guyhadad01's picture
Training in progress, step 1042, checkpoint
7962dff verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1042,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04798464491362764,
"grad_norm": 8.8125,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.484,
"step": 50
},
{
"epoch": 0.09596928982725528,
"grad_norm": 8.4375,
"learning_rate": 4.714285714285714e-05,
"loss": 0.2763,
"step": 100
},
{
"epoch": 0.14395393474088292,
"grad_norm": 6.65625,
"learning_rate": 4.765208110992529e-05,
"loss": 0.2883,
"step": 150
},
{
"epoch": 0.19193857965451055,
"grad_norm": 6.125,
"learning_rate": 4.4983991462113126e-05,
"loss": 0.2636,
"step": 200
},
{
"epoch": 0.2399232245681382,
"grad_norm": 5.875,
"learning_rate": 4.231590181430096e-05,
"loss": 0.2626,
"step": 250
},
{
"epoch": 0.28790786948176583,
"grad_norm": 5.9375,
"learning_rate": 3.9647812166488794e-05,
"loss": 0.2219,
"step": 300
},
{
"epoch": 0.33589251439539347,
"grad_norm": 5.125,
"learning_rate": 3.697972251867663e-05,
"loss": 0.2227,
"step": 350
},
{
"epoch": 0.3838771593090211,
"grad_norm": 5.15625,
"learning_rate": 3.431163287086446e-05,
"loss": 0.207,
"step": 400
},
{
"epoch": 0.43186180422264875,
"grad_norm": 3.703125,
"learning_rate": 3.16435432230523e-05,
"loss": 0.1853,
"step": 450
},
{
"epoch": 0.4798464491362764,
"grad_norm": 4.125,
"learning_rate": 2.897545357524013e-05,
"loss": 0.177,
"step": 500
},
{
"epoch": 0.527831094049904,
"grad_norm": 4.09375,
"learning_rate": 2.6307363927427965e-05,
"loss": 0.1739,
"step": 550
},
{
"epoch": 0.5758157389635317,
"grad_norm": 4.0,
"learning_rate": 2.3639274279615796e-05,
"loss": 0.1743,
"step": 600
},
{
"epoch": 0.6238003838771593,
"grad_norm": 3.28125,
"learning_rate": 2.097118463180363e-05,
"loss": 0.1574,
"step": 650
},
{
"epoch": 0.6717850287907869,
"grad_norm": 4.125,
"learning_rate": 1.830309498399146e-05,
"loss": 0.1586,
"step": 700
},
{
"epoch": 0.7197696737044146,
"grad_norm": 3.875,
"learning_rate": 1.5635005336179295e-05,
"loss": 0.1473,
"step": 750
},
{
"epoch": 0.7677543186180422,
"grad_norm": 3.671875,
"learning_rate": 1.2966915688367129e-05,
"loss": 0.1547,
"step": 800
},
{
"epoch": 0.8157389635316699,
"grad_norm": 3.75,
"learning_rate": 1.0298826040554963e-05,
"loss": 0.146,
"step": 850
},
{
"epoch": 0.8637236084452975,
"grad_norm": 4.09375,
"learning_rate": 7.630736392742796e-06,
"loss": 0.1453,
"step": 900
},
{
"epoch": 0.9117082533589251,
"grad_norm": 3.765625,
"learning_rate": 4.96264674493063e-06,
"loss": 0.1349,
"step": 950
},
{
"epoch": 0.9596928982725528,
"grad_norm": 3.96875,
"learning_rate": 2.294557097118463e-06,
"loss": 0.1433,
"step": 1000
}
],
"logging_steps": 50,
"max_steps": 1042,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 512,
"trial_name": null,
"trial_params": null
}