| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 0, |
| "global_step": 22, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 1.552415370941162, |
| "learning_rate": 0.0001, |
| "loss": 2.999, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 0.4872569739818573, |
| "learning_rate": 9.949107209404665e-05, |
| "loss": 2.5352, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 0.5185389518737793, |
| "learning_rate": 9.797464868072488e-05, |
| "loss": 2.5439, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 0.4187912344932556, |
| "learning_rate": 9.548159976772592e-05, |
| "loss": 2.3682, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 0.5700090527534485, |
| "learning_rate": 9.206267664155907e-05, |
| "loss": 2.3809, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 0.4453843832015991, |
| "learning_rate": 8.778747871771292e-05, |
| "loss": 2.208, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 0.3923359513282776, |
| "learning_rate": 8.274303669726426e-05, |
| "loss": 2.0957, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.3846656084060669, |
| "learning_rate": 7.703204087277988e-05, |
| "loss": 2.1084, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4090909090909091, |
| "grad_norm": 0.41849443316459656, |
| "learning_rate": 7.077075065009433e-05, |
| "loss": 2.1025, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 0.34051984548568726, |
| "learning_rate": 6.408662784207149e-05, |
| "loss": 2.083, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.4713260531425476, |
| "learning_rate": 5.7115741913664264e-05, |
| "loss": 2.1738, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.3551165461540222, |
| "learning_rate": 5e-05, |
| "loss": 2.0518, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5909090909090909, |
| "grad_norm": 0.37817567586898804, |
| "learning_rate": 4.288425808633575e-05, |
| "loss": 1.9263, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 0.3147885203361511, |
| "learning_rate": 3.591337215792852e-05, |
| "loss": 1.9814, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 0.45024269819259644, |
| "learning_rate": 2.9229249349905684e-05, |
| "loss": 2.0127, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.3615564703941345, |
| "learning_rate": 2.296795912722014e-05, |
| "loss": 1.9878, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7727272727272727, |
| "grad_norm": 0.3617531359195709, |
| "learning_rate": 1.725696330273575e-05, |
| "loss": 1.9639, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 0.41035544872283936, |
| "learning_rate": 1.2212521282287092e-05, |
| "loss": 1.9199, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8636363636363636, |
| "grad_norm": 0.3631443679332733, |
| "learning_rate": 7.937323358440935e-06, |
| "loss": 2.0889, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.34457656741142273, |
| "learning_rate": 4.5184002322740785e-06, |
| "loss": 1.915, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9545454545454546, |
| "grad_norm": 0.44199007749557495, |
| "learning_rate": 2.0253513192751373e-06, |
| "loss": 2.083, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.4146347641944885, |
| "learning_rate": 5.089279059533658e-07, |
| "loss": 2.1191, |
| "step": 22 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 22, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8862517073805312.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
