756439208984, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 6.7817, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7424, | |
| "grad_norm": 1.0973552465438843, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 6.7701, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7488, | |
| "grad_norm": 1.67232346534729, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 6.7657, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7552, | |
| "grad_norm": 1.071197748184204, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 6.8816, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7616, | |
| "grad_norm": 0.8870216608047485, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 6.854, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 0.8856467604637146, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 6.8337, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7744, | |
| "grad_norm": 0.7022458910942078, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 6.7082, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.7808, | |
| "grad_norm": 0.8062697052955627, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 6.7377, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7872, | |
| "grad_norm": 0.9013355374336243, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 6.7669, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7936, | |
| "grad_norm": 0.5724779367446899, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 6.6174, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.5374643802642822, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 6.6612, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 6.694909572601318, | |
| "eval_runtime": 0.0438, | |
| "eval_samples_per_second": 1142.364, | |
| "eval_steps_per_second": 159.931, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8064, | |
| "grad_norm": 0.5468215346336365, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 6.667, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8128, | |
| "grad_norm": 0.4469563364982605, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 6.6637, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8192, | |
| "grad_norm": 0.6111487150192261, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 6.6008, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8256, | |
| "grad_norm": 0.46038818359375, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 6.6134, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 0.5608881115913391, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 6.5824, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8384, | |
| "grad_norm": 0.5066159963607788, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 6.5936, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8448, | |
| "grad_norm": 0.35695910453796387, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 6.6303, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8512, | |
| "grad_norm": 0.5033596158027649, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 6.583, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.8576, | |
| "grad_norm": 0.417173832654953, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 6.6496, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.3751719892024994, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 6.6507, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8704, | |
| "grad_norm": 0.3995749056339264, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 6.5948, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8768, | |
| "grad_norm": 0.4013768136501312, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 6.6164, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.8832, | |
| "grad_norm": 0.3744851052761078, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 6.6189, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.8896, | |
| "grad_norm": 0.3870219886302948, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 6.6008, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 0.42525532841682434, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 6.6112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9024, | |
| "grad_norm": 0.3942902088165283, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 6.5992, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9088, | |
| "grad_norm": 0.48578906059265137, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 6.5816, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9152, | |
| "grad_norm": 0.36412331461906433, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 6.6061, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9216, | |
| "grad_norm": 0.4250425398349762, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 6.6691, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 0.4022601842880249, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 6.6641, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9344, | |
| "grad_norm": 0.5123599171638489, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 6.6763, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9408, | |
| "grad_norm": 0.44589608907699585, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 6.6136, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9472, | |
| "grad_norm": 0.4042072892189026, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 6.6563, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9536, | |
| "grad_norm": 0.4555412232875824, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 6.661, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.3993721008300781, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 6.674, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 6.682973861694336, | |
| "eval_runtime": 0.0454, | |
| "eval_samples_per_second": 1101.37, | |
| "eval_steps_per_second": 154.192, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1878403276800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |