arcwarden46's picture
Training in progress, step 50, checkpoint
cc11b6b verified
raw
history blame
10 kB
{
"best_metric": 10.309220314025879,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.011816838995568686,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002363367799113737,
"grad_norm": 0.6855791211128235,
"learning_rate": 1e-05,
"loss": 41.5264,
"step": 1
},
{
"epoch": 0.0002363367799113737,
"eval_loss": 10.377434730529785,
"eval_runtime": 14.0654,
"eval_samples_per_second": 506.703,
"eval_steps_per_second": 126.693,
"step": 1
},
{
"epoch": 0.0004726735598227474,
"grad_norm": 0.7774749994277954,
"learning_rate": 2e-05,
"loss": 41.5087,
"step": 2
},
{
"epoch": 0.0007090103397341211,
"grad_norm": 0.7203883528709412,
"learning_rate": 3e-05,
"loss": 41.5092,
"step": 3
},
{
"epoch": 0.0009453471196454948,
"grad_norm": 0.9194475412368774,
"learning_rate": 4e-05,
"loss": 41.4963,
"step": 4
},
{
"epoch": 0.0011816838995568684,
"grad_norm": 0.8236255645751953,
"learning_rate": 5e-05,
"loss": 41.5004,
"step": 5
},
{
"epoch": 0.0014180206794682422,
"grad_norm": 0.8352706432342529,
"learning_rate": 6e-05,
"loss": 41.5035,
"step": 6
},
{
"epoch": 0.001654357459379616,
"grad_norm": 0.783135712146759,
"learning_rate": 7e-05,
"loss": 41.4943,
"step": 7
},
{
"epoch": 0.0018906942392909896,
"grad_norm": 0.8593385219573975,
"learning_rate": 8e-05,
"loss": 41.4956,
"step": 8
},
{
"epoch": 0.0021270310192023634,
"grad_norm": 0.7282395362854004,
"learning_rate": 9e-05,
"loss": 41.5,
"step": 9
},
{
"epoch": 0.002363367799113737,
"grad_norm": 0.7706413865089417,
"learning_rate": 0.0001,
"loss": 41.4767,
"step": 10
},
{
"epoch": 0.002599704579025111,
"grad_norm": 0.831785261631012,
"learning_rate": 9.999316524962345e-05,
"loss": 41.4771,
"step": 11
},
{
"epoch": 0.0028360413589364844,
"grad_norm": 0.8828088045120239,
"learning_rate": 9.997266286704631e-05,
"loss": 41.4981,
"step": 12
},
{
"epoch": 0.0030723781388478583,
"grad_norm": 0.9311338067054749,
"learning_rate": 9.993849845741524e-05,
"loss": 41.4736,
"step": 13
},
{
"epoch": 0.003308714918759232,
"grad_norm": 0.9374275803565979,
"learning_rate": 9.989068136093873e-05,
"loss": 41.4564,
"step": 14
},
{
"epoch": 0.0035450516986706058,
"grad_norm": 1.2535253763198853,
"learning_rate": 9.98292246503335e-05,
"loss": 41.4439,
"step": 15
},
{
"epoch": 0.0037813884785819793,
"grad_norm": 1.1903295516967773,
"learning_rate": 9.975414512725057e-05,
"loss": 41.4627,
"step": 16
},
{
"epoch": 0.004017725258493353,
"grad_norm": 1.0873545408248901,
"learning_rate": 9.966546331768191e-05,
"loss": 41.4695,
"step": 17
},
{
"epoch": 0.004254062038404727,
"grad_norm": 1.307550072669983,
"learning_rate": 9.956320346634876e-05,
"loss": 41.4553,
"step": 18
},
{
"epoch": 0.0044903988183161,
"grad_norm": 1.0924787521362305,
"learning_rate": 9.944739353007344e-05,
"loss": 41.4305,
"step": 19
},
{
"epoch": 0.004726735598227474,
"grad_norm": 1.4635841846466064,
"learning_rate": 9.931806517013612e-05,
"loss": 41.4392,
"step": 20
},
{
"epoch": 0.004963072378138848,
"grad_norm": 1.5859185457229614,
"learning_rate": 9.917525374361912e-05,
"loss": 41.4098,
"step": 21
},
{
"epoch": 0.005199409158050222,
"grad_norm": 1.5835672616958618,
"learning_rate": 9.901899829374047e-05,
"loss": 41.4195,
"step": 22
},
{
"epoch": 0.005435745937961595,
"grad_norm": 1.5444989204406738,
"learning_rate": 9.884934153917997e-05,
"loss": 41.4233,
"step": 23
},
{
"epoch": 0.005672082717872969,
"grad_norm": 1.6059609651565552,
"learning_rate": 9.86663298624003e-05,
"loss": 41.4173,
"step": 24
},
{
"epoch": 0.005908419497784343,
"grad_norm": 1.460196614265442,
"learning_rate": 9.847001329696653e-05,
"loss": 41.4259,
"step": 25
},
{
