| { | |
| "best_metric": 2.9008495807647705, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0442477876106193, | |
| "eval_steps": 25, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 0.5193688273429871, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "eval_loss": 3.3404901027679443, | |
| "eval_runtime": 2.4194, | |
| "eval_samples_per_second": 39.265, | |
| "eval_steps_per_second": 4.96, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 0.8239558935165405, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2982, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": 1.1576820611953735, | |
| "learning_rate": 9.985329005918702e-05, | |
| "loss": 3.4534, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 0.6357854008674622, | |
| "learning_rate": 9.941402118901744e-05, | |
| "loss": 3.1246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 0.41208094358444214, | |
| "learning_rate": 9.868477119388896e-05, | |
| "loss": 2.9787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 0.6425259709358215, | |
| "learning_rate": 9.766981960274653e-05, | |
| "loss": 3.1863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.49557522123893805, | |
| "grad_norm": 0.9896420836448669, | |
| "learning_rate": 9.637512255510475e-05, | |
| "loss": 3.2937, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 0.4809434115886688, | |
| "learning_rate": 9.480827784805278e-05, | |
| "loss": 2.9278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": 0.4268536865711212, | |
| "learning_rate": 9.297848034936006e-05, | |
| "loss": 2.968, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.43410423398017883, | |
| "learning_rate": 9.089646803833589e-05, | |
| "loss": 3.0674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7787610619469026, | |
| "grad_norm": 0.40264034271240234, | |
| "learning_rate": 8.857445899109715e-05, | |
| "loss": 2.9144, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.3227675259113312, | |
| "learning_rate": 8.602607968003935e-05, | |
| "loss": 2.86, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9203539823008849, | |
| "grad_norm": 0.3561253547668457, | |
| "learning_rate": 8.326628500827826e-05, | |
| "loss": 2.9454, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 0.5675299167633057, | |
| "learning_rate": 8.03112705483319e-05, | |
| "loss": 3.0785, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0619469026548674, | |
| "grad_norm": 0.8450691103935242, | |
| "learning_rate": 7.717837750006106e-05, | |
| "loss": 5.3565, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1327433628318584, | |
| "grad_norm": 0.4789603650569916, | |
| "learning_rate": 7.388599092561315e-05, | |
| "loss": 2.8486, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2035398230088497, | |
| "grad_norm": 0.6054747104644775, | |
| "learning_rate": 7.045343185856701e-05, | |
| "loss": 2.9886, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2743362831858407, | |
| "grad_norm": 0.441631942987442, | |
| "learning_rate": 6.690084392042513e-05, | |
| "loss": 2.6782, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3451327433628317, | |
| "grad_norm": 0.43877655267715454, | |
| "learning_rate": 6.32490751098331e-05, | |
| "loss": 2.9849, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 0.559032678604126, | |
| "learning_rate": 5.951955545823342e-05, | |
| "loss": 2.9156, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4867256637168142, | |
| "grad_norm": 0.7596845030784607, | |
| "learning_rate": 5.573417126992003e-05, | |
| "loss": 3.1224, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5575221238938053, | |
| "grad_norm": 0.4125724136829376, | |
| "learning_rate": 5.191513668450178e-05, | |
| "loss": 2.7414, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6283185840707963, | |
| "grad_norm": 0.5687753558158875, | |
| "learning_rate": 4.8084863315498234e-05, | |
| "loss": 2.8063, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6991150442477876, | |
| "grad_norm": 0.6780652403831482, | |
| "learning_rate": 4.4265828730079987e-05, | |
| "loss": 2.9407, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "grad_norm": 0.4667285680770874, | |
| "learning_rate": 4.0480444541766576e-05, | |
| "loss": 2.6603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "eval_loss": 2.9008495807647705, | |
| "eval_runtime": 2.4198, | |
| "eval_samples_per_second": 39.26, | |
| "eval_steps_per_second": 4.959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8407079646017699, | |
| "grad_norm": 0.4535748362541199, | |
| "learning_rate": 3.675092489016693e-05, | |
| "loss": 2.9285, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.911504424778761, | |
| "grad_norm": 0.5968184471130371, | |
| "learning_rate": 3.309915607957487e-05, | |
| "loss": 2.8405, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9823008849557522, | |
| "grad_norm": 0.7783849239349365, | |
| "learning_rate": 2.9546568141433006e-05, | |
| "loss": 3.0378, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0530973451327434, | |
| "grad_norm": 0.8722625374794006, | |
| "learning_rate": 2.6114009074386846e-05, | |
| "loss": 5.2923, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1238938053097347, | |
| "grad_norm": 0.5258104801177979, | |
| "learning_rate": 2.282162249993895e-05, | |
| "loss": 2.7651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1946902654867255, | |
| "grad_norm": 0.6721611618995667, | |
| "learning_rate": 1.9688729451668114e-05, | |
| "loss": 2.8586, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.265486725663717, | |
| "grad_norm": 0.4610719084739685, | |
| "learning_rate": 1.673371499172174e-05, | |
| "loss": 2.4631, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.336283185840708, | |
| "grad_norm": 0.5183499455451965, | |
| "learning_rate": 1.3973920319960655e-05, | |
| "loss": 3.2142, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.4070796460176993, | |
| "grad_norm": 0.5465492010116577, | |
| "learning_rate": 1.1425541008902851e-05, | |
| "loss": 2.848, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.47787610619469, | |
| "grad_norm": 0.8566042184829712, | |
| "learning_rate": 9.103531961664118e-06, | |
| "loss": 3.0925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5486725663716814, | |
| "grad_norm": 0.4418770968914032, | |
| "learning_rate": 7.0215196506399515e-06, | |
| "loss": 2.7127, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.6194690265486726, | |
| "grad_norm": 0.523547351360321, | |
| "learning_rate": 5.191722151947226e-06, | |
| "loss": 2.6927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.6902654867256635, | |
| "grad_norm": 0.6238358616828918, | |
| "learning_rate": 3.6248774448952695e-06, | |
| "loss": 2.9245, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7610619469026547, | |
| "grad_norm": 0.423245370388031, | |
| "learning_rate": 2.330180397253473e-06, | |
| "loss": 2.3783, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.831858407079646, | |
| "grad_norm": 0.5013735890388489, | |
| "learning_rate": 1.3152288061110518e-06, | |
| "loss": 3.1361, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.9026548672566372, | |
| "grad_norm": 0.5441763997077942, | |
| "learning_rate": 5.859788109825793e-07, | |
| "loss": 2.8389, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9734513274336285, | |
| "grad_norm": 0.7712870836257935, | |
| "learning_rate": 1.4670994081297795e-07, | |
| "loss": 3.0242, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0442477876106193, | |
| "grad_norm": 0.7878711223602295, | |
| "learning_rate": 0.0, | |
| "loss": 5.2321, | |
| "step": 43 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 43, | |
| "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": 9.112012643421389e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |