| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19138755980861244, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019138755980861243, | |
| "grad_norm": 0.3160504996776581, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019138755980861243, | |
| "eval_loss": 1.4776239395141602, | |
| "eval_runtime": 1.2876, | |
| "eval_samples_per_second": 17.863, | |
| "eval_steps_per_second": 9.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03827751196172249, | |
| "grad_norm": 0.30724653601646423, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05741626794258373, | |
| "grad_norm": 0.3146219551563263, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4272, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05741626794258373, | |
| "eval_loss": 1.4738867282867432, | |
| "eval_runtime": 1.2857, | |
| "eval_samples_per_second": 17.889, | |
| "eval_steps_per_second": 9.333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07655502392344497, | |
| "grad_norm": 0.3195428252220154, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09569377990430622, | |
| "grad_norm": 0.3404718041419983, | |
| "learning_rate": 0.0001, | |
| "loss": 1.537, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11483253588516747, | |
| "grad_norm": 0.3823797106742859, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4345, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11483253588516747, | |
| "eval_loss": 1.4316757917404175, | |
| "eval_runtime": 1.2951, | |
| "eval_samples_per_second": 17.759, | |
| "eval_steps_per_second": 9.265, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1339712918660287, | |
| "grad_norm": 0.3827013075351715, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4411, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15311004784688995, | |
| "grad_norm": 0.38532698154449463, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5198, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1722488038277512, | |
| "grad_norm": 0.3466355502605438, | |
| "learning_rate": 0.00018, | |
| "loss": 1.345, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1722488038277512, | |
| "eval_loss": 1.337863802909851, | |
| "eval_runtime": 1.288, | |
| "eval_samples_per_second": 17.857, | |
| "eval_steps_per_second": 9.317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19138755980861244, | |
| "grad_norm": 0.3907493054866791, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3918, | |
| "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": 1640097329971200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |