checkpoint-126/trainer_state.json

{
 "best_metric": null,
 "best_model_checkpoint": null,
 "epoch": 2.9473684210526314,
 "eval_steps": 500,
 "global_step": 126,
 "is_hyper_param_search": false,
 "is_local_process_zero": true,
 "is_world_process_zero": true,
 "log_history": [
 {
 "epoch": 0.11695906432748537,
 "grad_norm": 1.7820518016815186,
 "learning_rate": 0.0002,
 "loss": 3.8601,
 "step": 5
 },
 {
 "epoch": 0.23391812865497075,
 "grad_norm": 2.071708917617798,
 "learning_rate": 0.0002,
 "loss": 3.0122,
 "step": 10
 },
 {
 "epoch": 0.3508771929824561,
 "grad_norm": 3.0540826320648193,
 "learning_rate": 0.0002,
 "loss": 2.3113,
 "step": 15
 },
 {
 "epoch": 0.4678362573099415,
 "grad_norm": 2.741673707962036,
 "learning_rate": 0.0002,
 "loss": 1.862,
 "step": 20
 },
 {
 "epoch": 0.5847953216374269,
 "grad_norm": 1.061865210533142,
 "learning_rate": 0.0002,
 "loss": 1.5215,
 "step": 25
 },
 {
 "epoch": 0.7017543859649122,
 "grad_norm": 1.1919221878051758,
 "learning_rate": 0.0002,
 "loss": 1.3492,
 "step": 30
 },
 {
 "epoch": 0.8187134502923976,
 "grad_norm": 1.1614408493041992,
 "learning_rate": 0.0002,
 "loss": 1.3886,
 "step": 35
 },
 {
 "epoch": 0.935672514619883,
 "grad_norm": 1.2684136629104614,
 "learning_rate": 0.0002,
 "loss": 1.3099,
 "step": 40
 },
 {
 "epoch": 1.0526315789473684,
 "grad_norm": 1.0680867433547974,
 "learning_rate": 0.0002,
 "loss": 1.2574,
 "step": 45
 },
 {
 "epoch": 1.1695906432748537,
 "grad_norm": 2.7324814796447754,
 "learning_rate": 0.0002,
 "loss": 1.2232,
 "step": 50
 },
 {
 "epoch": 1.286549707602339,
 "grad_norm": 8.411725044250488,
 "learning_rate": 0.0002,
 "loss": 1.0544,
 "step": 55
 },
 {
 "epoch": 1.4035087719298245,
 "grad_norm": 1.4623502492904663,
 "learning_rate": 0.0002,
 "loss": 0.9857,
 "step": 60
 },
 {
 "epoch": 1.52046783625731,
 "grad_norm": 1.1131906509399414,
 "learning_rate": 0.0002,
 "loss": 0.9013,
 "step": 65
 },
 {
 "epoch": 1.6374269005847952,
 "grad_norm": 1.1788413524627686,
 "learning_rate": 0.0002,
 "loss": 0.9038,
 "step": 70
 },
 {
 "epoch": 1.7543859649122808,
 "grad_norm": 1.288320541381836,
 "learning_rate": 0.0002,
 "loss": 0.954,
 "step": 75
 },
 {
 "epoch": 1.871345029239766,
 "grad_norm": 1.06460702419281,
 "learning_rate": 0.0002,
 "loss": 0.9295,
 "step": 80
 },
 {
 "epoch": 1.9883040935672516,
 "grad_norm": 1.1221821308135986,
 "learning_rate": 0.0002,
 "loss": 0.8751,
 "step": 85
 },
 {
 "epoch": 2.1052631578947367,
 "grad_norm": 0.9662391543388367,
 "learning_rate": 0.0002,
 "loss": 0.8753,
 "step": 90
 },
 {
 "epoch": 2.2222222222222223,
 "grad_norm": 1.5002328157424927,
 "learning_rate": 0.0002,
 "loss": 0.8752,
 "step": 95
 },
 {
 "epoch": 2.3391812865497075,
 "grad_norm": 1.0283668041229248,
 "learning_rate": 0.0002,
 "loss": 0.86,
 "step": 100
 },
 {
 "epoch": 2.456140350877193,
 "grad_norm": 1.232816457748413,
 "learning_rate": 0.0002,
 "loss": 0.8915,
 "step": 105
 },
 {
 "epoch": 2.573099415204678,
 "grad_norm": 1.2354693412780762,
 "learning_rate": 0.0002,
 "loss": 0.8731,
 "step": 110
 },
 {
 "epoch": 2.690058479532164,
 "grad_norm": 1.081337809562683,
 "learning_rate": 0.0002,
 "loss": 0.7528,
 "step": 115
 },
 {
 "epoch": 2.807017543859649,
 "grad_norm": 1.3441332578659058,
 "learning_rate": 0.0002,
 "loss": 0.8583,
 "step": 120
 },
 {
 "epoch": 2.9239766081871346,
 "grad_norm": 1.032715916633606,
 "learning_rate": 0.0002,
 "loss": 0.8275,
 "step": 125
 }
 ],
 "logging_steps": 5,
 "max_steps": 126,
 "num_input_tokens_seen": 0,
 "num_train_epochs": 3,
 "save_steps": 500,
 "stateful_callbacks": {
 "TrainerControl": {
 "args": {
 "should_epoch_stop": false,
 "should_evaluate": false,
 "should_log": false,
 "should_save": true,
 "should_training_stop": true
 },
 "attributes": {}
 }
 },
 "total_flos": 5.514015933663437e+16,
 "train_batch_size": 2,
 "trial_name": null,
 "trial_params": null
}