"epoch": 0.006144756277695717,
"grad_norm": 1.8095245361328125,
"learning_rate": 9.826044551386744e-05,
"loss": 41.3885,
"step": 26
},
{
"epoch": 0.00638109305760709,
"grad_norm": 1.8408820629119873,
"learning_rate": 9.803768380684242e-05,
"loss": 41.3851,
"step": 27
},
{
"epoch": 0.006617429837518464,
"grad_norm": 1.849540114402771,
"learning_rate": 9.780178907671789e-05,
"loss": 41.3981,
"step": 28
},
{
"epoch": 0.006853766617429837,
"grad_norm": 2.062612533569336,
"learning_rate": 9.755282581475769e-05,
"loss": 41.401,
"step": 29
},
{
"epoch": 0.0070901033973412115,
"grad_norm": 1.838928461074829,
"learning_rate": 9.729086208503174e-05,
"loss": 41.3591,
"step": 30
},
{
"epoch": 0.007326440177252585,
"grad_norm": 1.7389370203018188,
"learning_rate": 9.701596950580806e-05,
"loss": 41.3756,
"step": 31
},
{
"epoch": 0.0075627769571639586,
"grad_norm": 1.8914003372192383,
"learning_rate": 9.672822322997305e-05,
"loss": 41.3296,
"step": 32
},
{
"epoch": 0.007799113737075332,
"grad_norm": 1.6221506595611572,
"learning_rate": 9.642770192448536e-05,
"loss": 41.3345,
"step": 33
},
{
"epoch": 0.008035450516986706,
"grad_norm": 1.8179858922958374,
"learning_rate": 9.611448774886924e-05,
"loss": 41.324,
"step": 34
},
{
"epoch": 0.00827178729689808,
"grad_norm": 1.6034808158874512,
"learning_rate": 9.578866633275288e-05,
"loss": 41.3101,
"step": 35
},
{
"epoch": 0.008508124076809453,
"grad_norm": 1.5293911695480347,
"learning_rate": 9.545032675245813e-05,
"loss": 41.3234,
"step": 36
},
{
"epoch": 0.008744460856720827,
"grad_norm": 1.5270508527755737,
"learning_rate": 9.509956150664796e-05,
"loss": 41.2781,
"step": 37
},
{
"epoch": 0.0089807976366322,
"grad_norm": 1.3063689470291138,
"learning_rate": 9.473646649103818e-05,
"loss": 41.302,
"step": 38
},
{
"epoch": 0.009217134416543574,
"grad_norm": 1.4343252182006836,
"learning_rate": 9.43611409721806e-05,
"loss": 41.2907,
"step": 39
},
{
"epoch": 0.009453471196454948,
"grad_norm": 1.2640676498413086,
"learning_rate": 9.397368756032445e-05,
"loss": 41.3028,
"step": 40
},
{
"epoch": 0.009689807976366323,
"grad_norm": 1.1832501888275146,
"learning_rate": 9.357421218136386e-05,
"loss": 41.299,
"step": 41
},
{
"epoch": 0.009926144756277696,
"grad_norm": 1.1388680934906006,
"learning_rate": 9.316282404787871e-05,
"loss": 41.2568,
"step": 42
},
{
"epoch": 0.01016248153618907,
"grad_norm": 1.110303521156311,
"learning_rate": 9.273963562927695e-05,
"loss": 41.2381,
"step": 43
},
{
"epoch": 0.010398818316100443,
"grad_norm": 1.0398728847503662,
"learning_rate": 9.230476262104677e-05,
"loss": 41.2495,
"step": 44
},
{
"epoch": 0.010635155096011817,
"grad_norm": 0.9440134167671204,
"learning_rate": 9.185832391312644e-05,
"loss": 41.2392,
"step": 45
},
{
"epoch": 0.01087149187592319,
"grad_norm": 0.9111349582672119,
"learning_rate": 9.140044155740101e-05,
"loss": 41.2446,
"step": 46
},
{
"epoch": 0.011107828655834564,
"grad_norm": 0.9278951287269592,
"learning_rate": 9.093124073433463e-05,
"loss": 41.237,
"step": 47
},
{
"epoch": 0.011344165435745937,
"grad_norm": 0.7140603065490723,
"learning_rate": 9.045084971874738e-05,
"loss": 41.2872,
"step": 48
},
{
"epoch": 0.011580502215657311,
"grad_norm": 0.8889676332473755,
"learning_rate": 8.995939984474624e-05,
"loss": 41.2582,
"step": 49
},
{
"epoch": 0.011816838995568686,
"grad_norm": 1.084532380104065,
"learning_rate": 8.945702546981969e-05,
"loss": 41.2216,
"step": 50
},
{
"epoch": 0.011816838995568686,
"eval_loss": 10.309220314025879,
"eval_runtime": 14.0346,
"eval_samples_per_second": 507.815,
"eval_steps_per_second": 126.972,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 10847863701504.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}