last-checkpoint/trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 5.913978494623656,
 "eval_steps": 200,
 "global_step": 2200,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.54,
 "learning_rate": 0.0002,
 "loss": 0.1582,
 "step": 200
 },
 {
 "epoch": 0.54,
 "eval_runtime": 113.8373,
 "eval_samples_per_second": 2.75,
 "eval_steps_per_second": 0.176,
 "step": 200
 },
 {
 "epoch": 1.08,
 "learning_rate": 0.0002,
 "loss": 0.077,
 "step": 400
 },
 {
 "epoch": 1.08,
 "eval_runtime": 113.8308,
 "eval_samples_per_second": 2.75,
 "eval_steps_per_second": 0.176,
 "step": 400
 },
 {
 "epoch": 1.61,
 "learning_rate": 0.0002,
 "loss": 0.0598,
 "step": 600
 },
 {
 "epoch": 1.61,
 "eval_runtime": 113.7433,
 "eval_samples_per_second": 2.752,
 "eval_steps_per_second": 0.176,
 "step": 600
 },
 {
 "epoch": 2.15,
 "learning_rate": 0.0002,
 "loss": 0.0552,
 "step": 800
 },
 {
 "epoch": 2.15,
 "eval_runtime": 113.7453,
 "eval_samples_per_second": 2.752,
 "eval_steps_per_second": 0.176,
 "step": 800
 },
 {
 "epoch": 2.69,
 "learning_rate": 0.0002,
 "loss": 0.0418,
 "step": 1000
 },
 {
 "epoch": 2.69,
 "eval_runtime": 113.7299,
 "eval_samples_per_second": 2.752,
 "eval_steps_per_second": 0.176,
 "step": 1000
 },
 {
 "epoch": 3.23,
 "learning_rate": 0.0002,
 "loss": 0.0396,
 "step": 1200
 },
 {
 "epoch": 3.23,
 "eval_runtime": 113.7472,
 "eval_samples_per_second": 2.752,
 "eval_steps_per_second": 0.176,
 "step": 1200
 },
 {
 "epoch": 3.76,
 "learning_rate": 0.0002,
 "loss": 0.0333,
 "step": 1400
 },
 {
 "epoch": 3.76,
 "eval_runtime": 113.6577,
 "eval_samples_per_second": 2.754,
 "eval_steps_per_second": 0.176,
 "step": 1400
 },
 {
 "epoch": 4.3,
 "learning_rate": 0.0002,
 "loss": 0.0303,
 "step": 1600
 },
 {
 "epoch": 4.3,
 "eval_runtime": 113.7892,
 "eval_samples_per_second": 2.751,
 "eval_steps_per_second": 0.176,
 "step": 1600
 },
 {
 "epoch": 4.84,
 "learning_rate": 0.0002,
 "loss": 0.028,
 "step": 1800
 },
 {
 "epoch": 4.84,
 "eval_runtime": 113.8547,
 "eval_samples_per_second": 2.749,
 "eval_steps_per_second": 0.176,
 "step": 1800
 },
 {
 "epoch": 5.38,
 "learning_rate": 0.0002,
 "loss": 0.0255,
 "step": 2000
 },
 {
 "epoch": 5.38,
 "eval_runtime": 113.7853,
 "eval_samples_per_second": 2.751,
 "eval_steps_per_second": 0.176,
 "step": 2000
 },
 {
 "epoch": 5.91,
 "learning_rate": 0.0002,
 "loss": 0.0259,
 "step": 2200
 },
 {
 "epoch": 5.91,
 "eval_runtime": 113.6789,
 "eval_samples_per_second": 2.753,
 "eval_steps_per_second": 0.176,
 "step": 2200
 }
 ],
 "logging_steps": 200,
 "max_steps": 2232,
 "num_train_epochs": 6,
 "save_steps": 200,
 "total_flos": 1.048086317730816e+18,
 "trial_name": null,
 "trial_params": null
}