| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004608294930875576, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004608294930875576, | |
| "grad_norm": 1.725007176399231, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5505, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004608294930875576, | |
| "eval_loss": 1.8385721445083618, | |
| "eval_runtime": 51.5965, | |
| "eval_samples_per_second": 17.714, | |
| "eval_steps_per_second": 8.857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009216589861751152, | |
| "grad_norm": 1.7148290872573853, | |
| "learning_rate": 4e-05, | |
| "loss": 2.164, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013824884792626728, | |
| "grad_norm": 1.2495578527450562, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4731, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013824884792626728, | |
| "eval_loss": 1.833776593208313, | |
| "eval_runtime": 50.2556, | |
| "eval_samples_per_second": 18.187, | |
| "eval_steps_per_second": 9.094, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018433179723502304, | |
| "grad_norm": 1.7767750024795532, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9123, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002304147465437788, | |
| "grad_norm": 1.192010521888733, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0913, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027649769585253456, | |
| "grad_norm": 1.4868011474609375, | |
| "learning_rate": 0.00012, | |
| "loss": 1.794, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027649769585253456, | |
| "eval_loss": 1.7426038980484009, | |
| "eval_runtime": 50.5081, | |
| "eval_samples_per_second": 18.096, | |
| "eval_steps_per_second": 9.048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032258064516129032, | |
| "grad_norm": 1.1867609024047852, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6008, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003686635944700461, | |
| "grad_norm": 1.3795751333236694, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004147465437788019, | |
| "grad_norm": 1.678766131401062, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004147465437788019, | |
| "eval_loss": 1.4757215976715088, | |
| "eval_runtime": 50.3951, | |
| "eval_samples_per_second": 18.137, | |
| "eval_steps_per_second": 9.068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004608294930875576, | |
| "grad_norm": 1.1294562816619873, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3355, | |
| "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": 3168274061721600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |