prxy5605's picture
Training in progress, step 50, checkpoint
b2adb23 verified
raw
history blame
9.82 kB
{
"best_metric": 1.1070915460586548,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 2.061224489795918,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04081632653061224,
"grad_norm": 3.8167569637298584,
"learning_rate": 1e-05,
"loss": 5.0013,
"step": 1
},
{
"epoch": 0.04081632653061224,
"eval_loss": 1.616941213607788,
"eval_runtime": 1.9737,
"eval_samples_per_second": 21.279,
"eval_steps_per_second": 5.573,
"step": 1
},
{
"epoch": 0.08163265306122448,
"grad_norm": 4.669461250305176,
"learning_rate": 2e-05,
"loss": 5.8704,
"step": 2
},
{
"epoch": 0.12244897959183673,
"grad_norm": 5.1267523765563965,
"learning_rate": 3e-05,
"loss": 6.4629,
"step": 3
},
{
"epoch": 0.16326530612244897,
"grad_norm": 5.208806991577148,
"learning_rate": 4e-05,
"loss": 6.5763,
"step": 4
},
{
"epoch": 0.20408163265306123,
"grad_norm": 6.084200382232666,
"learning_rate": 5e-05,
"loss": 6.3859,
"step": 5
},
{
"epoch": 0.24489795918367346,
"grad_norm": 6.192852973937988,
"learning_rate": 6e-05,
"loss": 6.8691,
"step": 6
},
{
"epoch": 0.2857142857142857,
"grad_norm": 2.8081114292144775,
"learning_rate": 7e-05,
"loss": 4.8936,
"step": 7
},
{
"epoch": 0.32653061224489793,
"grad_norm": 3.0847012996673584,
"learning_rate": 8e-05,
"loss": 4.5358,
"step": 8
},
{
"epoch": 0.3673469387755102,
"grad_norm": 3.113804817199707,
"learning_rate": 9e-05,
"loss": 5.5366,
"step": 9
},
{
"epoch": 0.40816326530612246,
"grad_norm": 3.7368416786193848,
"learning_rate": 0.0001,
"loss": 5.2371,
"step": 10
},
{
"epoch": 0.4489795918367347,
"grad_norm": 4.704006671905518,
"learning_rate": 9.993977281025862e-05,
"loss": 5.5426,
"step": 11
},
{
"epoch": 0.4897959183673469,
"grad_norm": 5.045379638671875,
"learning_rate": 9.975923633360985e-05,
"loss": 5.5486,
"step": 12
},
{
"epoch": 0.5306122448979592,
"grad_norm": 2.9507429599761963,
"learning_rate": 9.945882549823906e-05,
"loss": 4.5517,
"step": 13
},
{
"epoch": 0.5714285714285714,
"grad_norm": 3.5386080741882324,
"learning_rate": 9.903926402016153e-05,
"loss": 4.6742,
"step": 14
},
{
"epoch": 0.6122448979591837,
"grad_norm": 3.318535804748535,
"learning_rate": 9.850156265972721e-05,
"loss": 4.5647,
"step": 15
},
{
"epoch": 0.6530612244897959,
"grad_norm": 3.5165586471557617,
"learning_rate": 9.784701678661045e-05,
"loss": 4.1373,
"step": 16
},
{
"epoch": 0.6938775510204082,
"grad_norm": 3.11450457572937,
"learning_rate": 9.707720325915104e-05,
"loss": 4.8453,
"step": 17
},
{
"epoch": 0.7346938775510204,
"grad_norm": 3.800767421722412,
"learning_rate": 9.619397662556435e-05,
"loss": 5.2269,
"step": 18
},
{
"epoch": 0.7755102040816326,
"grad_norm": 2.5894737243652344,
"learning_rate": 9.519946465617218e-05,
"loss": 4.6343,
"step": 19
},
{
"epoch": 0.8163265306122449,
"grad_norm": 3.455152988433838,
"learning_rate": 9.409606321741775e-05,
"loss": 4.6455,
"step": 20
},
{
"epoch": 0.8571428571428571,
"grad_norm": 3.879774808883667,
"learning_rate": 9.288643050001361e-05,
"loss": 4.2191,
"step": 21
},
{
"epoch": 0.8979591836734694,
"grad_norm": 3.647123336791992,
"learning_rate": 9.157348061512727e-05,
"loss": 5.1176,
"step": 22
},
{
"epoch": 0.9387755102040817,
"grad_norm": 3.1560988426208496,
"learning_rate": 9.016037657403224e-05,
"loss": 4.787,
"step": 23
},
{
"epoch": 0.9795918367346939,
"grad_norm": 4.0848212242126465,
"learning_rate": 8.865052266813685e-05,
"loss": 5.1071,
"step": 24
},
{
"epoch": 1.030612244897959,
"grad_norm": 2.5242435932159424,
"learning_rate": 8.704755626774796e-05,
"loss": 4.1258,
"step": 25
},
{
"epoch": 1.0714285714285714,
"grad_norm": 2.305724620819092,
"learning_rate": 8.535533905932738e-05,
"loss": 3.9269,
"step": 26
},
{
"epoch": 1.1122448979591837,
"grad_norm": 2.2410366535186768,
"learning_rate": 8.357794774235092e-05,
"loss": 4.1793,
"step": 27
},
{
"epoch": 1.153061224489796,
"grad_norm": 3.6255550384521484,
"learning_rate": 8.171966420818228e-05,
"loss": 3.9643,
"step": 28
},
{
"epoch": 1.193877551020408,
"grad_norm": 2.4370410442352295,
"learning_rate": 7.978496522462167e-05,
"loss": 3.9714,
"step": 29
},
{
"epoch": 1.2346938775510203,
"grad_norm": 3.172468423843384,
"learning_rate": 7.777851165098012e-05,
"loss": 4.4107,
"step": 30
},
{
"epoch": 1.2755102040816326,
"grad_norm": 2.33469820022583,
"learning_rate": 7.570513720966108e-05,
"loss": 4.1162,
"step": 31
},
{
"epoch": 1.316326530612245,
"grad_norm": 2.3233158588409424,
"learning_rate": 7.35698368412999e-05,
"loss": 4.0241,
"step": 32
},
{
"epoch": 1.3571428571428572,
"grad_norm": 2.4508869647979736,
"learning_rate": 7.137775467151411e-05,
"loss": 3.6321,
"step": 33
},
{
"epoch": 1.3979591836734695,
"grad_norm": 2.6886332035064697,
"learning_rate": 6.91341716182545e-05,
"loss": 3.9451,
"step": 34
},
{
"epoch": 1.4387755102040816,
"grad_norm": 2.929544687271118,
"learning_rate": 6.6844492669611e-05,
"loss": 4.2282,
"step": 35
},
{
"epoch": 1.4795918367346939,
"grad_norm": 3.1234920024871826,
"learning_rate": 6.451423386272312e-05,
"loss": 4.4053,
"step": 36
},
{
"epoch": 1.5204081632653061,
"grad_norm": 2.7144057750701904,
"learning_rate": 6.21490089951632e-05,
"loss": 3.887,
"step": 37
},
{
"epoch": 1.5612244897959182,
"grad_norm": 2.749767541885376,
"learning_rate": 5.9754516100806423e-05,
"loss": 3.7678,
"step": 38
},
{
"epoch": 1.6020408163265305,
"grad_norm": 2.5833752155303955,
"learning_rate": 5.733652372276809e-05,
"loss": 4.1636,
"step": 39
},
{
"epoch": 1.6428571428571428,
"grad_norm": 2.9307188987731934,
"learning_rate": 5.490085701647805e-05,
"loss": 3.7071,
"step": 40
},
{
"epoch": 1.683673469387755,
"grad_norm": 3.1807944774627686,
"learning_rate": 5.245338371637091e-05,
"loss": 3.6077,
"step": 41
},
{
"epoch": 1.7244897959183674,
"grad_norm": 3.5064828395843506,
"learning_rate": 5e-05,
"loss": 3.6712,
"step": 42
},
{
"epoch": 1.7653061224489797,
"grad_norm": 2.263582468032837,
"learning_rate": 4.7546616283629105e-05,
"loss": 3.4453,
"step": 43
},
{
"epoch": 1.806122448979592,
"grad_norm": 2.1443774700164795,
"learning_rate": 4.509914298352197e-05,
"loss": 3.3618,
"step": 44
},
{
"epoch": 1.8469387755102042,
"grad_norm": 2.293882131576538,
"learning_rate": 4.2663476277231915e-05,
"loss": 3.4901,
"step": 45
},
{
"epoch": 1.8877551020408163,
"grad_norm": 2.586204767227173,
"learning_rate": 4.0245483899193595e-05,
"loss": 3.9754,
"step": 46
},
{
"epoch": 1.9285714285714286,
"grad_norm": 2.9233639240264893,
"learning_rate": 3.785099100483681e-05,
"loss": 4.1341,
"step": 47
},
{
"epoch": 1.9693877551020407,
"grad_norm": 3.0968315601348877,
"learning_rate": 3.5485766137276894e-05,
"loss": 4.0113,
"step": 48
},
{
"epoch": 2.020408163265306,
"grad_norm": 2.734189748764038,
"learning_rate": 3.3155507330389e-05,
"loss": 3.6672,
"step": 49
},
{
"epoch": 2.061224489795918,
"grad_norm": 2.0895090103149414,
"learning_rate": 3.086582838174551e-05,
"loss": 3.2272,
"step": 50
},
{
"epoch": 2.061224489795918,
"eval_loss": 1.1070915460586548,
"eval_runtime": 2.0195,
"eval_samples_per_second": 20.797,
"eval_steps_per_second": 5.447,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 74,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": 3.7584000516096e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}