| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.99138991389914, | |
| "eval_steps": 500, | |
| "global_step": 1117, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.984009840098401, | |
| "grad_norm": 0.4337162958714847, | |
| "learning_rate": 3.9716940317357863e-05, | |
| "loss": 0.3891, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.968019680196802, | |
| "grad_norm": 0.1396883245826383, | |
| "learning_rate": 3.813054755147253e-05, | |
| "loss": 0.2684, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.952029520295203, | |
| "grad_norm": 0.15652005092055915, | |
| "learning_rate": 3.525576816314786e-05, | |
| "loss": 0.2466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.936039360393604, | |
| "grad_norm": 0.13772877463793512, | |
| "learning_rate": 3.129688871879154e-05, | |
| "loss": 0.231, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.920049200492005, | |
| "grad_norm": 0.1091216912999427, | |
| "learning_rate": 2.6535233723440083e-05, | |
| "loss": 0.2175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.920049200492005, | |
| "eval_accuracy": 0.10576923076923077, | |
| "eval_loss": 0.21833498775959015, | |
| "eval_runtime": 295.2386, | |
| "eval_samples_per_second": 39.141, | |
| "eval_steps_per_second": 0.308, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.904059040590406, | |
| "grad_norm": 0.15919845220255527, | |
| "learning_rate": 2.1309174237276054e-05, | |
| "loss": 0.2061, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.888068880688807, | |
| "grad_norm": 0.4136694543936493, | |
| "learning_rate": 1.599008266981608e-05, | |
| "loss": 0.1963, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.872078720787208, | |
| "grad_norm": 0.19563061260392473, | |
| "learning_rate": 1.0955942443766471e-05, | |
| "loss": 0.1883, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.85608856088561, | |
| "grad_norm": 0.14621027138210882, | |
| "learning_rate": 6.5644878693742254e-06, | |
| "loss": 0.1837, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.84009840098401, | |
| "grad_norm": 0.13931415581090145, | |
| "learning_rate": 3.1277829541181015e-06, | |
| "loss": 0.1798, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.84009840098401, | |
| "eval_accuracy": 0.28846153846153844, | |
| "eval_loss": 0.20196868479251862, | |
| "eval_runtime": 294.5472, | |
| "eval_samples_per_second": 39.233, | |
| "eval_steps_per_second": 0.309, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.824108241082412, | |
| "grad_norm": 0.18248542610400323, | |
| "learning_rate": 8.900456194655627e-07, | |
| "loss": 0.178, | |
| "step": 1100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1212, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |