dada22231's picture
Training in progress, step 33, checkpoint
5773989 verified
{
"best_metric": 0.6004818081855774,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 3.0697674418604652,
"eval_steps": 25,
"global_step": 33,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09302325581395349,
"grad_norm": 1.616852879524231,
"learning_rate": 5e-05,
"loss": 2.0474,
"step": 1
},
{
"epoch": 0.09302325581395349,
"eval_loss": 2.9822559356689453,
"eval_runtime": 3.4381,
"eval_samples_per_second": 14.543,
"eval_steps_per_second": 3.781,
"step": 1
},
{
"epoch": 0.18604651162790697,
"grad_norm": 2.1614630222320557,
"learning_rate": 0.0001,
"loss": 2.4994,
"step": 2
},
{
"epoch": 0.27906976744186046,
"grad_norm": 1.7438641786575317,
"learning_rate": 9.976911955263529e-05,
"loss": 1.8839,
"step": 3
},
{
"epoch": 0.37209302325581395,
"grad_norm": 1.934104561805725,
"learning_rate": 9.907884735636226e-05,
"loss": 1.7032,
"step": 4
},
{
"epoch": 0.46511627906976744,
"grad_norm": 2.6693766117095947,
"learning_rate": 9.793626653800219e-05,
"loss": 1.7775,
"step": 5
},
{
"epoch": 0.5581395348837209,
"grad_norm": 1.5809624195098877,
"learning_rate": 9.635310152291039e-05,
"loss": 0.8558,
"step": 6
},
{
"epoch": 0.6511627906976745,
"grad_norm": 2.7533814907073975,
"learning_rate": 9.43455977265062e-05,
"loss": 0.9982,
"step": 7
},
{
"epoch": 0.7441860465116279,
"grad_norm": 2.5589840412139893,
"learning_rate": 9.193435485432745e-05,
"loss": 0.7236,
"step": 8
},
{
"epoch": 0.8372093023255814,
"grad_norm": 1.5994662046432495,
"learning_rate": 8.914411552117559e-05,
"loss": 0.7621,
"step": 9
},
{
"epoch": 0.9302325581395349,
"grad_norm": 1.975174903869629,
"learning_rate": 8.600351135840589e-05,
"loss": 0.8413,
"step": 10
},
{
"epoch": 1.0232558139534884,
"grad_norm": 1.1943004131317139,
"learning_rate": 8.254476921464484e-05,
"loss": 0.6243,
"step": 11
},
{
"epoch": 1.1162790697674418,
"grad_norm": 0.5302379727363586,
"learning_rate": 7.880338046471331e-05,
"loss": 0.4453,
"step": 12
},
{
"epoch": 1.2093023255813953,
"grad_norm": 0.6890483498573303,
"learning_rate": 7.481773682009356e-05,
"loss": 0.5305,
"step": 13
},
{
"epoch": 1.302325581395349,
"grad_norm": 0.4094037115573883,
"learning_rate": 7.062873637801692e-05,
"loss": 0.4227,
"step": 14
},
{
"epoch": 1.3953488372093024,
"grad_norm": 0.454261839389801,
"learning_rate": 6.627936395164243e-05,
"loss": 0.4896,
"step": 15
},
{
"epoch": 1.4883720930232558,
"grad_norm": 0.5503323078155518,
"learning_rate": 6.181424998770595e-05,
"loss": 0.5499,
"step": 16
},
{
"epoch": 1.5813953488372094,
"grad_norm": 0.331122487783432,
"learning_rate": 5.727921259774208e-05,
"loss": 0.3566,
"step": 17
},
{
"epoch": 1.6744186046511627,
"grad_norm": 0.4989646375179291,
"learning_rate": 5.2720787402257935e-05,
"loss": 0.4685,
"step": 18
},
{
"epoch": 1.7674418604651163,
"grad_norm": 0.30750206112861633,
"learning_rate": 4.8185750012294065e-05,
"loss": 0.4377,
"step": 19
},
{
"epoch": 1.8604651162790697,
"grad_norm": 0.41947314143180847,
"learning_rate": 4.372063604835758e-05,
"loss": 0.47,
"step": 20
},
{
"epoch": 1.9534883720930232,
"grad_norm": 0.5602025389671326,
"learning_rate": 3.93712636219831e-05,
"loss": 0.5443,
"step": 21
},
{
"epoch": 2.046511627906977,
"grad_norm": 0.5113930702209473,
"learning_rate": 3.518226317990646e-05,
"loss": 0.4755,
"step": 22
},
{
"epoch": 2.13953488372093,
"grad_norm": 0.27189022302627563,
"learning_rate": 3.119661953528671e-05,
"loss": 0.3877,
"step": 23
},
{
"epoch": 2.2325581395348837,
"grad_norm": 0.15714497864246368,
"learning_rate": 2.745523078535517e-05,
"loss": 0.4046,
"step": 24
},
{
"epoch": 2.3255813953488373,
"grad_norm": 0.2902805805206299,
"learning_rate": 2.39964886415941e-05,
"loss": 0.3778,
"step": 25
},
{
"epoch": 2.3255813953488373,
"eval_loss": 0.6004818081855774,
"eval_runtime": 3.5049,
"eval_samples_per_second": 14.266,
"eval_steps_per_second": 3.709,
"step": 25
},
{
"epoch": 2.4186046511627906,
"grad_norm": 0.2399173527956009,
"learning_rate": 2.0855884478824412e-05,
"loss": 0.4546,
"step": 26
},
{
"epoch": 2.511627906976744,
"grad_norm": 0.21842080354690552,
"learning_rate": 1.806564514567258e-05,
"loss": 0.4159,
"step": 27
},
{
"epoch": 2.604651162790698,
"grad_norm": 0.09714235365390778,
"learning_rate": 1.5654402273493805e-05,
"loss": 0.3683,
"step": 28
},
{
"epoch": 2.697674418604651,
"grad_norm": 0.1338994950056076,
"learning_rate": 1.3646898477089626e-05,
"loss": 0.405,
"step": 29
},
{
"epoch": 2.7906976744186047,
"grad_norm": 0.18371757864952087,
"learning_rate": 1.2063733461997805e-05,
"loss": 0.4067,
"step": 30
},
{
"epoch": 2.883720930232558,
"grad_norm": 0.12735600769519806,
"learning_rate": 1.092115264363775e-05,
"loss": 0.4753,
"step": 31
},
{
"epoch": 2.9767441860465116,
"grad_norm": 0.1807902604341507,
"learning_rate": 1.023088044736472e-05,
"loss": 0.4981,
"step": 32
},
{
"epoch": 3.0697674418604652,
"grad_norm": 0.3723318576812744,
"learning_rate": 1e-05,
"loss": 0.4004,
"step": 33
}
],
"logging_steps": 1,
"max_steps": 33,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 3.953855388419359e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}