| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013364517206815904, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013364517206815904, | |
| "grad_norm": 0.2659130394458771, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013364517206815904, | |
| "eval_loss": 10.839484214782715, | |
| "eval_runtime": 2.3583, | |
| "eval_samples_per_second": 133.573, | |
| "eval_steps_per_second": 66.998, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026729034413631807, | |
| "grad_norm": 0.23665907979011536, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8211, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "grad_norm": 0.20450706779956818, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004009355162044771, | |
| "eval_loss": 10.83917236328125, | |
| "eval_runtime": 1.1549, | |
| "eval_samples_per_second": 272.759, | |
| "eval_steps_per_second": 136.812, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0053458068827263614, | |
| "grad_norm": 0.25612157583236694, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006682258603407952, | |
| "grad_norm": 0.23330692946910858, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "grad_norm": 0.17283666133880615, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008018710324089542, | |
| "eval_loss": 10.836779594421387, | |
| "eval_runtime": 1.2036, | |
| "eval_samples_per_second": 261.712, | |
| "eval_steps_per_second": 131.272, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009355162044771133, | |
| "grad_norm": 0.25193992257118225, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010691613765452723, | |
| "grad_norm": 0.21499177813529968, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "grad_norm": 0.20489895343780518, | |
| "learning_rate": 0.00018, | |
| "loss": 10.8208, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012028065486134313, | |
| "eval_loss": 10.832963943481445, | |
| "eval_runtime": 1.2067, | |
| "eval_samples_per_second": 261.033, | |
| "eval_steps_per_second": 130.931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013364517206815904, | |
| "grad_norm": 0.2217206358909607, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8361, | |
| "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": 1620084129792.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |