checkpoint-600/trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 0.6,
 "eval_steps": 100,
 "global_step": 600,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.03,
 "learning_rate": 0.0001666666666666667,
 "loss": 0.8745,
 "step": 25
 },
 {
 "epoch": 0.05,
 "learning_rate": 0.00019979028262377118,
 "loss": 0.8093,
 "step": 50
 },
 {
 "epoch": 0.07,
 "learning_rate": 0.00019893981312363562,
 "loss": 0.7357,
 "step": 75
 },
 {
 "epoch": 0.1,
 "learning_rate": 0.00019744105246469263,
 "loss": 0.7535,
 "step": 100
 },
 {
 "epoch": 0.1,
 "eval_loss": 0.4003306031227112,
 "eval_runtime": 1.7839,
 "eval_samples_per_second": 2.242,
 "eval_steps_per_second": 0.561,
 "step": 100
 },
 {
 "epoch": 0.12,
 "learning_rate": 0.0001953038210948861,
 "loss": 0.7249,
 "step": 125
 },
 {
 "epoch": 0.15,
 "learning_rate": 0.00019254212296427044,
 "loss": 0.7118,
 "step": 150
 },
 {
 "epoch": 0.17,
 "learning_rate": 0.00018917405376582145,
 "loss": 0.7467,
 "step": 175
 },
 {
 "epoch": 0.2,
 "learning_rate": 0.00018522168236559695,
 "loss": 0.6714,
 "step": 200
 },
 {
 "epoch": 0.2,
 "eval_loss": 0.3684937059879303,
 "eval_runtime": 1.7853,
 "eval_samples_per_second": 2.24,
 "eval_steps_per_second": 0.56,
 "step": 200
 },
 {
 "epoch": 0.23,
 "learning_rate": 0.00018071090619916093,
 "loss": 0.654,
 "step": 225
 },
 {
 "epoch": 0.25,
 "learning_rate": 0.00017567128158176953,
 "loss": 0.6392,
 "step": 250
 },
 {
 "epoch": 0.28,
 "learning_rate": 0.00017013583004418993,
 "loss": 0.5745,
 "step": 275
 },
 {
 "epoch": 0.3,
 "learning_rate": 0.000164140821963114,
 "loss": 0.5364,
 "step": 300
 },
 {
 "epoch": 0.3,
 "eval_loss": 0.3665352761745453,
 "eval_runtime": 1.7852,
 "eval_samples_per_second": 2.241,
 "eval_steps_per_second": 0.56,
 "step": 300
 },
 {
 "epoch": 0.33,
 "learning_rate": 0.00015772553890390197,
 "loss": 0.5693,
 "step": 325
 },
 {
 "epoch": 0.35,
 "learning_rate": 0.00015093201623287631,
 "loss": 0.563,
 "step": 350
 },
 {
 "epoch": 0.38,
 "learning_rate": 0.00014380476768566824,
 "loss": 0.5478,
 "step": 375
 },
 {
 "epoch": 0.4,
 "learning_rate": 0.00013639049369634876,
 "loss": 0.5763,
 "step": 400
 },
 {
 "epoch": 0.4,
 "eval_loss": 0.3363753855228424,
 "eval_runtime": 1.7851,
 "eval_samples_per_second": 2.241,
 "eval_steps_per_second": 0.56,
 "step": 400
 },
 {
 "epoch": 0.42,
 "learning_rate": 0.00012873777539848283,
 "loss": 0.4891,
 "step": 425
 },
 {
 "epoch": 0.45,
 "learning_rate": 0.00012089675630312754,
 "loss": 0.5331,
 "step": 450
 },
 {
 "epoch": 0.47,
 "learning_rate": 0.00011291881373954065,
 "loss": 0.5679,
 "step": 475
 },
 {
 "epoch": 0.5,
 "learning_rate": 0.00010485622221144484,
 "loss": 0.5982,
 "step": 500
 },
 {
 "epoch": 0.5,
 "eval_loss": 0.3186224400997162,
 "eval_runtime": 1.7828,
 "eval_samples_per_second": 2.244,
 "eval_steps_per_second": 0.561,
 "step": 500
 },
 {
 "epoch": 0.53,
 "learning_rate": 9.676181087466444e-05,
 "loss": 0.5467,
 "step": 525
 },
 {
 "epoch": 0.55,
 "learning_rate": 8.868861738047158e-05,
 "loss": 0.5706,
 "step": 550
 },
 {
 "epoch": 0.57,
 "learning_rate": 8.068954035279121e-05,
 "loss": 0.504,
 "step": 575
 },
 {
 "epoch": 0.6,
 "learning_rate": 7.281699277636572e-05,
 "loss": 0.5267,
 "step": 600
 },
 {
 "epoch": 0.6,
 "eval_loss": 0.32175499200820923,
 "eval_runtime": 1.7846,
 "eval_samples_per_second": 2.241,
 "eval_steps_per_second": 0.56,
 "step": 600
 }
 ],
 "logging_steps": 25,
 "max_steps": 1000,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 9223372036854775807,
 "save_steps": 100,
 "total_flos": 8.961043791347712e+17,
 "train_batch_size": 4,
 "trial_name": null,
 "trial_params": null
}