| { |
| "best_metric": 12.4584321975708, |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", |
| "epoch": 3.0673575129533677, |
| "eval_steps": 25, |
| "global_step": 37, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08290155440414508, |
| "grad_norm": 0.01514320820569992, |
| "learning_rate": 5e-05, |
| "loss": 12.4613, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08290155440414508, |
| "eval_loss": 12.459206581115723, |
| "eval_runtime": 0.2163, |
| "eval_samples_per_second": 379.053, |
| "eval_steps_per_second": 50.849, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.16580310880829016, |
| "grad_norm": 0.016940046101808548, |
| "learning_rate": 0.0001, |
| "loss": 12.4646, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.24870466321243523, |
| "grad_norm": 0.020668400451540947, |
| "learning_rate": 9.979871469976196e-05, |
| "loss": 12.4644, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3316062176165803, |
| "grad_norm": 0.014744357205927372, |
| "learning_rate": 9.919647942993148e-05, |
| "loss": 12.462, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.41450777202072536, |
| "grad_norm": 0.01674213632941246, |
| "learning_rate": 9.819814303479267e-05, |
| "loss": 12.4649, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.49740932642487046, |
| "grad_norm": 0.020822757855057716, |
| "learning_rate": 9.681174353198687e-05, |
| "loss": 12.4644, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.5803108808290155, |
| "grad_norm": 0.015361081808805466, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 12.4614, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6632124352331606, |
| "grad_norm": 0.016944194212555885, |
| "learning_rate": 9.292243968009331e-05, |
| "loss": 12.4609, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.7461139896373057, |
| "grad_norm": 0.020996803417801857, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 12.4639, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.8290155440414507, |
| "grad_norm": 0.01585252955555916, |
| "learning_rate": 8.765357330018056e-05, |
| "loss": 12.4602, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9119170984455959, |
| "grad_norm": 0.01822737418115139, |
| "learning_rate": 8.455313244934324e-05, |
| "loss": 12.4607, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.9948186528497409, |
| "grad_norm": 0.02217421680688858, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 12.4639, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.077720207253886, |
| "grad_norm": 0.03750379756093025, |
| "learning_rate": 7.754484907260513e-05, |
| "loss": 24.2304, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.160621761658031, |
| "grad_norm": 0.01910383254289627, |
| "learning_rate": 7.369343312364993e-05, |
| "loss": 12.4002, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.2435233160621761, |
| "grad_norm": 0.022818854078650475, |
| "learning_rate": 6.965125158269619e-05, |
| "loss": 12.545, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.3264248704663213, |
| "grad_norm": 0.01749342679977417, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 12.3828, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.4093264248704664, |
| "grad_norm": 0.020716814324259758, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 12.5032, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.4922279792746114, |
| "grad_norm": 0.025025969371199608, |
| "learning_rate": 5.6711663290882776e-05, |
| "loss": 12.5683, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.5751295336787565, |
| "grad_norm": 0.020646177232265472, |
| "learning_rate": 5.2243241517525754e-05, |
| "loss": 12.3345, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.6580310880829017, |
| "grad_norm": 0.022280218079686165, |
| "learning_rate": 4.775675848247427e-05, |
| "loss": 12.3543, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.7409326424870466, |
| "grad_norm": 0.028573088347911835, |
| "learning_rate": 4.328833670911724e-05, |
| "loss": 12.6777, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.8238341968911918, |
| "grad_norm": 0.01995987445116043, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 12.3295, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.906735751295337, |
| "grad_norm": 0.022720159962773323, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 12.5127, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.9896373056994818, |
| "grad_norm": 0.027929486706852913, |
| "learning_rate": 3.0348748417303823e-05, |
| "loss": 12.5036, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.0725388601036268, |
| "grad_norm": 0.04317659139633179, |
| "learning_rate": 2.630656687635007e-05, |
| "loss": 24.1762, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0725388601036268, |
| "eval_loss": 12.4584321975708, |
| "eval_runtime": 0.2152, |
| "eval_samples_per_second": 380.993, |
| "eval_steps_per_second": 51.109, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.155440414507772, |
| "grad_norm": 0.023453839123249054, |
| "learning_rate": 2.245515092739488e-05, |
| "loss": 12.3639, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.238341968911917, |
| "grad_norm": 0.02777229994535446, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 12.6757, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.321243523316062, |
| "grad_norm": 0.02316541038453579, |
| "learning_rate": 1.544686755065677e-05, |
| "loss": 12.2681, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.4041450777202074, |
| "grad_norm": 0.02422947622835636, |
| "learning_rate": 1.2346426699819458e-05, |
| "loss": 12.4471, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.4870466321243523, |
| "grad_norm": 0.02776755392551422, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 12.5286, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.5699481865284977, |
| "grad_norm": 0.022363506257534027, |
| "learning_rate": 7.077560319906695e-06, |
| "loss": 12.452, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.6528497409326426, |
| "grad_norm": 0.024167869240045547, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 12.3364, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.7357512953367875, |
| "grad_norm": 0.029816903173923492, |
| "learning_rate": 3.18825646801314e-06, |
| "loss": 12.6708, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.818652849740933, |
| "grad_norm": 0.022897807881236076, |
| "learning_rate": 1.8018569652073381e-06, |
| "loss": 12.2847, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.901554404145078, |
| "grad_norm": 0.022587254643440247, |
| "learning_rate": 8.035205700685167e-07, |
| "loss": 12.4786, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.9844559585492227, |
| "grad_norm": 0.028138399124145508, |
| "learning_rate": 2.012853002380466e-07, |
| "loss": 12.6596, |
| "step": 36 |
| }, |
| { |
| "epoch": 3.0673575129533677, |
| "grad_norm": 0.04486376419663429, |
| "learning_rate": 0.0, |
| "loss": 24.0609, |
| "step": 37 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 37, |
| "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": 623860776960.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
