|
{ |
|
"best_metric": 1.6570053100585938, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.14144271570014144, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.002828854314002829, |
|
"grad_norm": 4.835982322692871, |
|
"learning_rate": 5e-06, |
|
"loss": 2.7483, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.002828854314002829, |
|
"eval_loss": 2.652212142944336, |
|
"eval_runtime": 28.5954, |
|
"eval_samples_per_second": 20.843, |
|
"eval_steps_per_second": 2.623, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.005657708628005658, |
|
"grad_norm": 5.14434289932251, |
|
"learning_rate": 1e-05, |
|
"loss": 2.6398, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.008486562942008486, |
|
"grad_norm": 4.789090156555176, |
|
"learning_rate": 1.5e-05, |
|
"loss": 2.7924, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.011315417256011316, |
|
"grad_norm": 4.524115562438965, |
|
"learning_rate": 2e-05, |
|
"loss": 2.787, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.014144271570014143, |
|
"grad_norm": 4.898167133331299, |
|
"learning_rate": 2.5e-05, |
|
"loss": 2.6675, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.016973125884016973, |
|
"grad_norm": 4.676875114440918, |
|
"learning_rate": 3e-05, |
|
"loss": 2.68, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.019801980198019802, |
|
"grad_norm": 5.323249340057373, |
|
"learning_rate": 3.5e-05, |
|
"loss": 2.6687, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.02263083451202263, |
|
"grad_norm": 5.85331392288208, |
|
"learning_rate": 4e-05, |
|
"loss": 2.6787, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.02545968882602546, |
|
"grad_norm": 4.22189474105835, |
|
"learning_rate": 4.5e-05, |
|
"loss": 2.5529, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.028288543140028287, |
|
"grad_norm": 4.426727771759033, |
|
"learning_rate": 5e-05, |
|
"loss": 2.7338, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.031117397454031116, |
|
"grad_norm": 4.649036884307861, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 2.5902, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.033946251768033946, |
|
"grad_norm": 5.093221664428711, |
|
"learning_rate": 6e-05, |
|
"loss": 2.5167, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.036775106082036775, |
|
"grad_norm": 4.573429584503174, |
|
"learning_rate": 6.500000000000001e-05, |
|
"loss": 2.409, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.039603960396039604, |
|
"grad_norm": 4.811120986938477, |
|
"learning_rate": 7e-05, |
|
"loss": 2.5057, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.042432814710042434, |
|
"grad_norm": 4.52741003036499, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 2.2795, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.04526166902404526, |
|
"grad_norm": 4.902586936950684, |
|
"learning_rate": 8e-05, |
|
"loss": 2.2757, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.04809052333804809, |
|
"grad_norm": 4.699262619018555, |
|
"learning_rate": 8.5e-05, |
|
"loss": 2.2644, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.05091937765205092, |
|
"grad_norm": 4.109030246734619, |
|
"learning_rate": 9e-05, |
|
"loss": 2.3355, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.05374823196605375, |
|
"grad_norm": 4.7285943031311035, |
|
"learning_rate": 9.5e-05, |
|
"loss": 2.1301, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.056577086280056574, |
|
"grad_norm": 3.8704135417938232, |
|
"learning_rate": 0.0001, |
|
"loss": 2.2602, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0594059405940594, |
|
"grad_norm": 4.164304733276367, |
|
"learning_rate": 9.972609476841367e-05, |
|
"loss": 2.0421, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.06223479490806223, |
|
"grad_norm": 4.296514987945557, |
|
"learning_rate": 9.890738003669029e-05, |
|
"loss": 2.0358, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.06506364922206506, |
|
"grad_norm": 4.264124393463135, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 2.1852, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.06789250353606789, |
|
"grad_norm": 4.8569016456604, |
|
"learning_rate": 9.567727288213005e-05, |
|
"loss": 2.0011, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.07072135785007072, |
|
"grad_norm": 4.313958168029785, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 1.8973, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07072135785007072, |
|
"eval_loss": 1.8785371780395508, |
|
"eval_runtime": 28.6135, |
|
"eval_samples_per_second": 20.829, |
|
"eval_steps_per_second": 2.621, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07355021216407355, |
|
"grad_norm": 5.226122856140137, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 1.9575, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.07637906647807638, |
|
"grad_norm": 5.659665107727051, |
|
"learning_rate": 8.715724127386972e-05, |
|
"loss": 1.8721, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.07920792079207921, |
|
"grad_norm": 8.166505813598633, |
|
"learning_rate": 8.345653031794292e-05, |
|
"loss": 2.0821, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.08203677510608204, |
|
"grad_norm": 6.374522686004639, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 1.8542, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.08486562942008487, |
|
"grad_norm": 6.295704364776611, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.925, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0876944837340877, |
|
"grad_norm": 6.594677448272705, |
|
"learning_rate": 7.033683215379002e-05, |
|
"loss": 1.8658, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.09052333804809053, |
|
"grad_norm": 5.89158296585083, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 1.8313, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.09335219236209336, |
|
"grad_norm": 6.842565059661865, |
|
"learning_rate": 6.0395584540887963e-05, |
|
"loss": 1.8701, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.09618104667609619, |
|
"grad_norm": 5.680135726928711, |
|
"learning_rate": 5.522642316338268e-05, |
|
"loss": 1.9606, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.09900990099009901, |
|
"grad_norm": 6.305683135986328, |
|
"learning_rate": 5e-05, |
|
"loss": 1.8179, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.10183875530410184, |
|
"grad_norm": 6.212825775146484, |
|
"learning_rate": 4.477357683661734e-05, |
|
"loss": 1.8664, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.10466760961810467, |
|
"grad_norm": 5.87861442565918, |
|
"learning_rate": 3.960441545911204e-05, |
|
"loss": 1.7242, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.1074964639321075, |
|
"grad_norm": 7.144162654876709, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 1.916, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.11032531824611033, |
|
"grad_norm": 7.015084266662598, |
|
"learning_rate": 2.9663167846209998e-05, |
|
"loss": 1.7529, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.11315417256011315, |
|
"grad_norm": 5.531047344207764, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 1.6901, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11598302687411598, |
|
"grad_norm": 6.126357555389404, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 1.8466, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.1188118811881188, |
|
"grad_norm": 6.837929725646973, |
|
"learning_rate": 1.6543469682057106e-05, |
|
"loss": 1.8127, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.12164073550212164, |
|
"grad_norm": 6.8123016357421875, |
|
"learning_rate": 1.2842758726130283e-05, |
|
"loss": 1.6257, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.12446958981612447, |
|
"grad_norm": 5.996006011962891, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 1.653, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.1272984441301273, |
|
"grad_norm": 6.896071910858154, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 1.7862, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.13012729844413012, |
|
"grad_norm": 6.469790935516357, |
|
"learning_rate": 4.322727117869951e-06, |
|
"loss": 1.7479, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.13295615275813297, |
|
"grad_norm": 7.635956764221191, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 1.6934, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.13578500707213578, |
|
"grad_norm": 5.47963809967041, |
|
"learning_rate": 1.0926199633097157e-06, |
|
"loss": 1.8348, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.13861386138613863, |
|
"grad_norm": 6.420375823974609, |
|
"learning_rate": 2.7390523158633554e-07, |
|
"loss": 1.7703, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.14144271570014144, |
|
"grad_norm": 6.020177841186523, |
|
"learning_rate": 0.0, |
|
"loss": 1.6216, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.14144271570014144, |
|
"eval_loss": 1.6570053100585938, |
|
"eval_runtime": 28.6131, |
|
"eval_samples_per_second": 20.83, |
|
"eval_steps_per_second": 2.621, |
|
"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": 3, |
|
"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": 2.6964626767872e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|