| { | |
| "best_metric": 0.9690943360328674, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4179728317659352, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008359456635318705, | |
| "grad_norm": 0.528317391872406, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008359456635318705, | |
| "eval_loss": 1.539870023727417, | |
| "eval_runtime": 1.8349, | |
| "eval_samples_per_second": 27.25, | |
| "eval_steps_per_second": 7.085, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01671891327063741, | |
| "grad_norm": 0.8531002998352051, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4622, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025078369905956112, | |
| "grad_norm": 0.7735457420349121, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.4612, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03343782654127482, | |
| "grad_norm": 0.7207358479499817, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04179728317659352, | |
| "grad_norm": 0.7249660491943359, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3701, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.050156739811912224, | |
| "grad_norm": 0.7058163285255432, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3037, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05851619644723093, | |
| "grad_norm": 0.730956494808197, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06687565308254964, | |
| "grad_norm": 0.663693904876709, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.2384, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07523510971786834, | |
| "grad_norm": 0.5950675010681152, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2468, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08359456635318704, | |
| "grad_norm": 0.5878185033798218, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.201, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09195402298850575, | |
| "grad_norm": 0.7090585827827454, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.2783, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10031347962382445, | |
| "grad_norm": 0.6280428767204285, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10867293625914315, | |
| "grad_norm": 0.6365631818771362, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9264, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11703239289446186, | |
| "grad_norm": 0.5153186917304993, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.0121, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12539184952978055, | |
| "grad_norm": 0.44470345973968506, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.0041, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13375130616509928, | |
| "grad_norm": 0.4626646339893341, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0477, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14211076280041798, | |
| "grad_norm": 0.46722468733787537, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15047021943573669, | |
| "grad_norm": 0.46091338992118835, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.1099, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1588296760710554, | |
| "grad_norm": 0.3986632227897644, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1126, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1671891327063741, | |
| "grad_norm": 0.38878515362739563, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1755485893416928, | |
| "grad_norm": 0.4430249333381653, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.1306, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1839080459770115, | |
| "grad_norm": 0.49307769536972046, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.0652, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1922675026123302, | |
| "grad_norm": 0.4030891954898834, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.1236, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2006269592476489, | |
| "grad_norm": 0.43994420766830444, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2089864158829676, | |
| "grad_norm": 0.4256235361099243, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0948, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2089864158829676, | |
| "eval_loss": 1.001101016998291, | |
| "eval_runtime": 1.1638, | |
| "eval_samples_per_second": 42.962, | |
| "eval_steps_per_second": 11.17, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2173458725182863, | |
| "grad_norm": 0.4371124804019928, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8685, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.22570532915360503, | |
| "grad_norm": 0.39926087856292725, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.959, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23406478578892373, | |
| "grad_norm": 0.42637521028518677, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.0602, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.40809735655784607, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.0049, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2507836990595611, | |
| "grad_norm": 0.4572559595108032, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.0438, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25914315569487983, | |
| "grad_norm": 0.39180684089660645, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.97, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26750261233019856, | |
| "grad_norm": 0.4096227288246155, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0363, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.4008356034755707, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0532, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.28422152560083597, | |
| "grad_norm": 0.4251631796360016, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0442, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.29258098223615464, | |
| "grad_norm": 0.4049515128135681, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0944, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30094043887147337, | |
| "grad_norm": 0.47100144624710083, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0576, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.30929989550679204, | |
| "grad_norm": 0.4920854866504669, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0766, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3176593521421108, | |
| "grad_norm": 0.45009514689445496, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8845, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.32601880877742945, | |
| "grad_norm": 0.4449792802333832, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9975, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3343782654127482, | |
| "grad_norm": 0.4090271294116974, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9589, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34273772204806685, | |
| "grad_norm": 0.3993270993232727, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.9349, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3510971786833856, | |
| "grad_norm": 0.3873380124568939, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.0709, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3594566353187043, | |
| "grad_norm": 0.37261834740638733, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.0381, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.367816091954023, | |
| "grad_norm": 0.3891456127166748, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0721, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3761755485893417, | |
| "grad_norm": 0.3773375153541565, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9904, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3845350052246604, | |
| "grad_norm": 0.42510074377059937, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0608, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3928944618599791, | |
| "grad_norm": 0.4486747086048126, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0842, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4012539184952978, | |
| "grad_norm": 0.4293101727962494, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.1138, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4096133751306165, | |
| "grad_norm": 0.4755518138408661, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0434, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4179728317659352, | |
| "grad_norm": 0.4889579713344574, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1573, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4179728317659352, | |
| "eval_loss": 0.9690943360328674, | |
| "eval_runtime": 1.1476, | |
| "eval_samples_per_second": 43.568, | |
| "eval_steps_per_second": 11.328, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |