dada22231's picture
Training in progress, step 50, checkpoint
fe7c7e3 verified
{
"best_metric": 2.3959906101226807,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.04893265643158603,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009786531286317206,
"grad_norm": 0.8316358923912048,
"learning_rate": 5e-05,
"loss": 2.4264,
"step": 1
},
{
"epoch": 0.0009786531286317206,
"eval_loss": 2.862811326980591,
"eval_runtime": 3.8608,
"eval_samples_per_second": 12.951,
"eval_steps_per_second": 3.367,
"step": 1
},
{
"epoch": 0.0019573062572634413,
"grad_norm": 0.9247562885284424,
"learning_rate": 0.0001,
"loss": 2.5591,
"step": 2
},
{
"epoch": 0.002935959385895162,
"grad_norm": 0.8996179699897766,
"learning_rate": 9.990365154573717e-05,
"loss": 2.611,
"step": 3
},
{
"epoch": 0.0039146125145268825,
"grad_norm": 0.6197950839996338,
"learning_rate": 9.961501876182148e-05,
"loss": 2.4587,
"step": 4
},
{
"epoch": 0.004893265643158603,
"grad_norm": 0.5590848326683044,
"learning_rate": 9.913533761814537e-05,
"loss": 2.5131,
"step": 5
},
{
"epoch": 0.005871918771790324,
"grad_norm": 0.8712125420570374,
"learning_rate": 9.846666218300807e-05,
"loss": 2.4739,
"step": 6
},
{
"epoch": 0.006850571900422044,
"grad_norm": 0.6620206832885742,
"learning_rate": 9.761185582727977e-05,
"loss": 2.4627,
"step": 7
},
{
"epoch": 0.007829225029053765,
"grad_norm": 0.49366331100463867,
"learning_rate": 9.657457896300791e-05,
"loss": 2.443,
"step": 8
},
{
"epoch": 0.008807878157685486,
"grad_norm": 0.48205986618995667,
"learning_rate": 9.535927336897098e-05,
"loss": 2.4574,
"step": 9
},
{
"epoch": 0.009786531286317205,
"grad_norm": 0.530735194683075,
"learning_rate": 9.397114317029975e-05,
"loss": 2.4442,
"step": 10
},
{
"epoch": 0.010765184414948926,
"grad_norm": 0.5516226291656494,
"learning_rate": 9.241613255361455e-05,
"loss": 2.3873,
"step": 11
},
{
"epoch": 0.011743837543580648,
"grad_norm": 0.6918548941612244,
"learning_rate": 9.070090031310558e-05,
"loss": 2.3429,
"step": 12
},
{
"epoch": 0.012722490672212369,
"grad_norm": 0.5481558442115784,
"learning_rate": 8.883279133655399e-05,
"loss": 2.1984,
"step": 13
},
{
"epoch": 0.013701143800844088,
"grad_norm": 0.6193399429321289,
"learning_rate": 8.681980515339464e-05,
"loss": 2.3338,
"step": 14
},
{
"epoch": 0.014679796929475809,
"grad_norm": 0.4581556022167206,
"learning_rate": 8.467056167950311e-05,
"loss": 2.2973,
"step": 15
},
{
"epoch": 0.01565845005810753,
"grad_norm": 0.32524430751800537,
"learning_rate": 8.239426430539243e-05,
"loss": 2.2362,
"step": 16
},
{
"epoch": 0.01663710318673925,
"grad_norm": 0.2754608690738678,
"learning_rate": 8.000066048588211e-05,
"loss": 2.3678,
"step": 17
},
{
"epoch": 0.017615756315370972,
"grad_norm": 0.2892760634422302,
"learning_rate": 7.75e-05,
"loss": 2.3839,
"step": 18
},
{
"epoch": 0.01859440944400269,
"grad_norm": 0.3418925106525421,
"learning_rate": 7.490299105985507e-05,
"loss": 2.3053,
"step": 19
},
{
"epoch": 0.01957306257263441,
"grad_norm": 0.3567667305469513,
"learning_rate": 7.222075445642904e-05,
"loss": 2.3271,
"step": 20
},
{
"epoch": 0.020551715701266134,
"grad_norm": 0.3940460979938507,
"learning_rate": 6.946477593864228e-05,
"loss": 2.3585,
"step": 21
},
{
"epoch": 0.021530368829897853,
"grad_norm": 0.43177926540374756,
"learning_rate": 6.664685702961344e-05,
"loss": 2.3478,
"step": 22
},
{
"epoch": 0.022509021958529572,
"grad_norm": 0.45484182238578796,
"learning_rate": 6.377906449072578e-05,
"loss": 2.3482,
"step": 23
},
{
"epoch": 0.023487675087161295,
"grad_norm": 0.4482674300670624,
"learning_rate": 6.087367864990233e-05,
"loss": 2.3099,
"step": 24
},
{
"epoch": 0.024466328215793014,
"grad_norm": 0.5691775679588318,
"learning_rate": 5.794314081535644e-05,
"loss": 2.4265,
"step": 25
},
{
"epoch": 0.024466328215793014,
"eval_loss": 2.410771131515503,
"eval_runtime": 3.4876,
"eval_samples_per_second": 14.336,
"eval_steps_per_second": 3.727,
"step": 25
},
{
"epoch": 0.025444981344424737,
"grad_norm": 0.19927345216274261,
"learning_rate": 5.500000000000001e-05,
"loss": 2.1858,
"step": 26
},
{
"epoch": 0.026423634473056457,
"grad_norm": 0.24525891244411469,
"learning_rate": 5.205685918464356e-05,
"loss": 2.2758,
"step": 27
},
{
"epoch": 0.027402287601688176,
"grad_norm": 0.28260111808776855,
"learning_rate": 4.912632135009769e-05,
"loss": 2.3156,
"step": 28
},
{
"epoch": 0.0283809407303199,
"grad_norm": 0.30988043546676636,
"learning_rate": 4.6220935509274235e-05,
"loss": 2.3343,
"step": 29
},
{
"epoch": 0.029359593858951618,
"grad_norm": 0.3335058093070984,
"learning_rate": 4.3353142970386564e-05,
"loss": 2.2584,
"step": 30
},
{
"epoch": 0.030338246987583337,
"grad_norm": 0.32451608777046204,
"learning_rate": 4.053522406135775e-05,
"loss": 2.291,
"step": 31
},
{
"epoch": 0.03131690011621506,
"grad_norm": 0.342134028673172,
"learning_rate": 3.777924554357096e-05,
"loss": 2.28,
"step": 32
},
{
"epoch": 0.03229555324484678,
"grad_norm": 0.3195323348045349,
"learning_rate": 3.509700894014496e-05,
"loss": 2.3299,
"step": 33
},
{
"epoch": 0.0332742063734785,
"grad_norm": 0.3132987916469574,
"learning_rate": 3.250000000000001e-05,
"loss": 2.3096,
"step": 34
},
{
"epoch": 0.03425285950211022,
"grad_norm": 0.37992510199546814,
"learning_rate": 2.9999339514117912e-05,
"loss": 2.3594,
"step": 35
},
{
"epoch": 0.035231512630741944,
"grad_norm": 0.376974880695343,
"learning_rate": 2.760573569460757e-05,
"loss": 2.2945,
"step": 36
},
{
"epoch": 0.036210165759373664,
"grad_norm": 0.42907246947288513,
"learning_rate": 2.53294383204969e-05,
"loss": 2.3236,
"step": 37
},
{
"epoch": 0.03718881888800538,
"grad_norm": 0.1865878850221634,
"learning_rate": 2.3180194846605367e-05,
"loss": 2.1561,
"step": 38
},
{
"epoch": 0.0381674720166371,
"grad_norm": 0.18192711472511292,
"learning_rate": 2.1167208663446025e-05,
"loss": 2.2334,
"step": 39
},
{
"epoch": 0.03914612514526882,
"grad_norm": 0.2045622020959854,
"learning_rate": 1.9299099686894423e-05,
"loss": 2.2695,
"step": 40
},
{
"epoch": 0.04012477827390054,
"grad_norm": 0.21859441697597504,
"learning_rate": 1.758386744638546e-05,
"loss": 2.2435,
"step": 41
},
{
"epoch": 0.04110343140253227,
"grad_norm": 0.23119929432868958,
"learning_rate": 1.602885682970026e-05,
"loss": 2.2306,
"step": 42
},
{
"epoch": 0.04208208453116399,
"grad_norm": 0.25025153160095215,
"learning_rate": 1.464072663102903e-05,
"loss": 2.3045,
"step": 43
},
{
"epoch": 0.043060737659795706,
"grad_norm": 0.26086995005607605,
"learning_rate": 1.3425421036992098e-05,
"loss": 2.2781,
"step": 44
},
{
"epoch": 0.044039390788427425,
"grad_norm": 0.27447056770324707,
"learning_rate": 1.2388144172720251e-05,
"loss": 2.2896,
"step": 45
},
{
"epoch": 0.045018043917059145,
"grad_norm": 0.2887076437473297,
"learning_rate": 1.1533337816991932e-05,
"loss": 2.2735,
"step": 46
},
{
"epoch": 0.04599669704569087,
"grad_norm": 0.3213229179382324,
"learning_rate": 1.0864662381854632e-05,
"loss": 2.3138,
"step": 47
},
{
"epoch": 0.04697535017432259,
"grad_norm": 0.3773607313632965,
"learning_rate": 1.0384981238178534e-05,
"loss": 2.3575,
"step": 48
},
{
"epoch": 0.04795400330295431,
"grad_norm": 0.39213332533836365,
"learning_rate": 1.0096348454262845e-05,
"loss": 2.2916,
"step": 49
},
{
"epoch": 0.04893265643158603,
"grad_norm": 0.47484299540519714,
"learning_rate": 1e-05,
"loss": 2.2866,
"step": 50
},
{
"epoch": 0.04893265643158603,
"eval_loss": 2.3959906101226807,
"eval_runtime": 3.4848,
"eval_samples_per_second": 14.348,
"eval_steps_per_second": 3.731,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"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": 5.969948642440643e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}