| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021586616297895305, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021586616297895305, | |
| "grad_norm": 21.68425750732422, | |
| "learning_rate": 2e-05, | |
| "loss": 6.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021586616297895305, | |
| "eval_loss": 1.9167486429214478, | |
| "eval_runtime": 6.312, | |
| "eval_samples_per_second": 30.894, | |
| "eval_steps_per_second": 15.526, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004317323259579061, | |
| "grad_norm": 16.387784957885742, | |
| "learning_rate": 4e-05, | |
| "loss": 7.238, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0064759848893685915, | |
| "grad_norm": 16.958606719970703, | |
| "learning_rate": 6e-05, | |
| "loss": 8.7787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0064759848893685915, | |
| "eval_loss": 1.8639930486679077, | |
| "eval_runtime": 6.2871, | |
| "eval_samples_per_second": 31.016, | |
| "eval_steps_per_second": 15.587, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008634646519158122, | |
| "grad_norm": 19.50927734375, | |
| "learning_rate": 8e-05, | |
| "loss": 8.3787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010793308148947653, | |
| "grad_norm": 17.37479019165039, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9027, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012951969778737183, | |
| "grad_norm": 23.768177032470703, | |
| "learning_rate": 0.00012, | |
| "loss": 7.3339, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012951969778737183, | |
| "eval_loss": 1.4118256568908691, | |
| "eval_runtime": 6.3331, | |
| "eval_samples_per_second": 30.791, | |
| "eval_steps_per_second": 15.474, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015110631408526714, | |
| "grad_norm": 21.00330352783203, | |
| "learning_rate": 0.00014, | |
| "loss": 6.8624, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017269293038316244, | |
| "grad_norm": 23.177852630615234, | |
| "learning_rate": 0.00016, | |
| "loss": 4.7309, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019427954668105773, | |
| "grad_norm": 16.235668182373047, | |
| "learning_rate": 0.00018, | |
| "loss": 4.2404, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019427954668105773, | |
| "eval_loss": 1.0453327894210815, | |
| "eval_runtime": 6.3324, | |
| "eval_samples_per_second": 30.794, | |
| "eval_steps_per_second": 15.476, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021586616297895305, | |
| "grad_norm": 20.74294662475586, | |
| "learning_rate": 0.0002, | |
| "loss": 3.8793, | |
| "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": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |