| { | |
| "best_metric": 6.661139965057373, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.17467248908296942, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034934497816593887, | |
| "grad_norm": 1.3092701435089111, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034934497816593887, | |
| "eval_loss": 6.968745231628418, | |
| "eval_runtime": 0.5639, | |
| "eval_samples_per_second": 854.754, | |
| "eval_steps_per_second": 108.174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069868995633187774, | |
| "grad_norm": 1.2442760467529297, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9645, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010480349344978166, | |
| "grad_norm": 1.4572207927703857, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.9642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013973799126637555, | |
| "grad_norm": 1.3128467798233032, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.9445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 1.3238770961761475, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.9489, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02096069868995633, | |
| "grad_norm": 1.378156304359436, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9479, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02445414847161572, | |
| "grad_norm": 1.3934940099716187, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.9302, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 1.3221594095230103, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0314410480349345, | |
| "grad_norm": 1.347082495689392, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.8889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 1.366279125213623, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.8951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03842794759825328, | |
| "grad_norm": 1.3531293869018555, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.8685, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04192139737991266, | |
| "grad_norm": 1.3544623851776123, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.8802, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.045414847161572056, | |
| "grad_norm": 1.482946515083313, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.8534, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04890829694323144, | |
| "grad_norm": 1.4593490362167358, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.8437, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 1.4448790550231934, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.8272, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05589519650655022, | |
| "grad_norm": 1.6794919967651367, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.8196, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.059388646288209605, | |
| "grad_norm": 1.5125168561935425, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.8103, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.062882096069869, | |
| "grad_norm": 1.6657400131225586, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.8233, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06637554585152838, | |
| "grad_norm": 1.6942110061645508, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.7919, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 1.3869768381118774, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.7821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07336244541484715, | |
| "grad_norm": 1.834231972694397, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.7824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07685589519650655, | |
| "grad_norm": 1.4711532592773438, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.7632, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08034934497816594, | |
| "grad_norm": 1.4155688285827637, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.7628, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08384279475982533, | |
| "grad_norm": 1.4608124494552612, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.745, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "grad_norm": 1.4313796758651733, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.7361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "eval_loss": 6.729074954986572, | |
| "eval_runtime": 0.5555, | |
| "eval_samples_per_second": 867.649, | |
| "eval_steps_per_second": 109.806, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09082969432314411, | |
| "grad_norm": 1.7198904752731323, | |
| "learning_rate": 0.0001, | |
| "loss": 6.721, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0943231441048035, | |
| "grad_norm": 1.4587581157684326, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.7278, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09781659388646288, | |
| "grad_norm": 1.5983480215072632, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.7303, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10131004366812227, | |
| "grad_norm": 1.626555323600769, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.7129, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10480349344978165, | |
| "grad_norm": 1.3530901670455933, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.7166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10829694323144105, | |
| "grad_norm": 1.6371723413467407, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.7081, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11179039301310044, | |
| "grad_norm": 1.4091604948043823, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.6933, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11528384279475982, | |
| "grad_norm": 1.3315062522888184, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.7152, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11877729257641921, | |
| "grad_norm": 1.406883716583252, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.6903, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1222707423580786, | |
| "grad_norm": 1.270359992980957, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.6839, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.125764192139738, | |
| "grad_norm": 1.3271560668945312, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.6798, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12925764192139738, | |
| "grad_norm": 1.5681676864624023, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.6776, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13275109170305677, | |
| "grad_norm": 1.1914104223251343, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.6897, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13624454148471615, | |
| "grad_norm": 1.5367497205734253, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.658, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 1.427626132965088, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.6709, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14323144104803492, | |
| "grad_norm": 1.4009745121002197, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.6851, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1467248908296943, | |
| "grad_norm": 1.2408397197723389, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.6675, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15021834061135372, | |
| "grad_norm": 1.4328770637512207, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.6639, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1537117903930131, | |
| "grad_norm": 1.4258441925048828, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.6586, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1572052401746725, | |
| "grad_norm": 1.161400556564331, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.6903, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16069868995633188, | |
| "grad_norm": 1.23970365524292, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.6612, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16419213973799127, | |
| "grad_norm": 1.5629112720489502, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.6537, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16768558951965065, | |
| "grad_norm": 1.22788405418396, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.6729, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.17117903930131004, | |
| "grad_norm": 1.2596584558486938, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.6638, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "grad_norm": 1.359727382659912, | |
| "learning_rate": 0.0, | |
| "loss": 6.659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17467248908296942, | |
| "eval_loss": 6.661139965057373, | |
| "eval_runtime": 0.5655, | |
| "eval_samples_per_second": 852.39, | |
| "eval_steps_per_second": 107.875, | |
| "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": 2357211955200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |