| { | |
| "best_metric": 1.3384933471679688, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03352329869259135, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006704659738518271, | |
| "grad_norm": 2.785381555557251, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006704659738518271, | |
| "eval_loss": 5.129286766052246, | |
| "eval_runtime": 217.5802, | |
| "eval_samples_per_second": 2.886, | |
| "eval_steps_per_second": 1.443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013409319477036541, | |
| "grad_norm": 4.200088024139404, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5378, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002011397921555481, | |
| "grad_norm": 2.5246617794036865, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 3.8154, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026818638954073082, | |
| "grad_norm": 3.857762575149536, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 3.9286, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003352329869259135, | |
| "grad_norm": 3.4422905445098877, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 2.9298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004022795843110962, | |
| "grad_norm": 5.336806774139404, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.6884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004693261816962789, | |
| "grad_norm": 2.9105687141418457, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 2.3281, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0053637277908146165, | |
| "grad_norm": 2.198127269744873, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.1382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006034193764666443, | |
| "grad_norm": 2.610673427581787, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 2.0367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00670465973851827, | |
| "grad_norm": 1.9399616718292236, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.6264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0073751257123700975, | |
| "grad_norm": 2.213160753250122, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.1415, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008045591686221924, | |
| "grad_norm": 2.0367908477783203, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.8516, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008716057660073752, | |
| "grad_norm": 2.198748826980591, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.7538, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009386523633925578, | |
| "grad_norm": 1.8134102821350098, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.6823, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010056989607777405, | |
| "grad_norm": 2.1345443725585938, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.8103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010727455581629233, | |
| "grad_norm": 2.9759273529052734, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.6287, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011397921555481059, | |
| "grad_norm": 2.164623975753784, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.693, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012068387529332886, | |
| "grad_norm": 1.6544045209884644, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.5992, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012738853503184714, | |
| "grad_norm": 1.7987711429595947, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.6052, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01340931947703654, | |
| "grad_norm": 2.2308642864227295, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.5962, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014079785450888367, | |
| "grad_norm": 1.4975007772445679, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.3212, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014750251424740195, | |
| "grad_norm": 1.5792878866195679, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.6516, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015420717398592021, | |
| "grad_norm": 1.7073818445205688, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.5147, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01609118337244385, | |
| "grad_norm": 1.8162294626235962, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.3587, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016761649346295676, | |
| "grad_norm": 1.8236422538757324, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.3354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016761649346295676, | |
| "eval_loss": 1.3677418231964111, | |
| "eval_runtime": 219.7996, | |
| "eval_samples_per_second": 2.857, | |
| "eval_steps_per_second": 1.429, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017432115320147504, | |
| "grad_norm": 1.7336963415145874, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3554, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.018102581293999328, | |
| "grad_norm": 1.6814982891082764, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.2641, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018773047267851155, | |
| "grad_norm": 1.820735216140747, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.3903, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019443513241702983, | |
| "grad_norm": 1.9364521503448486, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.4451, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02011397921555481, | |
| "grad_norm": 2.0241713523864746, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.3482, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02078444518940664, | |
| "grad_norm": 1.512275218963623, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.2534, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021454911163258466, | |
| "grad_norm": 1.9568251371383667, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.5905, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02212537713711029, | |
| "grad_norm": 2.224773645401001, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.1378, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022795843110962118, | |
| "grad_norm": 1.7800034284591675, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.0066, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023466309084813945, | |
| "grad_norm": 2.645667314529419, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.9694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024136775058665773, | |
| "grad_norm": 2.402721405029297, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.3358, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0248072410325176, | |
| "grad_norm": 2.066645860671997, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.2806, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025477707006369428, | |
| "grad_norm": 1.59635329246521, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.834, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.026148172980221252, | |
| "grad_norm": 1.2451773881912231, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.767, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02681863895407308, | |
| "grad_norm": 2.293517589569092, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.1113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027489104927924907, | |
| "grad_norm": 1.319640040397644, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.6773, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.028159570901776735, | |
| "grad_norm": 1.7485390901565552, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.0643, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.028830036875628563, | |
| "grad_norm": 1.466673493385315, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.7863, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02950050284948039, | |
| "grad_norm": 1.6620216369628906, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.7743, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.030170968823332214, | |
| "grad_norm": 2.3844711780548096, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.5747, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.030841434797184042, | |
| "grad_norm": 1.4075263738632202, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.6564, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03151190077103587, | |
| "grad_norm": 1.3964762687683105, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.6778, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0321823667448877, | |
| "grad_norm": 1.50095796585083, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.6561, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.032852832718739525, | |
| "grad_norm": 1.9353364706039429, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.5138, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03352329869259135, | |
| "grad_norm": 2.526801824569702, | |
| "learning_rate": 0.0, | |
| "loss": 0.5273, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03352329869259135, | |
| "eval_loss": 1.3384933471679688, | |
| "eval_runtime": 219.8146, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.41887283560448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |