| { | |
| "best_metric": 2.978853464126587, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5390835579514824, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01078167115902965, | |
| "grad_norm": 4.415461540222168, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01078167115902965, | |
| "eval_loss": 4.603348731994629, | |
| "eval_runtime": 3.1244, | |
| "eval_samples_per_second": 16.003, | |
| "eval_steps_per_second": 4.161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0215633423180593, | |
| "grad_norm": 5.256311893463135, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03234501347708895, | |
| "grad_norm": 4.593958854675293, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.1495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0431266846361186, | |
| "grad_norm": 3.407309055328369, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.4765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05390835579514825, | |
| "grad_norm": 2.637965440750122, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0646900269541779, | |
| "grad_norm": 2.010531187057495, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.283, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 1.616788387298584, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.8039, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0862533692722372, | |
| "grad_norm": 1.2796103954315186, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.3466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09703504043126684, | |
| "grad_norm": 1.040218710899353, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.9491, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1078167115902965, | |
| "grad_norm": 0.9119211435317993, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7575, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11859838274932614, | |
| "grad_norm": 0.5928375720977783, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.6597, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1293800539083558, | |
| "grad_norm": 0.2615983486175537, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3557, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14016172506738545, | |
| "grad_norm": 3.63720440864563, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.8158, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 2.683013677597046, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.3179, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16172506738544473, | |
| "grad_norm": 2.0742197036743164, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.7292, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1725067385444744, | |
| "grad_norm": 1.6573094129562378, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.1911, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18328840970350405, | |
| "grad_norm": 1.4329888820648193, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.7933, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1940700808625337, | |
| "grad_norm": 1.186693787574768, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.4546, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20485175202156333, | |
| "grad_norm": 1.0899081230163574, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.1654, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.215633423180593, | |
| "grad_norm": 0.9327430129051208, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.8684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": 0.5573920607566833, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.7372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2371967654986523, | |
| "grad_norm": 0.4957171082496643, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.5848, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24797843665768193, | |
| "grad_norm": 0.557580292224884, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.6152, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2587601078167116, | |
| "grad_norm": 0.45015281438827515, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.3927, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2695417789757412, | |
| "grad_norm": 0.33957406878471375, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.4163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2695417789757412, | |
| "eval_loss": 3.217378854751587, | |
| "eval_runtime": 2.6153, | |
| "eval_samples_per_second": 19.118, | |
| "eval_steps_per_second": 4.971, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2803234501347709, | |
| "grad_norm": 2.7146284580230713, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.7519, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29110512129380056, | |
| "grad_norm": 1.6230659484863281, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.024, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 1.2240214347839355, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.6623, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31266846361185985, | |
| "grad_norm": 0.9349792003631592, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.369, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32345013477088946, | |
| "grad_norm": 1.0889204740524292, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.0932, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33423180592991913, | |
| "grad_norm": 1.3626528978347778, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.8357, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3450134770889488, | |
| "grad_norm": 1.3906242847442627, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.6933, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3557951482479784, | |
| "grad_norm": 1.2971469163894653, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.6283, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3665768194070081, | |
| "grad_norm": 1.0674742460250854, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.5326, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.9163751006126404, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.5948, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3881401617250674, | |
| "grad_norm": 0.7036921381950378, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.4848, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.39892183288409705, | |
| "grad_norm": 0.4230988323688507, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.3287, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.40970350404312667, | |
| "grad_norm": 2.271873950958252, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.5126, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.42048517520215634, | |
| "grad_norm": 2.1975555419921875, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.9926, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.431266846361186, | |
| "grad_norm": 1.8238301277160645, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.5651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4420485175202156, | |
| "grad_norm": 1.4213221073150635, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.2511, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4528301886792453, | |
| "grad_norm": 1.154116153717041, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.9906, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4636118598382749, | |
| "grad_norm": 0.9232210516929626, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.8678, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4743935309973046, | |
| "grad_norm": 0.5954862236976624, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.74, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.48517520215633425, | |
| "grad_norm": 0.3422981798648834, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.5759, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49595687331536387, | |
| "grad_norm": 0.36076000332832336, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.5384, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5067385444743935, | |
| "grad_norm": 0.41339829564094543, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.4947, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5175202156334232, | |
| "grad_norm": 0.42015019059181213, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.5452, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5283018867924528, | |
| "grad_norm": 0.48948684334754944, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.3207, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5390835579514824, | |
| "grad_norm": 0.32463398575782776, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5390835579514824, | |
| "eval_loss": 2.978853464126587, | |
| "eval_runtime": 2.2172, | |
| "eval_samples_per_second": 22.551, | |
| "eval_steps_per_second": 5.863, | |
| "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": 1.5595304203268915e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |