| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027149321266968326, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001005530417295123, | |
| "eval_loss": 10.755413055419922, | |
| "eval_runtime": 11.149, | |
| "eval_samples_per_second": 150.237, | |
| "eval_steps_per_second": 18.836, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030165912518853697, | |
| "grad_norm": 3.2384252548217773, | |
| "learning_rate": 1.5e-05, | |
| "loss": 10.7531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006033182503770739, | |
| "grad_norm": 3.522120952606201, | |
| "learning_rate": 3e-05, | |
| "loss": 10.7362, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00904977375565611, | |
| "grad_norm": 3.7233874797821045, | |
| "learning_rate": 4.5e-05, | |
| "loss": 10.6587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00904977375565611, | |
| "eval_loss": 10.54302978515625, | |
| "eval_runtime": 11.1743, | |
| "eval_samples_per_second": 149.898, | |
| "eval_steps_per_second": 18.793, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012066365007541479, | |
| "grad_norm": 4.279703617095947, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 10.4367, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015082956259426848, | |
| "grad_norm": 5.507565021514893, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 10.1176, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01809954751131222, | |
| "grad_norm": 6.325550079345703, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 9.7615, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01809954751131222, | |
| "eval_loss": 9.461087226867676, | |
| "eval_runtime": 11.1633, | |
| "eval_samples_per_second": 150.045, | |
| "eval_steps_per_second": 18.812, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021116138763197588, | |
| "grad_norm": 6.642955780029297, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 9.3199, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024132730015082957, | |
| "grad_norm": 7.369113922119141, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 8.8135, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027149321266968326, | |
| "grad_norm": 6.994415760040283, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 8.3456, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027149321266968326, | |
| "eval_loss": 7.989864349365234, | |
| "eval_runtime": 11.0595, | |
| "eval_samples_per_second": 151.454, | |
| "eval_steps_per_second": 18.988, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2314236994781184.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |