| { | |
| "best_metric": 0.16282150149345398, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03711952487008166, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007423904974016332, | |
| "grad_norm": 0.6487741470336914, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007423904974016332, | |
| "eval_loss": 2.591169834136963, | |
| "eval_runtime": 197.2852, | |
| "eval_samples_per_second": 2.879, | |
| "eval_steps_per_second": 1.44, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014847809948032665, | |
| "grad_norm": 2.3651726245880127, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4163, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022271714922048997, | |
| "grad_norm": 1.3198089599609375, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.3814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002969561989606533, | |
| "grad_norm": 2.1703317165374756, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.2471, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003711952487008166, | |
| "grad_norm": 1.6247034072875977, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.1354, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "grad_norm": 2.12754487991333, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.1925, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005196733481811433, | |
| "grad_norm": 1.0829967260360718, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.1403, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005939123979213066, | |
| "grad_norm": 1.0773605108261108, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.1134, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0066815144766146995, | |
| "grad_norm": 0.8257158398628235, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0786, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007423904974016332, | |
| "grad_norm": 0.5242513418197632, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0609, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008166295471417966, | |
| "grad_norm": 1.4674206972122192, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0633, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 1.7347350120544434, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0578, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009651076466221232, | |
| "grad_norm": 0.9604913592338562, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0722, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010393466963622866, | |
| "grad_norm": 1.2394442558288574, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.1024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011135857461024499, | |
| "grad_norm": 1.7442325353622437, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.108, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011878247958426132, | |
| "grad_norm": 0.8243395090103149, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.069, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012620638455827766, | |
| "grad_norm": 0.9156538248062134, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0934, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013363028953229399, | |
| "grad_norm": 0.5281884670257568, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0152, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014105419450631032, | |
| "grad_norm": 1.2212343215942383, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0413, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014847809948032665, | |
| "grad_norm": 0.5214835405349731, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015590200445434299, | |
| "grad_norm": 0.3459300398826599, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.017, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016332590942835932, | |
| "grad_norm": 0.5943859815597534, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0299, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017074981440237565, | |
| "grad_norm": 1.0379056930541992, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 1.2425271272659302, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.1157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01855976243504083, | |
| "grad_norm": 1.3894206285476685, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0278, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01855976243504083, | |
| "eval_loss": 0.16282150149345398, | |
| "eval_runtime": 198.8339, | |
| "eval_samples_per_second": 2.857, | |
| "eval_steps_per_second": 1.428, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019302152932442463, | |
| "grad_norm": 0.3026466369628906, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0200445434298441, | |
| "grad_norm": 0.882306694984436, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.136, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020786933927245732, | |
| "grad_norm": 0.8444817066192627, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.021529324424647365, | |
| "grad_norm": 1.1410984992980957, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0993, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022271714922048998, | |
| "grad_norm": 0.5272141098976135, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0364, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02301410541945063, | |
| "grad_norm": 0.3858809769153595, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0412, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.023756495916852263, | |
| "grad_norm": 0.44752252101898193, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0214, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024498886414253896, | |
| "grad_norm": 0.5306777954101562, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.011, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025241276911655532, | |
| "grad_norm": 0.9459553360939026, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0844, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025983667409057165, | |
| "grad_norm": 0.47654223442077637, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0523, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 0.9003578424453735, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0696, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02746844840386043, | |
| "grad_norm": 2.070967674255371, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.1786, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028210838901262063, | |
| "grad_norm": 0.4337747097015381, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0155, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.028953229398663696, | |
| "grad_norm": 0.3766095042228699, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0135, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02969561989606533, | |
| "grad_norm": 1.6106809377670288, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030438010393466965, | |
| "grad_norm": 2.527824878692627, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.042, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.031180400890868598, | |
| "grad_norm": 2.065561056137085, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0284, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03192279138827023, | |
| "grad_norm": 0.4519674777984619, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0148, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.032665181885671864, | |
| "grad_norm": 0.6088566184043884, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0132, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0334075723830735, | |
| "grad_norm": 0.1786351203918457, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0076, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03414996288047513, | |
| "grad_norm": 0.5400381684303284, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0073, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.034892353377876766, | |
| "grad_norm": 62.15085983276367, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.0234, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 23.811513900756836, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.7888, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03637713437268003, | |
| "grad_norm": 27.518611907958984, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.8569, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03711952487008166, | |
| "grad_norm": 50.407073974609375, | |
| "learning_rate": 0.0, | |
| "loss": 1.3908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03711952487008166, | |
| "eval_loss": 0.1675003468990326, | |
| "eval_runtime": 198.8265, | |
| "eval_samples_per_second": 2.857, | |
| "eval_steps_per_second": 1.428, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.455967199782502e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |