trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 2.991097922848665,
 "eval_steps": 500,
 "global_step": 126,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.11869436201780416,
 "grad_norm": 0.6501234173774719,
 "learning_rate": 0.0002,
 "loss": 2.5793,
 "step": 5
 },
 {
 "epoch": 0.23738872403560832,
 "grad_norm": 0.9226903915405273,
 "learning_rate": 0.0002,
 "loss": 2.2797,
 "step": 10
 },
 {
 "epoch": 0.3560830860534125,
 "grad_norm": 1.3594255447387695,
 "learning_rate": 0.0002,
 "loss": 1.8775,
 "step": 15
 },
 {
 "epoch": 0.47477744807121663,
 "grad_norm": 1.391525149345398,
 "learning_rate": 0.0002,
 "loss": 1.4896,
 "step": 20
 },
 {
 "epoch": 0.5934718100890207,
 "grad_norm": 0.9402475357055664,
 "learning_rate": 0.0002,
 "loss": 1.2145,
 "step": 25
 },
 {
 "epoch": 0.712166172106825,
 "grad_norm": 0.516862690448761,
 "learning_rate": 0.0002,
 "loss": 1.0708,
 "step": 30
 },
 {
 "epoch": 0.8308605341246291,
 "grad_norm": 0.39975354075431824,
 "learning_rate": 0.0002,
 "loss": 0.9909,
 "step": 35
 },
 {
 "epoch": 0.9495548961424333,
 "grad_norm": 0.4522175192832947,
 "learning_rate": 0.0002,
 "loss": 0.9651,
 "step": 40
 },
 {
 "epoch": 1.0682492581602374,
 "grad_norm": 0.4957733452320099,
 "learning_rate": 0.0002,
 "loss": 0.9213,
 "step": 45
 },
 {
 "epoch": 1.1869436201780414,
 "grad_norm": 0.45304545760154724,
 "learning_rate": 0.0002,
 "loss": 0.9047,
 "step": 50
 },
 {
 "epoch": 1.3056379821958457,
 "grad_norm": 0.6747499108314514,
 "learning_rate": 0.0002,
 "loss": 0.8819,
 "step": 55
 },
 {
 "epoch": 1.4243323442136497,
 "grad_norm": 0.7882275581359863,
 "learning_rate": 0.0002,
 "loss": 0.8359,
 "step": 60
 },
 {
 "epoch": 1.543026706231454,
 "grad_norm": 0.42021647095680237,
 "learning_rate": 0.0002,
 "loss": 0.8254,
 "step": 65
 },
 {
 "epoch": 1.6617210682492582,
 "grad_norm": 0.41371551156044006,
 "learning_rate": 0.0002,
 "loss": 0.7991,
 "step": 70
 },
 {
 "epoch": 1.7804154302670623,
 "grad_norm": 0.45561087131500244,
 "learning_rate": 0.0002,
 "loss": 0.7887,
 "step": 75
 },
 {
 "epoch": 1.8991097922848663,
 "grad_norm": 0.40611913800239563,
 "learning_rate": 0.0002,
 "loss": 0.7941,
 "step": 80
 },
 {
 "epoch": 2.0178041543026706,
 "grad_norm": 0.5473902225494385,
 "learning_rate": 0.0002,
 "loss": 0.7779,
 "step": 85
 },
 {
 "epoch": 2.136498516320475,
 "grad_norm": 0.4852384924888611,
 "learning_rate": 0.0002,
 "loss": 0.7517,
 "step": 90
 },
 {
 "epoch": 2.255192878338279,
 "grad_norm": 0.4257807731628418,
 "learning_rate": 0.0002,
 "loss": 0.7545,
 "step": 95
 },
 {
 "epoch": 2.373887240356083,
 "grad_norm": 0.4694693386554718,
 "learning_rate": 0.0002,
 "loss": 0.7389,
 "step": 100
 },
 {
 "epoch": 2.492581602373887,
 "grad_norm": 0.46692556142807007,
 "learning_rate": 0.0002,
 "loss": 0.7348,
 "step": 105
 },
 {
 "epoch": 2.6112759643916914,
 "grad_norm": 0.38663822412490845,
 "learning_rate": 0.0002,
 "loss": 0.7368,
 "step": 110
 },
 {
 "epoch": 2.7299703264094957,
 "grad_norm": 0.4077226519584656,
 "learning_rate": 0.0002,
 "loss": 0.7335,
 "step": 115
 },
 {
 "epoch": 2.8486646884272995,
 "grad_norm": 0.4740726351737976,
 "learning_rate": 0.0002,
 "loss": 0.7462,
 "step": 120
 },
 {
 "epoch": 2.9673590504451037,
 "grad_norm": 0.40621665120124817,
 "learning_rate": 0.0002,
 "loss": 0.75,
 "step": 125
 }
 ],
 "logging_steps": 5,
 "max_steps": 126,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 3,
 "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": 9.310063237541069e+16,
 "train_batch_size": 4,
 "trial_name": null,
 "trial_params": null
}