trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 1.0,
 "eval_steps": 500,
 "global_step": 1933,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.05173305742369374,
 "grad_norm": 0.20534886419773102,
 "learning_rate": 1.0362694300518135e-05,
 "loss": 2.372,
 "step": 100
 },
 {
 "epoch": 0.10346611484738748,
 "grad_norm": 0.3482538163661957,
 "learning_rate": 1.9999201340701767e-05,
 "loss": 2.2663,
 "step": 200
 },
 {
 "epoch": 0.1551991722710812,
 "grad_norm": 0.5800974369049072,
 "learning_rate": 1.981396800312055e-05,
 "loss": 2.1092,
 "step": 300
 },
 {
 "epoch": 0.20693222969477496,
 "grad_norm": 0.8034837245941162,
 "learning_rate": 1.9309679502465225e-05,
 "loss": 1.9755,
 "step": 400
 },
 {
 "epoch": 0.2586652871184687,
 "grad_norm": 0.8570711016654968,
 "learning_rate": 1.8502730415298682e-05,
 "loss": 1.887,
 "step": 500
 },
 {
 "epoch": 0.3103983445421624,
 "grad_norm": 0.9559773206710815,
 "learning_rate": 1.741935490832257e-05,
 "loss": 1.8283,
 "step": 600
 },
 {
 "epoch": 0.3621314019658562,
 "grad_norm": 0.9662678837776184,
 "learning_rate": 1.6094773857429165e-05,
 "loss": 1.8393,
 "step": 700
 },
 {
 "epoch": 0.4138644593895499,
 "grad_norm": 1.23440682888031,
 "learning_rate": 1.4572049806032437e-05,
 "loss": 1.7,
 "step": 800
 },
 {
 "epoch": 0.4655975168132437,
 "grad_norm": 1.1646474599838257,
 "learning_rate": 1.2900686988340288e-05,
 "loss": 1.703,
 "step": 900
 },
 {
 "epoch": 0.5173305742369374,
 "grad_norm": 1.043607473373413,
 "learning_rate": 1.1135021931248375e-05,
 "loss": 1.6366,
 "step": 1000
 },
 {
 "epoch": 0.5690636316606311,
 "grad_norm": 1.163309931755066,
 "learning_rate": 9.332456956890377e-06,
 "loss": 1.6961,
 "step": 1100
 },
 {
 "epoch": 0.6207966890843248,
 "grad_norm": 1.1546854972839355,
 "learning_rate": 7.551594015228087e-06,
 "loss": 1.6418,
 "step": 1200
 },
 {
 "epoch": 0.6725297465080187,
 "grad_norm": 1.1681387424468994,
 "learning_rate": 5.850329516366368e-06,
 "loss": 1.6815,
 "step": 1300
 },
 {
 "epoch": 0.7242628039317124,
 "grad_norm": 1.1528677940368652,
 "learning_rate": 4.283972100189098e-06,
 "loss": 1.6221,
 "step": 1400
 },
 {
 "epoch": 0.7759958613554061,
 "grad_norm": 1.3576257228851318,
 "learning_rate": 2.903444535212738e-06,
 "loss": 1.6389,
 "step": 1500
 },
 {
 "epoch": 0.8277289187790998,
 "grad_norm": 1.1139311790466309,
 "learning_rate": 1.7536282034870066e-06,
 "loss": 1.6398,
 "step": 1600
 },
 {
 "epoch": 0.8794619762027935,
 "grad_norm": 1.1810859441757202,
 "learning_rate": 8.71903992855374e-07,
 "loss": 1.678,
 "step": 1700
 },
 {
 "epoch": 0.9311950336264874,
 "grad_norm": 1.1703745126724243,
 "learning_rate": 2.8693703262333894e-07,
 "loss": 1.6531,
 "step": 1800
 },
 {
 "epoch": 0.9829280910501811,
 "grad_norm": 1.3099007606506348,
 "learning_rate": 1.774478125728729e-08,
 "loss": 1.653,
 "step": 1900
 },
 {
 "epoch": 1.0,
 "eval_loss": 1.5814313888549805,
 "eval_runtime": 31.0467,
 "eval_samples_per_second": 13.464,
 "eval_steps_per_second": 1.707,
 "step": 1933
 },
 {
 "epoch": 1.0,
 "step": 1933,
 "total_flos": 3.52000008192e+16,
 "train_loss": 1.7970823928351485,
 "train_runtime": 655.195,
 "train_samples_per_second": 5.899,
 "train_steps_per_second": 2.95
 }
 ],
 "logging_steps": 100,
 "max_steps": 1933,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 1,
 "save_steps": 500,
 "stateful_callbacks": {
 "TrainerControl": {
 "args": {
 "should_epoch_stop": false,
 "should_evaluate": false,
 "should_log": false,
 "should_save": true,
 "should_training_stop": true
 },
 "attributes": {}
 }
 },
 "total_flos": 3.52000008192e+16,
 "train_batch_size": 2,
 "trial_name": null,
 "trial_params": null
}