trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 1.1261261261261262,
 "eval_steps": 500,
 "global_step": 250,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.11261261261261261,
 "grad_norm": 0.618191659450531,
 "learning_rate": 0.00019510565162951537,
 "loss": 1.2486,
 "step": 25
 },
 {
 "epoch": 0.22522522522522523,
 "grad_norm": 0.8095678687095642,
 "learning_rate": 0.00018090169943749476,
 "loss": 1.2557,
 "step": 50
 },
 {
 "epoch": 0.33783783783783783,
 "grad_norm": 0.578891396522522,
 "learning_rate": 0.00015877852522924732,
 "loss": 1.257,
 "step": 75
 },
 {
 "epoch": 0.45045045045045046,
 "grad_norm": 0.6523413062095642,
 "learning_rate": 0.00013090169943749476,
 "loss": 1.2573,
 "step": 100
 },
 {
 "epoch": 0.5630630630630631,
 "grad_norm": 0.5457090735435486,
 "learning_rate": 0.0001,
 "loss": 1.2009,
 "step": 125
 },
 {
 "epoch": 0.6756756756756757,
 "grad_norm": 0.5979616045951843,
 "learning_rate": 6.909830056250527e-05,
 "loss": 1.2826,
 "step": 150
 },
 {
 "epoch": 0.7882882882882883,
 "grad_norm": 0.6098126173019409,
 "learning_rate": 4.12214747707527e-05,
 "loss": 1.3606,
 "step": 175
 },
 {
 "epoch": 0.9009009009009009,
 "grad_norm": 0.7838721871376038,
 "learning_rate": 1.9098300562505266e-05,
 "loss": 1.3275,
 "step": 200
 },
 {
 "epoch": 1.0135135135135136,
 "grad_norm": 0.5452545881271362,
 "learning_rate": 4.8943483704846475e-06,
 "loss": 1.31,
 "step": 225
 },
 {
 "epoch": 1.1261261261261262,
 "grad_norm": 0.5899876356124878,
 "learning_rate": 0.0,
 "loss": 1.2133,
 "step": 250
 }
 ],
 "logging_steps": 25,
 "max_steps": 250,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 2,
 "save_steps": 500,
 "total_flos": 814586836156416.0,
 "train_batch_size": 8,
 "trial_name": null,
 "trial_params": null
}