| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003511441446713876, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011704804822379587, | |
| "eval_loss": 4.554361820220947, | |
| "eval_runtime": 300.759, | |
| "eval_samples_per_second": 11.963, | |
| "eval_steps_per_second": 5.982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003511441446713876, | |
| "grad_norm": 4.222924709320068, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4889, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007022882893427752, | |
| "grad_norm": 5.726322650909424, | |
| "learning_rate": 0.00012, | |
| "loss": 4.3174, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000936384385790367, | |
| "eval_loss": 2.8311750888824463, | |
| "eval_runtime": 301.662, | |
| "eval_samples_per_second": 11.927, | |
| "eval_steps_per_second": 5.964, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001053432434014163, | |
| "grad_norm": 6.246539115905762, | |
| "learning_rate": 0.00018, | |
| "loss": 3.5675, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014045765786855505, | |
| "grad_norm": 4.769035816192627, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.6984, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001755720723356938, | |
| "grad_norm": 4.509332656860352, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.2977, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001872768771580734, | |
| "eval_loss": 2.0571675300598145, | |
| "eval_runtime": 301.7004, | |
| "eval_samples_per_second": 11.926, | |
| "eval_steps_per_second": 5.963, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002106864868028326, | |
| "grad_norm": 6.054222583770752, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0006, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024580090126997134, | |
| "grad_norm": 3.8717751502990723, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.8978, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002809153157371101, | |
| "grad_norm": 3.579822540283203, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.8987, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002809153157371101, | |
| "eval_loss": 1.8924885988235474, | |
| "eval_runtime": 301.8067, | |
| "eval_samples_per_second": 11.922, | |
| "eval_steps_per_second": 5.961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0031602973020424885, | |
| "grad_norm": 4.799511909484863, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.2176, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003511441446713876, | |
| "grad_norm": 3.684116840362549, | |
| "learning_rate": 0.0, | |
| "loss": 1.863, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |