last-checkpoint/trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 11.650485436893204,
 "eval_steps": 200,
 "global_step": 2400,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.97,
 "learning_rate": 0.0002,
 "loss": 0.1883,
 "step": 200
 },
 {
 "epoch": 0.97,
 "eval_runtime": 21.7937,
 "eval_samples_per_second": 7.938,
 "eval_steps_per_second": 0.505,
 "step": 200
 },
 {
 "epoch": 1.94,
 "learning_rate": 0.0002,
 "loss": 0.0814,
 "step": 400
 },
 {
 "epoch": 1.94,
 "eval_runtime": 21.8179,
 "eval_samples_per_second": 7.929,
 "eval_steps_per_second": 0.504,
 "step": 400
 },
 {
 "epoch": 2.91,
 "learning_rate": 0.0002,
 "loss": 0.0547,
 "step": 600
 },
 {
 "epoch": 2.91,
 "eval_runtime": 21.793,
 "eval_samples_per_second": 7.938,
 "eval_steps_per_second": 0.505,
 "step": 600
 },
 {
 "epoch": 3.88,
 "learning_rate": 0.0002,
 "loss": 0.0419,
 "step": 800
 },
 {
 "epoch": 3.88,
 "eval_runtime": 21.8103,
 "eval_samples_per_second": 7.932,
 "eval_steps_per_second": 0.504,
 "step": 800
 },
 {
 "epoch": 4.85,
 "learning_rate": 0.0002,
 "loss": 0.0351,
 "step": 1000
 },
 {
 "epoch": 4.85,
 "eval_runtime": 21.7909,
 "eval_samples_per_second": 7.939,
 "eval_steps_per_second": 0.505,
 "step": 1000
 },
 {
 "epoch": 5.83,
 "learning_rate": 0.0002,
 "loss": 0.0309,
 "step": 1200
 },
 {
 "epoch": 5.83,
 "eval_runtime": 21.768,
 "eval_samples_per_second": 7.947,
 "eval_steps_per_second": 0.505,
 "step": 1200
 },
 {
 "epoch": 6.8,
 "learning_rate": 0.0002,
 "loss": 0.0296,
 "step": 1400
 },
 {
 "epoch": 6.8,
 "eval_runtime": 21.7916,
 "eval_samples_per_second": 7.939,
 "eval_steps_per_second": 0.505,
 "step": 1400
 },
 {
 "epoch": 7.77,
 "learning_rate": 0.0002,
 "loss": 0.0277,
 "step": 1600
 },
 {
 "epoch": 7.77,
 "eval_runtime": 21.7885,
 "eval_samples_per_second": 7.94,
 "eval_steps_per_second": 0.505,
 "step": 1600
 },
 {
 "epoch": 8.74,
 "learning_rate": 0.0002,
 "loss": 0.0277,
 "step": 1800
 },
 {
 "epoch": 8.74,
 "eval_runtime": 21.8025,
 "eval_samples_per_second": 7.935,
 "eval_steps_per_second": 0.505,
 "step": 1800
 },
 {
 "epoch": 9.71,
 "learning_rate": 0.0002,
 "loss": 0.0276,
 "step": 2000
 },
 {
 "epoch": 9.71,
 "eval_runtime": 21.8115,
 "eval_samples_per_second": 7.932,
 "eval_steps_per_second": 0.504,
 "step": 2000
 },
 {
 "epoch": 10.68,
 "learning_rate": 0.0002,
 "loss": 0.0258,
 "step": 2200
 },
 {
 "epoch": 10.68,
 "eval_runtime": 21.7533,
 "eval_samples_per_second": 7.953,
 "eval_steps_per_second": 0.506,
 "step": 2200
 },
 {
 "epoch": 11.65,
 "learning_rate": 0.0002,
 "loss": 0.0245,
 "step": 2400
 },
 {
 "epoch": 11.65,
 "eval_runtime": 21.7676,
 "eval_samples_per_second": 7.948,
 "eval_steps_per_second": 0.505,
 "step": 2400
 }
 ],
 "logging_steps": 200,
 "max_steps": 2472,
 "num_train_epochs": 12,
 "save_steps": 200,
 "total_flos": 7.726720077791232e+17,
 "trial_name": null,
 "trial_params": null
}