dada22231's picture
Training in progress, step 75, checkpoint
3e15b06 verified
raw
history blame
14.7 kB
{
"best_metric": 0.22316619753837585,
"best_model_checkpoint": "miner_id_24/checkpoint-75",
"epoch": 0.9799918334013883,
"eval_steps": 25,
"global_step": 75,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013066557778685178,
"grad_norm": 1.6932507753372192,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.2152,
"step": 1
},
{
"epoch": 0.013066557778685178,
"eval_loss": 1.5535104274749756,
"eval_runtime": 1.5142,
"eval_samples_per_second": 33.021,
"eval_steps_per_second": 8.585,
"step": 1
},
{
"epoch": 0.026133115557370357,
"grad_norm": 2.5225236415863037,
"learning_rate": 6.666666666666667e-05,
"loss": 1.3169,
"step": 2
},
{
"epoch": 0.039199673336055535,
"grad_norm": 2.8033957481384277,
"learning_rate": 0.0001,
"loss": 1.3364,
"step": 3
},
{
"epoch": 0.05226623111474071,
"grad_norm": 2.008617877960205,
"learning_rate": 9.99571699711836e-05,
"loss": 1.2427,
"step": 4
},
{
"epoch": 0.06533278889342589,
"grad_norm": 2.0534799098968506,
"learning_rate": 9.982876141412856e-05,
"loss": 1.3013,
"step": 5
},
{
"epoch": 0.07839934667211107,
"grad_norm": 2.1992785930633545,
"learning_rate": 9.961501876182148e-05,
"loss": 1.2599,
"step": 6
},
{
"epoch": 0.09146590445079625,
"grad_norm": 2.2852184772491455,
"learning_rate": 9.931634888554937e-05,
"loss": 1.1142,
"step": 7
},
{
"epoch": 0.10453246222948143,
"grad_norm": 1.6609108448028564,
"learning_rate": 9.893332032039701e-05,
"loss": 1.521,
"step": 8
},
{
"epoch": 0.1175990200081666,
"grad_norm": 2.5087709426879883,
"learning_rate": 9.846666218300807e-05,
"loss": 1.3596,
"step": 9
},
{
"epoch": 0.13066557778685178,
"grad_norm": 2.0769166946411133,
"learning_rate": 9.791726278367022e-05,
"loss": 1.2476,
"step": 10
},
{
"epoch": 0.14373213556553696,
"grad_norm": 2.1793136596679688,
"learning_rate": 9.728616793536588e-05,
"loss": 1.3515,
"step": 11
},
{
"epoch": 0.15679869334422214,
"grad_norm": 3.35315203666687,
"learning_rate": 9.657457896300791e-05,
"loss": 1.6377,
"step": 12
},
{
"epoch": 0.16986525112290732,
"grad_norm": 1.5212485790252686,
"learning_rate": 9.578385041664925e-05,
"loss": 0.9341,
"step": 13
},
{
"epoch": 0.1829318089015925,
"grad_norm": 1.2225775718688965,
"learning_rate": 9.491548749301997e-05,
"loss": 0.9495,
"step": 14
},
{
"epoch": 0.19599836668027767,
"grad_norm": 2.4777283668518066,
"learning_rate": 9.397114317029975e-05,
"loss": 0.7017,
"step": 15
},
{
"epoch": 0.20906492445896285,
"grad_norm": 1.527767300605774,
"learning_rate": 9.295261506157986e-05,
"loss": 0.7389,
"step": 16
},
{
"epoch": 0.22213148223764803,
"grad_norm": 1.3528121709823608,
"learning_rate": 9.186184199300464e-05,
"loss": 0.8243,
"step": 17
},
{
"epoch": 0.2351980400163332,
"grad_norm": 1.3979260921478271,
"learning_rate": 9.070090031310558e-05,
"loss": 0.7762,
"step": 18
},
{
"epoch": 0.2482645977950184,
"grad_norm": 2.6196300983428955,
"learning_rate": 8.947199994035401e-05,
"loss": 0.6698,
"step": 19
},
{
"epoch": 0.26133115557370357,
"grad_norm": 1.5927413702011108,
"learning_rate": 8.817748015645558e-05,
"loss": 0.8977,
"step": 20
},
{
"epoch": 0.2743977133523887,
"grad_norm": 1.7954849004745483,
"learning_rate": 8.681980515339464e-05,
"loss": 1.12,
"step": 21
},
{
"epoch": 0.2874642711310739,
"grad_norm": 2.6149048805236816,
"learning_rate": 8.540155934270471e-05,
"loss": 0.9328,
"step": 22
},
{
"epoch": 0.3005308289097591,
"grad_norm": 2.0966615676879883,
"learning_rate": 8.392544243589427e-05,
"loss": 0.8724,
"step": 23
},
{
"epoch": 0.3135973866884443,
"grad_norm": 2.034907579421997,
"learning_rate": 8.239426430539243e-05,
"loss": 1.0333,
"step": 24
},
{
"epoch": 0.32666394446712943,
"grad_norm": 3.575545310974121,
"learning_rate": 8.081093963579707e-05,
"loss": 1.5723,
"step": 25
},
{
"epoch": 0.32666394446712943,
"eval_loss": 0.5558741092681885,
"eval_runtime": 1.5449,
"eval_samples_per_second": 32.364,
"eval_steps_per_second": 8.415,
"step": 25
},
{
"epoch": 0.33973050224581464,
"grad_norm": 1.975691318511963,
"learning_rate": 7.917848237560709e-05,
"loss": 0.5943,
"step": 26
},
{
"epoch": 0.3527970600244998,
"grad_norm": 1.5834639072418213,
"learning_rate": 7.75e-05,
"loss": 0.5643,
"step": 27
},
{
"epoch": 0.365863617803185,
"grad_norm": 1.6365801095962524,
"learning_rate": 7.577868759557654e-05,
"loss": 0.4526,
"step": 28
},
{
"epoch": 0.37893017558187014,
"grad_norm": 1.463999629020691,
"learning_rate": 7.401782177833148e-05,
"loss": 0.4972,
"step": 29
},
{
"epoch": 0.39199673336055535,
"grad_norm": 1.2677172422409058,
"learning_rate": 7.222075445642904e-05,
"loss": 0.5389,
"step": 30
},
{
"epoch": 0.4050632911392405,
"grad_norm": 2.432539224624634,
"learning_rate": 7.03909064496551e-05,
"loss": 0.4597,
"step": 31
},
{
"epoch": 0.4181298489179257,
"grad_norm": 2.4917757511138916,
"learning_rate": 6.853176097769229e-05,
"loss": 0.4929,
"step": 32
},
{
"epoch": 0.43119640669661086,
"grad_norm": 1.3739546537399292,
"learning_rate": 6.664685702961344e-05,
"loss": 0.9248,
"step": 33
},
{
"epoch": 0.44426296447529606,
"grad_norm": 1.6721895933151245,
"learning_rate": 6.473978262721463e-05,
"loss": 0.6351,
"step": 34
},
{
"epoch": 0.4573295222539812,
"grad_norm": 1.3729504346847534,
"learning_rate": 6.281416799501188e-05,
"loss": 0.5844,
"step": 35
},
{
"epoch": 0.4703960800326664,
"grad_norm": 1.3768748044967651,
"learning_rate": 6.087367864990233e-05,
"loss": 0.6757,
"step": 36
},
{
"epoch": 0.48346263781135157,
"grad_norm": 2.0230472087860107,
"learning_rate": 5.8922008423644624e-05,
"loss": 1.0381,
"step": 37
},
{
"epoch": 0.4965291955900368,
"grad_norm": 1.3043603897094727,
"learning_rate": 5.696287243144013e-05,
"loss": 0.4569,
"step": 38
},
{
"epoch": 0.509595753368722,
"grad_norm": 0.9272847175598145,
"learning_rate": 5.500000000000001e-05,
"loss": 0.4936,
"step": 39
},
{
"epoch": 0.5226623111474071,
"grad_norm": 1.6384899616241455,
"learning_rate": 5.303712756855988e-05,
"loss": 0.4535,
"step": 40
},
{
"epoch": 0.5357288689260923,
"grad_norm": 1.546187400817871,
"learning_rate": 5.107799157635538e-05,
"loss": 0.3763,
"step": 41
},
{
"epoch": 0.5487954267047774,
"grad_norm": 1.2767608165740967,
"learning_rate": 4.912632135009769e-05,
"loss": 0.4207,
"step": 42
},
{
"epoch": 0.5618619844834626,
"grad_norm": 1.1065655946731567,
"learning_rate": 4.718583200498814e-05,
"loss": 0.3935,
"step": 43
},
{
"epoch": 0.5749285422621478,
"grad_norm": 2.4505350589752197,
"learning_rate": 4.526021737278538e-05,
"loss": 0.2702,
"step": 44
},
{
"epoch": 0.587995100040833,
"grad_norm": 1.1374635696411133,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.6616,
"step": 45
},
{
"epoch": 0.6010616578195181,
"grad_norm": 1.3470594882965088,
"learning_rate": 4.146823902230772e-05,
"loss": 0.7169,
"step": 46
},
{
"epoch": 0.6141282155982033,
"grad_norm": 1.4238591194152832,
"learning_rate": 3.960909355034491e-05,
"loss": 0.4089,
"step": 47
},
{
"epoch": 0.6271947733768886,
"grad_norm": 1.1624187231063843,
"learning_rate": 3.777924554357096e-05,
"loss": 0.5297,
"step": 48
},
{
"epoch": 0.6402613311555737,
"grad_norm": 1.2812923192977905,
"learning_rate": 3.598217822166854e-05,
"loss": 0.5576,
"step": 49
},
{
"epoch": 0.6533278889342589,
"grad_norm": 3.029040575027466,
"learning_rate": 3.422131240442349e-05,
"loss": 0.9427,
"step": 50
},
{
"epoch": 0.6533278889342589,
"eval_loss": 0.3033914864063263,
"eval_runtime": 1.537,
"eval_samples_per_second": 32.532,
"eval_steps_per_second": 8.458,
"step": 50
},
{
"epoch": 0.666394446712944,
"grad_norm": 0.9900059103965759,
"learning_rate": 3.250000000000001e-05,
"loss": 0.3231,
"step": 51
},
{
"epoch": 0.6794610044916293,
"grad_norm": 0.8345087766647339,
"learning_rate": 3.082151762439293e-05,
"loss": 0.3644,
"step": 52
},
{
"epoch": 0.6925275622703144,
"grad_norm": 0.8801731467247009,
"learning_rate": 2.9189060364202943e-05,
"loss": 0.2791,
"step": 53
},
{
"epoch": 0.7055941200489996,
"grad_norm": 1.1393957138061523,
"learning_rate": 2.760573569460757e-05,
"loss": 0.2965,
"step": 54
},
{
"epoch": 0.7186606778276847,
"grad_norm": 0.9782978892326355,
"learning_rate": 2.6074557564105727e-05,
"loss": 0.2393,
"step": 55
},
{
"epoch": 0.73172723560637,
"grad_norm": 0.8556644916534424,
"learning_rate": 2.459844065729529e-05,
"loss": 0.2027,
"step": 56
},
{
"epoch": 0.7447937933850551,
"grad_norm": 1.0292524099349976,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.275,
"step": 57
},
{
"epoch": 0.7578603511637403,
"grad_norm": 1.2255464792251587,
"learning_rate": 2.1822519843544424e-05,
"loss": 0.6167,
"step": 58
},
{
"epoch": 0.7709269089424254,
"grad_norm": 1.345024824142456,
"learning_rate": 2.0528000059645997e-05,
"loss": 0.51,
"step": 59
},
{
"epoch": 0.7839934667211107,
"grad_norm": 2.0753092765808105,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.3936,
"step": 60
},
{
"epoch": 0.7970600244997958,
"grad_norm": 1.9613157510757446,
"learning_rate": 1.8138158006995364e-05,
"loss": 0.4177,
"step": 61
},
{
"epoch": 0.810126582278481,
"grad_norm": 1.782265543937683,
"learning_rate": 1.7047384938420154e-05,
"loss": 0.5354,
"step": 62
},
{
"epoch": 0.8231931400571662,
"grad_norm": 0.880858302116394,
"learning_rate": 1.602885682970026e-05,
"loss": 0.227,
"step": 63
},
{
"epoch": 0.8362596978358514,
"grad_norm": 0.643760621547699,
"learning_rate": 1.5084512506980026e-05,
"loss": 0.339,
"step": 64
},
{
"epoch": 0.8493262556145366,
"grad_norm": 0.610495924949646,
"learning_rate": 1.4216149583350754e-05,
"loss": 0.2043,
"step": 65
},
{
"epoch": 0.8623928133932217,
"grad_norm": 0.7079125642776489,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.2392,
"step": 66
},
{
"epoch": 0.8754593711719069,
"grad_norm": 0.6936648488044739,
"learning_rate": 1.2713832064634126e-05,
"loss": 0.2807,
"step": 67
},
{
"epoch": 0.8885259289505921,
"grad_norm": 0.7526812553405762,
"learning_rate": 1.2082737216329794e-05,
"loss": 0.2831,
"step": 68
},
{
"epoch": 0.9015924867292773,
"grad_norm": 1.716686725616455,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.117,
"step": 69
},
{
"epoch": 0.9146590445079624,
"grad_norm": 0.9851632714271545,
"learning_rate": 1.1066679679603e-05,
"loss": 0.4664,
"step": 70
},
{
"epoch": 0.9277256022866476,
"grad_norm": 1.2416988611221313,
"learning_rate": 1.0683651114450641e-05,
"loss": 0.6231,
"step": 71
},
{
"epoch": 0.9407921600653328,
"grad_norm": 0.8936472535133362,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.3633,
"step": 72
},
{
"epoch": 0.953858717844018,
"grad_norm": 1.051101803779602,
"learning_rate": 1.017123858587145e-05,
"loss": 0.4201,
"step": 73
},
{
"epoch": 0.9669252756227031,
"grad_norm": 1.0521873235702515,
"learning_rate": 1.00428300288164e-05,
"loss": 0.395,
"step": 74
},
{
"epoch": 0.9799918334013883,
"grad_norm": 2.4216976165771484,
"learning_rate": 1e-05,
"loss": 0.6176,
"step": 75
},
{
"epoch": 0.9799918334013883,
"eval_loss": 0.22316619753837585,
"eval_runtime": 1.5353,
"eval_samples_per_second": 32.566,
"eval_steps_per_second": 8.467,
"step": 75
}
],
"logging_steps": 1,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"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": 4.42951368966144e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}