| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011981787682722263, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011981787682722263, | |
| "grad_norm": 0.16319094598293304, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011981787682722263, | |
| "eval_loss": 10.839637756347656, | |
| "eval_runtime": 10.3007, | |
| "eval_samples_per_second": 341.237, | |
| "eval_steps_per_second": 170.667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023963575365444525, | |
| "grad_norm": 0.15802831947803497, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8345, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003594536304816679, | |
| "grad_norm": 0.14335568249225616, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003594536304816679, | |
| "eval_loss": 10.839527130126953, | |
| "eval_runtime": 9.0167, | |
| "eval_samples_per_second": 389.832, | |
| "eval_steps_per_second": 194.972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004792715073088905, | |
| "grad_norm": 0.15909667313098907, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8235, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005990893841361131, | |
| "grad_norm": 0.1621047705411911, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007189072609633358, | |
| "grad_norm": 0.16605113446712494, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8363, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007189072609633358, | |
| "eval_loss": 10.838635444641113, | |
| "eval_runtime": 9.0993, | |
| "eval_samples_per_second": 386.294, | |
| "eval_steps_per_second": 193.202, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008387251377905584, | |
| "grad_norm": 0.14451463520526886, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000958543014617781, | |
| "grad_norm": 0.17358613014221191, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8334, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010783608914450035, | |
| "grad_norm": 0.13881893455982208, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010783608914450035, | |
| "eval_loss": 10.837157249450684, | |
| "eval_runtime": 9.1743, | |
| "eval_samples_per_second": 383.137, | |
| "eval_steps_per_second": 191.623, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011981787682722263, | |
| "grad_norm": 0.23394715785980225, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8405, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 820295761920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |