| { | |
| "best_metric": 2.1577975749969482, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-600", | |
| "epoch": 0.061870021396715734, | |
| "eval_steps": 50, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010311670232785956, | |
| "eval_loss": 4.732141971588135, | |
| "eval_runtime": 333.6338, | |
| "eval_samples_per_second": 48.958, | |
| "eval_steps_per_second": 12.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010311670232785956, | |
| "grad_norm": 1.6720637083053589, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002062334046557191, | |
| "grad_norm": 1.9888806343078613, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 2.5398, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030935010698357867, | |
| "grad_norm": 2.414046049118042, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 2.7624, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004124668093114382, | |
| "grad_norm": 3.4234137535095215, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 2.4618, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005155835116392978, | |
| "grad_norm": 5.409121513366699, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 2.4923, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005155835116392978, | |
| "eval_loss": 2.6833808422088623, | |
| "eval_runtime": 333.2547, | |
| "eval_samples_per_second": 49.014, | |
| "eval_steps_per_second": 12.255, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006187002139671573, | |
| "grad_norm": 0.715253472328186, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 1.8928, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007218169162950169, | |
| "grad_norm": 1.2599879503250122, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 2.3518, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008249336186228765, | |
| "grad_norm": 1.8510029315948486, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 2.6639, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00928050320950736, | |
| "grad_norm": 2.6438262462615967, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 2.3797, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.010311670232785956, | |
| "grad_norm": 4.056297302246094, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 2.3671, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.010311670232785956, | |
| "eval_loss": 2.5445327758789062, | |
| "eval_runtime": 333.7914, | |
| "eval_samples_per_second": 48.935, | |
| "eval_steps_per_second": 12.235, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011342837256064551, | |
| "grad_norm": 0.6714215278625488, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 1.8972, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.012374004279343147, | |
| "grad_norm": 1.4429042339324951, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 2.2593, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.013405171302621742, | |
| "grad_norm": 1.767311930656433, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 2.7356, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.014436338325900338, | |
| "grad_norm": 2.493459701538086, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 2.4359, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.015467505349178933, | |
| "grad_norm": 3.981605291366577, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 2.2622, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.015467505349178933, | |
| "eval_loss": 2.3954179286956787, | |
| "eval_runtime": 334.3325, | |
| "eval_samples_per_second": 48.856, | |
| "eval_steps_per_second": 12.215, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01649867237245753, | |
| "grad_norm": 0.597623348236084, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 1.8683, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.017529839395736123, | |
| "grad_norm": 1.2859327793121338, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 2.1469, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01856100641901472, | |
| "grad_norm": 1.5065349340438843, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 2.5904, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.019592173442293314, | |
| "grad_norm": 2.6285014152526855, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 2.2524, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02062334046557191, | |
| "grad_norm": 4.162689685821533, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 2.2073, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02062334046557191, | |
| "eval_loss": 2.3460395336151123, | |
| "eval_runtime": 334.257, | |
| "eval_samples_per_second": 48.867, | |
| "eval_steps_per_second": 12.218, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.021654507488850505, | |
| "grad_norm": 0.6041058301925659, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 1.8224, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.022685674512129102, | |
| "grad_norm": 1.3182774782180786, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 2.2141, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.023716841535407696, | |
| "grad_norm": 1.494461178779602, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 2.7371, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.024748008558686294, | |
| "grad_norm": 2.414562225341797, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 2.2599, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.025779175581964887, | |
| "grad_norm": 3.806607484817505, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 2.1804, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.025779175581964887, | |
| "eval_loss": 2.274019956588745, | |
| "eval_runtime": 333.7217, | |
| "eval_samples_per_second": 48.945, | |
| "eval_steps_per_second": 12.238, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.026810342605243485, | |
| "grad_norm": 0.5745736360549927, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 1.7065, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.02784150962852208, | |
| "grad_norm": 1.216685175895691, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 2.2073, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.028872676651800676, | |
| "grad_norm": 1.3834314346313477, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 2.6267, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.02990384367507927, | |
| "grad_norm": 2.0821757316589355, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 2.2572, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.030935010698357867, | |
| "grad_norm": 4.278872489929199, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 2.1662, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.030935010698357867, | |
| "eval_loss": 2.2416651248931885, | |
| "eval_runtime": 333.1876, | |
| "eval_samples_per_second": 49.023, | |
| "eval_steps_per_second": 12.257, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.031966177721636464, | |
| "grad_norm": 0.5629070997238159, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 1.7367, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.03299734474491506, | |
| "grad_norm": 1.3552706241607666, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 2.135, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.03402851176819365, | |
| "grad_norm": 1.389815330505371, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 2.669, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.035059678791472246, | |
| "grad_norm": 2.1797492504119873, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 2.1926, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.036090845814750847, | |
| "grad_norm": 3.770401954650879, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 2.1735, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.036090845814750847, | |
| "eval_loss": 2.213304042816162, | |
| "eval_runtime": 333.8272, | |
| "eval_samples_per_second": 48.93, | |
| "eval_steps_per_second": 12.234, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.03712201283802944, | |
| "grad_norm": 0.6478493213653564, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 1.7416, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.038153179861308034, | |
| "grad_norm": 1.3208801746368408, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 2.0733, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.03918434688458663, | |
| "grad_norm": 1.4734785556793213, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 2.6356, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04021551390786523, | |
| "grad_norm": 1.8664650917053223, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 2.2411, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.04124668093114382, | |
| "grad_norm": 3.517054796218872, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 2.0789, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04124668093114382, | |
| "eval_loss": 2.1788926124572754, | |
| "eval_runtime": 334.0731, | |
| "eval_samples_per_second": 48.893, | |
| "eval_steps_per_second": 12.225, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.042277847954422416, | |
| "grad_norm": 0.5625332593917847, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 1.7504, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.04330901497770101, | |
| "grad_norm": 1.5617921352386475, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 2.2538, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.04434018200097961, | |
| "grad_norm": 1.5214532613754272, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 2.6096, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.045371349024258205, | |
| "grad_norm": 2.148418664932251, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 2.182, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0464025160475368, | |
| "grad_norm": 3.7270758152008057, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 2.1063, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.0464025160475368, | |
| "eval_loss": 2.1697134971618652, | |
| "eval_runtime": 333.9603, | |
| "eval_samples_per_second": 48.91, | |
| "eval_steps_per_second": 12.229, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.04743368307081539, | |
| "grad_norm": 0.498226135969162, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 1.756, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.04846485009409399, | |
| "grad_norm": 1.1780967712402344, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 2.0653, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.04949601711737259, | |
| "grad_norm": 1.453464150428772, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 2.6079, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.05052718414065118, | |
| "grad_norm": 2.0182747840881348, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 2.1106, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.051558351163929775, | |
| "grad_norm": 3.5075230598449707, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 2.0581, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.051558351163929775, | |
| "eval_loss": 2.1618905067443848, | |
| "eval_runtime": 333.0388, | |
| "eval_samples_per_second": 49.045, | |
| "eval_steps_per_second": 12.263, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.052589518187208376, | |
| "grad_norm": 0.5434964895248413, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 1.77, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.05362068521048697, | |
| "grad_norm": 1.2367784976959229, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 2.1081, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.05465185223376556, | |
| "grad_norm": 1.470454454421997, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 2.5899, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.05568301925704416, | |
| "grad_norm": 2.281672477722168, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 2.1905, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.05671418628032276, | |
| "grad_norm": 3.330380916595459, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 2.074, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.05671418628032276, | |
| "eval_loss": 2.1590285301208496, | |
| "eval_runtime": 333.5902, | |
| "eval_samples_per_second": 48.964, | |
| "eval_steps_per_second": 12.243, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.05774535330360135, | |
| "grad_norm": 0.5410750508308411, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 1.7281, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.058776520326879945, | |
| "grad_norm": 1.255186915397644, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 2.0614, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.05980768735015854, | |
| "grad_norm": 1.453993558883667, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 2.5846, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.06083885437343714, | |
| "grad_norm": 1.7940559387207031, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 2.2761, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.061870021396715734, | |
| "grad_norm": 3.636902093887329, | |
| "learning_rate": 0.0, | |
| "loss": 2.0926, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.061870021396715734, | |
| "eval_loss": 2.1577975749969482, | |
| "eval_runtime": 333.6083, | |
| "eval_samples_per_second": 48.962, | |
| "eval_steps_per_second": 12.242, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.2563752110627226e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |