| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010741138560687433, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010741138560687433, | |
| "grad_norm": 2.2083053588867188, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010741138560687433, | |
| "eval_loss": 2.334104537963867, | |
| "eval_runtime": 36.9521, | |
| "eval_samples_per_second": 10.608, | |
| "eval_steps_per_second": 5.304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021482277121374865, | |
| "grad_norm": 2.335937738418579, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7871, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00322234156820623, | |
| "grad_norm": 3.0078506469726562, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0484, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00322234156820623, | |
| "eval_loss": 2.260688304901123, | |
| "eval_runtime": 37.006, | |
| "eval_samples_per_second": 10.593, | |
| "eval_steps_per_second": 5.296, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 3.236494302749634, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4528, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0053705692803437165, | |
| "grad_norm": 2.1256258487701416, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5065, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00644468313641246, | |
| "grad_norm": 1.8599263429641724, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1595, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00644468313641246, | |
| "eval_loss": 1.4259953498840332, | |
| "eval_runtime": 37.0719, | |
| "eval_samples_per_second": 10.574, | |
| "eval_steps_per_second": 5.287, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007518796992481203, | |
| "grad_norm": 2.1810078620910645, | |
| "learning_rate": 0.00014, | |
| "loss": 1.3973, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 1.4867852926254272, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9254, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00966702470461869, | |
| "grad_norm": 1.1330220699310303, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7735, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00966702470461869, | |
| "eval_loss": 0.8766637444496155, | |
| "eval_runtime": 37.0542, | |
| "eval_samples_per_second": 10.579, | |
| "eval_steps_per_second": 5.29, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010741138560687433, | |
| "grad_norm": 1.8013813495635986, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8574, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4104787234652160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |