| { | |
| "best_metric": 0.6671230792999268, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.076923076923077, | |
| "eval_steps": 25, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 33.737701416015625, | |
| "learning_rate": 5e-05, | |
| "loss": 10.0947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "eval_loss": 10.191614151000977, | |
| "eval_runtime": 1.4382, | |
| "eval_samples_per_second": 34.766, | |
| "eval_steps_per_second": 9.039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 30.049089431762695, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 29.79092025756836, | |
| "learning_rate": 9.971704944519594e-05, | |
| "loss": 8.9179, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 24.568462371826172, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 5.7438, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 20.547700881958008, | |
| "learning_rate": 9.747474986387654e-05, | |
| "loss": 3.427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 12.677267074584961, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 2.256, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 9.974773406982422, | |
| "learning_rate": 9.310258896527278e-05, | |
| "loss": 1.4638, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 4.876607894897461, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 1.0442, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 2.5556421279907227, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8391, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 5.1846771240234375, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 1.0291, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1282051282051282, | |
| "grad_norm": 0.995373547077179, | |
| "learning_rate": 7.894144344319014e-05, | |
| "loss": 0.7795, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 1.5625572204589844, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 0.7668, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 2.6887452602386475, | |
| "learning_rate": 6.986255778798253e-05, | |
| "loss": 0.8087, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": 0.9819567203521729, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.7795, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.8303066492080688, | |
| "learning_rate": 6.003840142464886e-05, | |
| "loss": 0.7573, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 1.412522315979004, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7435897435897436, | |
| "grad_norm": 2.325110673904419, | |
| "learning_rate": 4.9961598575351155e-05, | |
| "loss": 0.7713, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 1.1739482879638672, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.7873, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "grad_norm": 1.4842931032180786, | |
| "learning_rate": 4.01374422120175e-05, | |
| "loss": 0.803, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 1.1867262125015259, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 0.8698, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 2.1852214336395264, | |
| "learning_rate": 3.105855655680986e-05, | |
| "loss": 0.8206, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.2564102564102564, | |
| "grad_norm": 2.442964792251587, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.7546, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.358974358974359, | |
| "grad_norm": 2.661452293395996, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8421, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 1.0270347595214844, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 0.7241, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 0.8220930099487305, | |
| "learning_rate": 1.6897411034727218e-05, | |
| "loss": 0.7101, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 0.6671230792999268, | |
| "eval_runtime": 1.4963, | |
| "eval_samples_per_second": 33.416, | |
| "eval_steps_per_second": 8.688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.176918387413025, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.7793, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 0.5590916872024536, | |
| "learning_rate": 1.252525013612346e-05, | |
| "loss": 0.7132, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.871794871794872, | |
| "grad_norm": 0.7971133589744568, | |
| "learning_rate": 1.1128243951817937e-05, | |
| "loss": 0.736, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "grad_norm": 0.9218295216560364, | |
| "learning_rate": 1.0282950554804085e-05, | |
| "loss": 0.8827, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 2.245664119720459, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8213, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.698257208901632e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |