| { | |
| "best_metric": 3.311112642288208, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03707823507601038, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007415647015202076, | |
| "grad_norm": 3.377488136291504, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007415647015202076, | |
| "eval_loss": 9.218616485595703, | |
| "eval_runtime": 177.3737, | |
| "eval_samples_per_second": 3.202, | |
| "eval_steps_per_second": 1.601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014831294030404152, | |
| "grad_norm": 6.2697906494140625, | |
| "learning_rate": 0.0002, | |
| "loss": 10.61, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002224694104560623, | |
| "grad_norm": 3.270674467086792, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 9.1669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029662588060808304, | |
| "grad_norm": 3.1401238441467285, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 8.2194, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0037078235076010383, | |
| "grad_norm": 4.1089324951171875, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.6566, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004449388209121246, | |
| "grad_norm": 4.740741729736328, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 7.2733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005190952910641453, | |
| "grad_norm": 5.110124111175537, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.5047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005932517612161661, | |
| "grad_norm": 4.217177867889404, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 5.7418, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006674082313681869, | |
| "grad_norm": 5.452293395996094, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.8136, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007415647015202077, | |
| "grad_norm": 4.3546953201293945, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.0953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008157211716722283, | |
| "grad_norm": 4.2849555015563965, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 4.38, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008898776418242492, | |
| "grad_norm": 5.345592975616455, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 4.2612, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0096403411197627, | |
| "grad_norm": 8.180353164672852, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.5156, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010381905821282907, | |
| "grad_norm": 4.656401634216309, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.5006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011123470522803115, | |
| "grad_norm": 5.976954936981201, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.9601, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011865035224323322, | |
| "grad_norm": 4.536986351013184, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.7285, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01260659992584353, | |
| "grad_norm": 5.482044219970703, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 4.115, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013348164627363738, | |
| "grad_norm": 6.564908981323242, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.6749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014089729328883945, | |
| "grad_norm": 6.927220821380615, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 4.2839, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014831294030404153, | |
| "grad_norm": 6.5299177169799805, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.9471, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01557285873192436, | |
| "grad_norm": 6.840676307678223, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 2.8071, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016314423433444566, | |
| "grad_norm": 6.179226875305176, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 4.5197, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017055988134964777, | |
| "grad_norm": 5.269598007202148, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.9873, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017797552836484983, | |
| "grad_norm": 5.684578895568848, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.8623, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01853911753800519, | |
| "grad_norm": 5.754444122314453, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.9775, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01853911753800519, | |
| "eval_loss": 3.6264519691467285, | |
| "eval_runtime": 178.4867, | |
| "eval_samples_per_second": 3.182, | |
| "eval_steps_per_second": 1.591, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0192806822395254, | |
| "grad_norm": 5.769565105438232, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8071, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.020022246941045607, | |
| "grad_norm": 5.704461574554443, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 3.2958, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020763811642565813, | |
| "grad_norm": 5.851852893829346, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 3.9264, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.021505376344086023, | |
| "grad_norm": 5.5478715896606445, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 4.3509, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02224694104560623, | |
| "grad_norm": 6.7844367027282715, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.4878, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": 5.998141765594482, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 4.4051, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.023730070448646643, | |
| "grad_norm": 5.847940444946289, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 3.4056, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024471635150166853, | |
| "grad_norm": 5.002828598022461, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 3.02, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02521319985168706, | |
| "grad_norm": 4.438299179077148, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.562, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025954764553207266, | |
| "grad_norm": 5.450693607330322, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.7356, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.026696329254727477, | |
| "grad_norm": 4.7872314453125, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 3.2078, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027437893956247683, | |
| "grad_norm": 6.174244403839111, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 4.46, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02817945865776789, | |
| "grad_norm": 5.326364040374756, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.9328, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.028921023359288096, | |
| "grad_norm": 5.555682182312012, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 3.7987, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.029662588060808306, | |
| "grad_norm": 6.068312168121338, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 3.3475, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030404152762328513, | |
| "grad_norm": 5.438655376434326, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.974, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03114571746384872, | |
| "grad_norm": 5.173154830932617, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 3.0526, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03188728216536893, | |
| "grad_norm": 5.596974849700928, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 3.4781, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03262884686688913, | |
| "grad_norm": 4.907413959503174, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.716, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03337041156840934, | |
| "grad_norm": 6.975232124328613, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 3.4974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03411197626992955, | |
| "grad_norm": 6.564231872558594, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 3.3458, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.034853540971449756, | |
| "grad_norm": 9.936782836914062, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 3.1931, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.035595105672969966, | |
| "grad_norm": 8.084567070007324, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 3.0752, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.036336670374490176, | |
| "grad_norm": 6.863251686096191, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.0839, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03707823507601038, | |
| "grad_norm": 7.218696117401123, | |
| "learning_rate": 0.0, | |
| "loss": 4.2556, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03707823507601038, | |
| "eval_loss": 3.311112642288208, | |
| "eval_runtime": 178.6967, | |
| "eval_samples_per_second": 3.179, | |
| "eval_steps_per_second": 1.589, | |
| "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": 6.99038693326848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |