| { | |
| "best_metric": 0.4868355989456177, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 1.0038412291933418, | |
| "eval_steps": 50, | |
| "global_step": 196, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005121638924455826, | |
| "eval_loss": 8.380269050598145, | |
| "eval_runtime": 6.2344, | |
| "eval_samples_per_second": 52.771, | |
| "eval_steps_per_second": 13.313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05121638924455826, | |
| "grad_norm": 9.538023948669434, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2433, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10243277848911651, | |
| "grad_norm": 5.801913261413574, | |
| "learning_rate": 0.00019857697953148037, | |
| "loss": 1.1184, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15364916773367476, | |
| "grad_norm": 3.538983106613159, | |
| "learning_rate": 0.00019434841787099803, | |
| "loss": 0.6127, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20486555697823303, | |
| "grad_norm": 13.218347549438477, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 0.6928, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2560819462227913, | |
| "grad_norm": 5.4068732261657715, | |
| "learning_rate": 0.0001780324790952092, | |
| "loss": 2.6809, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2560819462227913, | |
| "eval_loss": 0.8460147976875305, | |
| "eval_runtime": 6.2948, | |
| "eval_samples_per_second": 52.265, | |
| "eval_steps_per_second": 13.185, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3072983354673495, | |
| "grad_norm": 2.373478889465332, | |
| "learning_rate": 0.00016640946027672392, | |
| "loss": 0.4578, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3585147247119078, | |
| "grad_norm": 2.6782474517822266, | |
| "learning_rate": 0.00015289640103269625, | |
| "loss": 0.3475, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.40973111395646605, | |
| "grad_norm": 2.94343638420105, | |
| "learning_rate": 0.0001378778885610576, | |
| "loss": 0.2493, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.46094750320102434, | |
| "grad_norm": 10.372923851013184, | |
| "learning_rate": 0.00012178135587488515, | |
| "loss": 0.8931, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5121638924455826, | |
| "grad_norm": 1.2253535985946655, | |
| "learning_rate": 0.00010506491688387127, | |
| "loss": 1.492, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5121638924455826, | |
| "eval_loss": 0.6194465160369873, | |
| "eval_runtime": 6.3051, | |
| "eval_samples_per_second": 52.18, | |
| "eval_steps_per_second": 13.164, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 1.6862285137176514, | |
| "learning_rate": 8.820432828491542e-05, | |
| "loss": 0.2869, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.614596670934699, | |
| "grad_norm": 1.361668348312378, | |
| "learning_rate": 7.16794493317696e-05, | |
| "loss": 0.2391, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6658130601792573, | |
| "grad_norm": 2.5609822273254395, | |
| "learning_rate": 5.596058484423656e-05, | |
| "loss": 0.158, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7170294494238156, | |
| "grad_norm": 5.137864112854004, | |
| "learning_rate": 4.149510014046922e-05, | |
| "loss": 1.0696, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7682458386683739, | |
| "grad_norm": 2.4468164443969727, | |
| "learning_rate": 2.869468883687798e-05, | |
| "loss": 0.9942, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7682458386683739, | |
| "eval_loss": 0.4868355989456177, | |
| "eval_runtime": 6.3284, | |
| "eval_samples_per_second": 51.988, | |
| "eval_steps_per_second": 13.116, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8194622279129321, | |
| "grad_norm": 2.048182487487793, | |
| "learning_rate": 1.7923655879272393e-05, | |
| "loss": 0.2675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8706786171574904, | |
| "grad_norm": 1.122640609741211, | |
| "learning_rate": 9.488549274967872e-06, | |
| "loss": 0.1, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9218950064020487, | |
| "grad_norm": 2.5161125659942627, | |
| "learning_rate": 3.6294356110059157e-06, | |
| "loss": 0.1207, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9731113956466069, | |
| "grad_norm": 6.927064895629883, | |
| "learning_rate": 5.130676608104845e-07, | |
| "loss": 1.1711, | |
| "step": 190 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 196, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 3.853325055924634e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |