| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021739130434782608, | |
| "grad_norm": 21.980525970458984, | |
| "learning_rate": 0.0, | |
| "loss": 2.2134, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 20.06768798828125, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.5251, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06521739130434782, | |
| "grad_norm": 23.364561080932617, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.2033, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 19.796825408935547, | |
| "learning_rate": 3e-06, | |
| "loss": 1.9776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10869565217391304, | |
| "grad_norm": 21.887332916259766, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.2999, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13043478260869565, | |
| "grad_norm": 20.906566619873047, | |
| "learning_rate": 5e-06, | |
| "loss": 1.9261, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15217391304347827, | |
| "grad_norm": 20.153642654418945, | |
| "learning_rate": 4.992664502959351e-06, | |
| "loss": 1.8537, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 19.199687957763672, | |
| "learning_rate": 4.970701059450872e-06, | |
| "loss": 1.9019, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1956521739130435, | |
| "grad_norm": 17.73782730102539, | |
| "learning_rate": 4.934238559694448e-06, | |
| "loss": 1.564, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21739130434782608, | |
| "grad_norm": 16.246173858642578, | |
| "learning_rate": 4.883490980137327e-06, | |
| "loss": 1.6703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2391304347826087, | |
| "grad_norm": 1828651.875, | |
| "learning_rate": 4.8187561277552376e-06, | |
| "loss": 1.4389, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 13.8928861618042, | |
| "learning_rate": 4.740413892402639e-06, | |
| "loss": 1.3761, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2826086956521739, | |
| "grad_norm": 720403.375, | |
| "learning_rate": 4.648924017468003e-06, | |
| "loss": 1.212, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.30434782608695654, | |
| "grad_norm": 14.764030456542969, | |
| "learning_rate": 4.544823401916794e-06, | |
| "loss": 1.5574, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.32608695652173914, | |
| "grad_norm": 12.913108825683594, | |
| "learning_rate": 4.428722949554858e-06, | |
| "loss": 1.4192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 10.674172401428223, | |
| "learning_rate": 4.3013039840019675e-06, | |
| "loss": 1.2746, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3695652173913043, | |
| "grad_norm": 9.80074691772461, | |
| "learning_rate": 4.163314250413913e-06, | |
| "loss": 1.072, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.391304347826087, | |
| "grad_norm": 10.42562484741211, | |
| "learning_rate": 4.015563527416596e-06, | |
| "loss": 0.9013, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.41304347826086957, | |
| "grad_norm": 10.28138256072998, | |
| "learning_rate": 3.858918875003053e-06, | |
| "loss": 1.3421, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 9.2878999710083, | |
| "learning_rate": 3.6942995462806574e-06, | |
| "loss": 1.1947, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45652173913043476, | |
| "grad_norm": 10.689302444458008, | |
| "learning_rate": 3.5226715929283507e-06, | |
| "loss": 1.1843, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4782608695652174, | |
| "grad_norm": 11.090900421142578, | |
| "learning_rate": 3.345042196021257e-06, | |
| "loss": 1.2872, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 8.946170806884766, | |
| "learning_rate": 3.162453755491655e-06, | |
| "loss": 1.1389, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 7.288694381713867, | |
| "learning_rate": 2.975977772911671e-06, | |
| "loss": 1.0438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5434782608695652, | |
| "grad_norm": 7.09510612487793, | |
| "learning_rate": 2.786708563496002e-06, | |
| "loss": 0.7908, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5652173913043478, | |
| "grad_norm": 7.513128280639648, | |
| "learning_rate": 2.595756834225089e-06, | |
| "loss": 0.8884, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5869565217391305, | |
| "grad_norm": 16309.765625, | |
| "learning_rate": 2.404243165774912e-06, | |
| "loss": 1.3966, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 9.216928482055664, | |
| "learning_rate": 2.2132914365039993e-06, | |
| "loss": 0.7335, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6304347826086957, | |
| "grad_norm": 8.130733489990234, | |
| "learning_rate": 2.024022227088329e-06, | |
| "loss": 1.4854, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6521739130434783, | |
| "grad_norm": 7.4941534996032715, | |
| "learning_rate": 1.8375462445083464e-06, | |
| "loss": 0.6889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6739130434782609, | |
| "grad_norm": 8.134994506835938, | |
| "learning_rate": 1.6549578039787436e-06, | |
| "loss": 1.0505, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 7.74264669418335, | |
| "learning_rate": 1.4773284070716504e-06, | |
| "loss": 0.9686, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.717391304347826, | |
| "grad_norm": 8.992671012878418, | |
| "learning_rate": 1.3057004537193424e-06, | |
| "loss": 1.0842, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7391304347826086, | |
| "grad_norm": 7.693203449249268, | |
| "learning_rate": 1.1410811249969475e-06, | |
| "loss": 0.8311, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7608695652173914, | |
| "grad_norm": 6.577566623687744, | |
| "learning_rate": 9.844364725834058e-07, | |
| "loss": 0.8217, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 10.145994186401367, | |
| "learning_rate": 8.366857495860869e-07, | |
| "loss": 0.8935, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8043478260869565, | |
| "grad_norm": 6.9202375411987305, | |
| "learning_rate": 6.986960159980327e-07, | |
| "loss": 0.8456, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8260869565217391, | |
| "grad_norm": 6.42577600479126, | |
| "learning_rate": 5.712770504451426e-07, | |
| "loss": 0.7391, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8478260869565217, | |
| "grad_norm": 8.795654296875, | |
| "learning_rate": 4.55176598083206e-07, | |
| "loss": 1.1633, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 9.373461723327637, | |
| "learning_rate": 3.510759825319976e-07, | |
| "loss": 0.8627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8913043478260869, | |
| "grad_norm": 7.181187629699707, | |
| "learning_rate": 2.5958610759736133e-07, | |
| "loss": 0.8084, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9130434782608695, | |
| "grad_norm": 7.831035137176514, | |
| "learning_rate": 1.8124387224476347e-07, | |
| "loss": 0.8626, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9347826086956522, | |
| "grad_norm": 8.75483512878418, | |
| "learning_rate": 1.1650901986267365e-07, | |
| "loss": 1.0262, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 6.860268592834473, | |
| "learning_rate": 6.576144030555259e-08, | |
| "loss": 0.9124, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9782608695652174, | |
| "grad_norm": 8.375471115112305, | |
| "learning_rate": 2.9298940549128962e-08, | |
| "loss": 0.9084, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.354442596435547, | |
| "learning_rate": 7.335497040648898e-09, | |
| "loss": 1.0854, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 46, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 514794267553536.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |