| { | |
| "best_metric": 0.9108405113220215, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7188885604493054, | |
| "eval_steps": 25, | |
| "global_step": 76, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009459060005911913, | |
| "grad_norm": 0.9699360728263855, | |
| "learning_rate": 0.00015, | |
| "loss": 1.3474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009459060005911913, | |
| "eval_loss": 1.4942742586135864, | |
| "eval_runtime": 11.3224, | |
| "eval_samples_per_second": 4.416, | |
| "eval_steps_per_second": 4.416, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018918120011823827, | |
| "grad_norm": 0.9874446392059326, | |
| "learning_rate": 0.0003, | |
| "loss": 1.4419, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02837718001773574, | |
| "grad_norm": 0.8229495286941528, | |
| "learning_rate": 0.000299878360437632, | |
| "loss": 1.2491, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03783624002364765, | |
| "grad_norm": 0.6731188297271729, | |
| "learning_rate": 0.00029951366095324104, | |
| "loss": 1.0968, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04729530002955956, | |
| "grad_norm": 0.7858128547668457, | |
| "learning_rate": 0.00029890655875994835, | |
| "loss": 1.0792, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05675436003547148, | |
| "grad_norm": 0.7995796799659729, | |
| "learning_rate": 0.0002980581478969406, | |
| "loss": 1.1033, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06621342004138339, | |
| "grad_norm": 0.616423487663269, | |
| "learning_rate": 0.00029696995725793764, | |
| "loss": 0.942, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0756724800472953, | |
| "grad_norm": 0.8099045753479004, | |
| "learning_rate": 0.00029564394783602234, | |
| "loss": 1.0823, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08513154005320721, | |
| "grad_norm": 0.7018675208091736, | |
| "learning_rate": 0.0002940825091897988, | |
| "loss": 1.1322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09459060005911912, | |
| "grad_norm": 0.6773211359977722, | |
| "learning_rate": 0.00029228845513724634, | |
| "loss": 1.1547, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10404966006503104, | |
| "grad_norm": 0.6189546585083008, | |
| "learning_rate": 0.00029026501868502873, | |
| "loss": 1.0361, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11350872007094295, | |
| "grad_norm": 0.623130202293396, | |
| "learning_rate": 0.0002880158462023983, | |
| "loss": 1.0837, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12296778007685487, | |
| "grad_norm": 0.55083829164505, | |
| "learning_rate": 0.0002855449908501917, | |
| "loss": 0.8752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13242684008276678, | |
| "grad_norm": 0.5632800459861755, | |
| "learning_rate": 0.00028285690527676035, | |
| "loss": 1.0141, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14188590008867868, | |
| "grad_norm": 0.5698175430297852, | |
| "learning_rate": 0.000279956433593997, | |
| "loss": 0.9583, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1513449600945906, | |
| "grad_norm": 0.6257957220077515, | |
| "learning_rate": 0.00027684880264791867, | |
| "loss": 1.1261, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16080402010050251, | |
| "grad_norm": 0.6792426109313965, | |
| "learning_rate": 0.00027353961259953696, | |
| "loss": 1.076, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17026308010641442, | |
| "grad_norm": 0.5756276249885559, | |
| "learning_rate": 0.00027003482683298933, | |
| "loss": 0.9779, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17972214011232635, | |
| "grad_norm": 0.6053583025932312, | |
| "learning_rate": 0.00026634076120911777, | |
| "loss": 1.168, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18918120011823825, | |
| "grad_norm": 0.5745776891708374, | |
| "learning_rate": 0.0002624640726838608, | |
| "loss": 0.997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19864026012415018, | |
| "grad_norm": 0.5367314219474792, | |
| "learning_rate": 0.00025841174731196877, | |
| "loss": 0.9194, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20809932013006208, | |
| "grad_norm": 0.5325618386268616, | |
| "learning_rate": 0.000254191087657661, | |
| "loss": 1.0697, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21755838013597398, | |
| "grad_norm": 0.6518679857254028, | |
| "learning_rate": 0.0002498096996349117, | |
| "loss": 1.1852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2270174401418859, | |
| "grad_norm": 0.6570560336112976, | |
| "learning_rate": 0.0002452754788010787, | |
| "loss": 1.1949, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2364765001477978, | |
| "grad_norm": 0.6248823404312134, | |
| "learning_rate": 0.00024059659612857536, | |
| "loss": 1.1139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2364765001477978, | |
| "eval_loss": 0.9684370160102844, | |
| "eval_runtime": 11.3298, | |
| "eval_samples_per_second": 4.413, | |
| "eval_steps_per_second": 4.413, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24593556015370974, | |
| "grad_norm": 0.6149452924728394, | |
| "learning_rate": 0.00023578148328022626, | |
| "loss": 1.2, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2553946201596216, | |
| "grad_norm": 0.5431950688362122, | |
| "learning_rate": 0.00023083881741484068, | |
| "loss": 1.1115, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26485368016553357, | |
| "grad_norm": 0.5499697923660278, | |
| "learning_rate": 0.00022577750555038587, | |
| "loss": 0.8515, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27431274017144547, | |
| "grad_norm": 0.45134755969047546, | |
| "learning_rate": 0.000220606668512939, | |
| "loss": 0.8734, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.28377180017735737, | |
| "grad_norm": 0.539884626865387, | |
| "learning_rate": 0.00021533562450034164, | |
| "loss": 0.9292, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29323086018326927, | |
| "grad_norm": 0.4615366458892822, | |
| "learning_rate": 0.00020997387229017774, | |
| "loss": 0.8075, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3026899201891812, | |
| "grad_norm": 0.4927918612957001, | |
| "learning_rate": 0.00020453107412233428, | |
| "loss": 0.8667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.31214898019509313, | |
| "grad_norm": 0.49951159954071045, | |
| "learning_rate": 0.0001990170382869919, | |
| "loss": 0.977, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.32160804020100503, | |
| "grad_norm": 0.4911053478717804, | |
| "learning_rate": 0.00019344170144942302, | |
| "loss": 0.8319, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33106710020691693, | |
| "grad_norm": 0.5060461163520813, | |
| "learning_rate": 0.00018781511074344962, | |
| "loss": 0.9303, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.34052616021282883, | |
| "grad_norm": 0.554681658744812, | |
| "learning_rate": 0.0001821474056658286, | |
| "loss": 0.9563, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3499852202187408, | |
| "grad_norm": 0.5921431183815002, | |
| "learning_rate": 0.00017644879980419374, | |
| "loss": 1.0516, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3594442802246527, | |
| "grad_norm": 0.4988238215446472, | |
| "learning_rate": 0.00017072956243148002, | |
| "loss": 0.9642, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3689033402305646, | |
| "grad_norm": 0.4554699659347534, | |
| "learning_rate": 0.000165, | |
| "loss": 0.8114, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3783624002364765, | |
| "grad_norm": 0.4806513488292694, | |
| "learning_rate": 0.00015927043756852, | |
| "loss": 1.0024, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3878214602423884, | |
| "grad_norm": 0.5541513562202454, | |
| "learning_rate": 0.0001535512001958063, | |
| "loss": 1.0891, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.39728052024830035, | |
| "grad_norm": 0.4677070081233978, | |
| "learning_rate": 0.00014785259433417133, | |
| "loss": 0.8085, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40673958025421225, | |
| "grad_norm": 0.4648246467113495, | |
| "learning_rate": 0.00014218488925655037, | |
| "loss": 0.8908, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.41619864026012415, | |
| "grad_norm": 0.5301900506019592, | |
| "learning_rate": 0.00013655829855057698, | |
| "loss": 0.9752, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.42565770026603605, | |
| "grad_norm": 0.5299180746078491, | |
| "learning_rate": 0.00013098296171300814, | |
| "loss": 1.0093, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43511676027194796, | |
| "grad_norm": 0.5281239151954651, | |
| "learning_rate": 0.0001254689258776657, | |
| "loss": 0.9709, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4445758202778599, | |
| "grad_norm": 0.5601954460144043, | |
| "learning_rate": 0.00012002612770982222, | |
| "loss": 1.0698, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4540348802837718, | |
| "grad_norm": 0.5613210201263428, | |
| "learning_rate": 0.00011466437549965834, | |
| "loss": 1.0451, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4634939402896837, | |
| "grad_norm": 0.6079455018043518, | |
| "learning_rate": 0.00010939333148706099, | |
| "loss": 1.0703, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4729530002955956, | |
| "grad_norm": 0.6424407362937927, | |
| "learning_rate": 0.00010422249444961407, | |
| "loss": 1.2829, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4729530002955956, | |
| "eval_loss": 0.9108405113220215, | |
| "eval_runtime": 11.325, | |
| "eval_samples_per_second": 4.415, | |
| "eval_steps_per_second": 4.415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4824120603015075, | |
| "grad_norm": 0.629723846912384, | |
| "learning_rate": 9.916118258515936e-05, | |
| "loss": 1.1712, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4918711203074195, | |
| "grad_norm": 0.7443132996559143, | |
| "learning_rate": 9.421851671977372e-05, | |
| "loss": 1.1707, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5013301803133313, | |
| "grad_norm": 0.46892011165618896, | |
| "learning_rate": 8.940340387142462e-05, | |
| "loss": 0.8093, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5107892403192432, | |
| "grad_norm": 0.43437010049819946, | |
| "learning_rate": 8.47245211989213e-05, | |
| "loss": 0.8652, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5202483003251552, | |
| "grad_norm": 0.3998465836048126, | |
| "learning_rate": 8.019030036508827e-05, | |
| "loss": 0.8075, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5297073603310671, | |
| "grad_norm": 0.4319959282875061, | |
| "learning_rate": 7.580891234233904e-05, | |
| "loss": 0.8248, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.539166420336979, | |
| "grad_norm": 0.4736616015434265, | |
| "learning_rate": 7.158825268803127e-05, | |
| "loss": 0.9148, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5486254803428909, | |
| "grad_norm": 0.3903331458568573, | |
| "learning_rate": 6.75359273161392e-05, | |
| "loss": 0.8549, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5580845403488028, | |
| "grad_norm": 0.428145170211792, | |
| "learning_rate": 6.365923879088219e-05, | |
| "loss": 0.8272, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5675436003547147, | |
| "grad_norm": 0.5180810689926147, | |
| "learning_rate": 5.996517316701069e-05, | |
| "loss": 0.9229, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5770026603606266, | |
| "grad_norm": 0.47326382994651794, | |
| "learning_rate": 5.646038740046304e-05, | |
| "loss": 0.768, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5864617203665385, | |
| "grad_norm": 0.47181880474090576, | |
| "learning_rate": 5.315119735208132e-05, | |
| "loss": 0.973, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5959207803724504, | |
| "grad_norm": 0.48134690523147583, | |
| "learning_rate": 5.004356640600297e-05, | |
| "loss": 0.8445, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6053798403783625, | |
| "grad_norm": 0.4601708650588989, | |
| "learning_rate": 4.71430947232396e-05, | |
| "loss": 0.898, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6148389003842744, | |
| "grad_norm": 0.4865597188472748, | |
| "learning_rate": 4.4455009149808265e-05, | |
| "loss": 0.922, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6242979603901863, | |
| "grad_norm": 0.47632795572280884, | |
| "learning_rate": 4.1984153797601665e-05, | |
| "loss": 0.936, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6337570203960982, | |
| "grad_norm": 0.5297707319259644, | |
| "learning_rate": 3.9734981314971234e-05, | |
| "loss": 0.9437, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6432160804020101, | |
| "grad_norm": 0.46655818819999695, | |
| "learning_rate": 3.771154486275363e-05, | |
| "loss": 0.7435, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.652675140407922, | |
| "grad_norm": 0.513863205909729, | |
| "learning_rate": 3.591749081020113e-05, | |
| "loss": 0.9687, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6621342004138339, | |
| "grad_norm": 0.5340255498886108, | |
| "learning_rate": 3.435605216397765e-05, | |
| "loss": 1.0353, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6715932604197458, | |
| "grad_norm": 0.45835715532302856, | |
| "learning_rate": 3.303004274206237e-05, | |
| "loss": 0.864, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6810523204256577, | |
| "grad_norm": 0.4819653034210205, | |
| "learning_rate": 3.194185210305936e-05, | |
| "loss": 1.0022, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6905113804315696, | |
| "grad_norm": 0.5713886618614197, | |
| "learning_rate": 3.1093441240051626e-05, | |
| "loss": 1.0681, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6999704404374816, | |
| "grad_norm": 0.5911141633987427, | |
| "learning_rate": 3.048633904675892e-05, | |
| "loss": 0.9129, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7094295004433935, | |
| "grad_norm": 0.5698217749595642, | |
| "learning_rate": 3.012163956236801e-05, | |
| "loss": 1.0666, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7094295004433935, | |
| "eval_loss": 0.8948501348495483, | |
| "eval_runtime": 11.3345, | |
| "eval_samples_per_second": 4.411, | |
| "eval_steps_per_second": 4.411, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7188885604493054, | |
| "grad_norm": 0.5917747616767883, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.0924, | |
| "step": 76 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 76, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.002568490422108e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |