| { | |
| "best_metric": 4.389261722564697, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08708904855214457, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017417809710428913, | |
| "grad_norm": 1042.4998779296875, | |
| "learning_rate": 5e-05, | |
| "loss": 52.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017417809710428913, | |
| "eval_loss": 95.80888366699219, | |
| "eval_runtime": 128.0354, | |
| "eval_samples_per_second": 30.21, | |
| "eval_steps_per_second": 3.78, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034835619420857827, | |
| "grad_norm": 1335.59716796875, | |
| "learning_rate": 0.0001, | |
| "loss": 66.1445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005225342913128674, | |
| "grad_norm": 244.45648193359375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 54.2622, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006967123884171565, | |
| "grad_norm": 182.58251953125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 44.3626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008708904855214456, | |
| "grad_norm": 222.32257080078125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 37.7121, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010450685826257348, | |
| "grad_norm": 240.82568359375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 22.2959, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012192466797300239, | |
| "grad_norm": 252.58872985839844, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 7.2634, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01393424776834313, | |
| "grad_norm": 8.834219932556152, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.4485, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015676028739386023, | |
| "grad_norm": 7.470920085906982, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.4602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017417809710428913, | |
| "grad_norm": 48.436824798583984, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.6101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019159590681471803, | |
| "grad_norm": 39.14765167236328, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.5374, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020901371652514697, | |
| "grad_norm": 11.199342727661133, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.44, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022643152623557587, | |
| "grad_norm": 13.544066429138184, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.8266, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.024384933594600477, | |
| "grad_norm": 9.120245933532715, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.4304, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02612671456564337, | |
| "grad_norm": 7.594675540924072, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.802, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02786849553668626, | |
| "grad_norm": 6.660674571990967, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.5614, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029610276507729152, | |
| "grad_norm": 7.0615925788879395, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.4997, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.031352057478772045, | |
| "grad_norm": 6.209261417388916, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.6316, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.033093838449814936, | |
| "grad_norm": 7.270112991333008, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.6835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034835619420857826, | |
| "grad_norm": 15.498638153076172, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5747, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.036577400391900716, | |
| "grad_norm": 8.84870719909668, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.4316, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.038319181362943606, | |
| "grad_norm": 6.131610870361328, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.4651, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.040060962333986504, | |
| "grad_norm": 8.077975273132324, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.8909, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.041802743305029394, | |
| "grad_norm": 4.703813076019287, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.6565, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.043544524276072284, | |
| "grad_norm": 8.461095809936523, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.8622, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043544524276072284, | |
| "eval_loss": 4.673962593078613, | |
| "eval_runtime": 128.7456, | |
| "eval_samples_per_second": 30.044, | |
| "eval_steps_per_second": 3.759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.045286305247115174, | |
| "grad_norm": 12.151058197021484, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3135, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.047028086218158065, | |
| "grad_norm": 10.991308212280273, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 5.1292, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.048769867189200955, | |
| "grad_norm": 9.190849304199219, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 4.7655, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05051164816024385, | |
| "grad_norm": 7.7433271408081055, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.5119, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05225342913128674, | |
| "grad_norm": 6.827936172485352, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.6849, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05399521010232963, | |
| "grad_norm": 5.0018086433410645, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.3018, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05573699107337252, | |
| "grad_norm": 4.091928482055664, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.3418, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05747877204441541, | |
| "grad_norm": 3.9832217693328857, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.3143, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.059220553015458303, | |
| "grad_norm": 5.432229518890381, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.3009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0609623339865012, | |
| "grad_norm": 7.460689544677734, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.5947, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06270411495754409, | |
| "grad_norm": 8.065680503845215, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.5716, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06444589592858697, | |
| "grad_norm": 8.407084465026855, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.5716, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06618767689962987, | |
| "grad_norm": 4.074368476867676, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.5244, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06792945787067277, | |
| "grad_norm": 4.50044059753418, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 4.4761, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06967123884171565, | |
| "grad_norm": 4.544261455535889, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 4.3594, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07141301981275855, | |
| "grad_norm": 4.384801864624023, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 4.2091, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07315480078380143, | |
| "grad_norm": 3.783501148223877, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.4318, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07489658175484433, | |
| "grad_norm": 3.7358858585357666, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 4.2778, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07663836272588721, | |
| "grad_norm": 3.247150421142578, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.0539, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07838014369693011, | |
| "grad_norm": 3.662083625793457, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.018, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08012192466797301, | |
| "grad_norm": 3.8572452068328857, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.3065, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08186370563901589, | |
| "grad_norm": 4.723749160766602, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.4023, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08360548661005879, | |
| "grad_norm": 7.412983417510986, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.5248, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08534726758110167, | |
| "grad_norm": 6.161107063293457, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.5663, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08708904855214457, | |
| "grad_norm": 8.415834426879883, | |
| "learning_rate": 0.0, | |
| "loss": 4.6307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08708904855214457, | |
| "eval_loss": 4.389261722564697, | |
| "eval_runtime": 128.3606, | |
| "eval_samples_per_second": 30.134, | |
| "eval_steps_per_second": 3.771, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |