lesso14's picture
Training in progress, step 25, checkpoint
09d28a1 verified
raw
history blame
6.44 kB
{
"best_metric": 2.044719934463501,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.02498126405196103,
"eval_steps": 5,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0009992505620784412,
"grad_norm": 3.7193825244903564,
"learning_rate": 1e-05,
"loss": 10.5487,
"step": 1
},
{
"epoch": 0.0009992505620784412,
"eval_loss": 2.5447795391082764,
"eval_runtime": 85.4906,
"eval_samples_per_second": 4.936,
"eval_steps_per_second": 2.468,
"step": 1
},
{
"epoch": 0.0019985011241568824,
"grad_norm": 2.6072869300842285,
"learning_rate": 2e-05,
"loss": 9.1591,
"step": 2
},
{
"epoch": 0.0029977516862353237,
"grad_norm": 2.9801859855651855,
"learning_rate": 3e-05,
"loss": 10.1539,
"step": 3
},
{
"epoch": 0.003997002248313765,
"grad_norm": 2.7656972408294678,
"learning_rate": 4e-05,
"loss": 9.1485,
"step": 4
},
{
"epoch": 0.004996252810392206,
"grad_norm": 1.8618946075439453,
"learning_rate": 5e-05,
"loss": 8.3817,
"step": 5
},
{
"epoch": 0.004996252810392206,
"eval_loss": 2.538808584213257,
"eval_runtime": 85.6506,
"eval_samples_per_second": 4.927,
"eval_steps_per_second": 2.463,
"step": 5
},
{
"epoch": 0.005995503372470647,
"grad_norm": 2.6605968475341797,
"learning_rate": 6e-05,
"loss": 8.9484,
"step": 6
},
{
"epoch": 0.0069947539345490885,
"grad_norm": 2.3858630657196045,
"learning_rate": 7e-05,
"loss": 9.6266,
"step": 7
},
{
"epoch": 0.00799400449662753,
"grad_norm": 2.107030153274536,
"learning_rate": 8e-05,
"loss": 8.4471,
"step": 8
},
{
"epoch": 0.008993255058705971,
"grad_norm": 3.73014235496521,
"learning_rate": 9e-05,
"loss": 10.4107,
"step": 9
},
{
"epoch": 0.009992505620784412,
"grad_norm": 3.2218165397644043,
"learning_rate": 0.0001,
"loss": 10.6904,
"step": 10
},
{
"epoch": 0.009992505620784412,
"eval_loss": 2.4495997428894043,
"eval_runtime": 85.8435,
"eval_samples_per_second": 4.916,
"eval_steps_per_second": 2.458,
"step": 10
},
{
"epoch": 0.010991756182862853,
"grad_norm": 4.003271579742432,
"learning_rate": 9.890738003669029e-05,
"loss": 10.2673,
"step": 11
},
{
"epoch": 0.011991006744941295,
"grad_norm": 4.2326555252075195,
"learning_rate": 9.567727288213005e-05,
"loss": 9.8006,
"step": 12
},
{
"epoch": 0.012990257307019736,
"grad_norm": 2.9779212474823,
"learning_rate": 9.045084971874738e-05,
"loss": 9.2463,
"step": 13
},
{
"epoch": 0.013989507869098177,
"grad_norm": 4.528616428375244,
"learning_rate": 8.345653031794292e-05,
"loss": 8.8378,
"step": 14
},
{
"epoch": 0.014988758431176618,
"grad_norm": 4.985352993011475,
"learning_rate": 7.500000000000001e-05,
"loss": 10.015,
"step": 15
},
{
"epoch": 0.014988758431176618,
"eval_loss": 2.1829171180725098,
"eval_runtime": 85.9558,
"eval_samples_per_second": 4.91,
"eval_steps_per_second": 2.455,
"step": 15
},
{
"epoch": 0.01598800899325506,
"grad_norm": 7.104391098022461,
"learning_rate": 6.545084971874738e-05,
"loss": 7.9238,
"step": 16
},
{
"epoch": 0.0169872595553335,
"grad_norm": 5.407159805297852,
"learning_rate": 5.522642316338268e-05,
"loss": 8.0276,
"step": 17
},
{
"epoch": 0.017986510117411942,
"grad_norm": 6.533193111419678,
"learning_rate": 4.477357683661734e-05,
"loss": 8.7472,
"step": 18
},
{
"epoch": 0.01898576067949038,
"grad_norm": 7.912476062774658,
"learning_rate": 3.4549150281252636e-05,
"loss": 9.1709,
"step": 19
},
{
"epoch": 0.019985011241568824,
"grad_norm": 4.488398551940918,
"learning_rate": 2.500000000000001e-05,
"loss": 6.9152,
"step": 20
},
{
"epoch": 0.019985011241568824,
"eval_loss": 2.0622997283935547,
"eval_runtime": 85.8087,
"eval_samples_per_second": 4.918,
"eval_steps_per_second": 2.459,
"step": 20
},
{
"epoch": 0.020984261803647264,
"grad_norm": 5.099001407623291,
"learning_rate": 1.6543469682057106e-05,
"loss": 8.2414,
"step": 21
},
{
"epoch": 0.021983512365725707,
"grad_norm": 5.913036346435547,
"learning_rate": 9.549150281252633e-06,
"loss": 9.1997,
"step": 22
},
{
"epoch": 0.022982762927804146,
"grad_norm": 6.968205451965332,
"learning_rate": 4.322727117869951e-06,
"loss": 9.1247,
"step": 23
},
{
"epoch": 0.02398201348988259,
"grad_norm": 7.832215785980225,
"learning_rate": 1.0926199633097157e-06,
"loss": 6.6349,
"step": 24
},
{
"epoch": 0.02498126405196103,
"grad_norm": 5.372540473937988,
"learning_rate": 0.0,
"loss": 7.4628,
"step": 25
},
{
"epoch": 0.02498126405196103,
"eval_loss": 2.044719934463501,
"eval_runtime": 85.8196,
"eval_samples_per_second": 4.917,
"eval_steps_per_second": 2.459,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 25,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"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": 7915560763392000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}