checkpoint-204/trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 3.0,
 "eval_steps": 500,
 "global_step": 204,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.37,
 "grad_norm": 0.8090548515319824,
 "learning_rate": 9.27461139896373e-05,
 "loss": 1.9577,
 "step": 25
 },
 {
 "epoch": 0.74,
 "grad_norm": 0.6409290432929993,
 "learning_rate": 7.979274611398964e-05,
 "loss": 1.4294,
 "step": 50
 },
 {
 "epoch": 1.1,
 "grad_norm": 0.5137680768966675,
 "learning_rate": 6.683937823834198e-05,
 "loss": 1.2701,
 "step": 75
 },
 {
 "epoch": 1.47,
 "grad_norm": 0.5483278036117554,
 "learning_rate": 5.38860103626943e-05,
 "loss": 1.252,
 "step": 100
 },
 {
 "epoch": 1.84,
 "grad_norm": 0.6372405290603638,
 "learning_rate": 4.093264248704664e-05,
 "loss": 1.2229,
 "step": 125
 },
 {
 "epoch": 2.21,
 "grad_norm": 0.5785545110702515,
 "learning_rate": 2.7979274611398963e-05,
 "loss": 1.2168,
 "step": 150
 },
 {
 "epoch": 2.57,
 "grad_norm": 0.5972379446029663,
 "learning_rate": 1.5025906735751296e-05,
 "loss": 1.2007,
 "step": 175
 },
 {
 "epoch": 2.94,
 "grad_norm": 0.5962512493133545,
 "learning_rate": 2.0725388601036273e-06,
 "loss": 1.2027,
 "step": 200
 }
 ],
 "logging_steps": 25,
 "max_steps": 204,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 3,
 "save_steps": 500,
 "total_flos": 3.566640754275123e+16,
 "train_batch_size": 4,
 "trial_name": null,
 "trial_params": null
}