| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07797270955165692, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002599090318388564, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.3925, | |
| "eval_samples_per_second": 12.171, | |
| "eval_steps_per_second": 6.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01299545159194282, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8245, | |
| "eval_samples_per_second": 12.71, | |
| "eval_steps_per_second": 6.394, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02599090318388564, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.7967, | |
| "eval_samples_per_second": 12.738, | |
| "eval_steps_per_second": 6.408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8027, | |
| "eval_samples_per_second": 12.732, | |
| "eval_steps_per_second": 6.405, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05198180636777128, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8453, | |
| "eval_samples_per_second": 12.689, | |
| "eval_steps_per_second": 6.384, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05458089668615984, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0649772579597141, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8328, | |
| "eval_samples_per_second": 12.702, | |
| "eval_steps_per_second": 6.39, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "eval_loss": NaN, | |
| "eval_runtime": 12.8013, | |
| "eval_samples_per_second": 12.733, | |
| "eval_steps_per_second": 6.406, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2736772790353920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |