| { | |
| "best_metric": 3.5254595279693604, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.022573363431151242, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009029345372460496, | |
| "grad_norm": 0.5397587418556213, | |
| "learning_rate": 2e-05, | |
| "loss": 4.8343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009029345372460496, | |
| "eval_loss": 4.486961841583252, | |
| "eval_runtime": 74.5945, | |
| "eval_samples_per_second": 6.261, | |
| "eval_steps_per_second": 3.137, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018058690744920992, | |
| "grad_norm": 0.5734784007072449, | |
| "learning_rate": 4e-05, | |
| "loss": 4.6517, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002708803611738149, | |
| "grad_norm": 0.516501247882843, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1793, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036117381489841984, | |
| "grad_norm": 0.5289381146430969, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0826, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "grad_norm": 0.5648006796836853, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4783, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "eval_loss": 4.469165325164795, | |
| "eval_runtime": 73.412, | |
| "eval_samples_per_second": 6.361, | |
| "eval_steps_per_second": 3.187, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005417607223476298, | |
| "grad_norm": 0.6955599784851074, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7307, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006320541760722348, | |
| "grad_norm": 0.6882440447807312, | |
| "learning_rate": 0.00014, | |
| "loss": 4.3198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007223476297968397, | |
| "grad_norm": 0.7614045143127441, | |
| "learning_rate": 0.00016, | |
| "loss": 4.3397, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008126410835214447, | |
| "grad_norm": 0.9158193469047546, | |
| "learning_rate": 0.00018, | |
| "loss": 4.5137, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 1.0128803253173828, | |
| "learning_rate": 0.0002, | |
| "loss": 4.35, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "eval_loss": 4.053124904632568, | |
| "eval_runtime": 72.7097, | |
| "eval_samples_per_second": 6.423, | |
| "eval_steps_per_second": 3.218, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009932279909706547, | |
| "grad_norm": 0.835163414478302, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.4282, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010835214446952596, | |
| "grad_norm": 1.1635563373565674, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.6538, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011738148984198645, | |
| "grad_norm": 1.4114489555358887, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.7767, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012641083521444696, | |
| "grad_norm": 1.5940505266189575, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.1882, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 1.4813003540039062, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.06, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "eval_loss": 3.730433940887451, | |
| "eval_runtime": 72.6114, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 3.223, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014446952595936794, | |
| "grad_norm": 1.7925143241882324, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.1655, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015349887133182845, | |
| "grad_norm": 1.607529878616333, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.8114, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016252821670428894, | |
| "grad_norm": 1.4072641134262085, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.7555, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017155756207674944, | |
| "grad_norm": 1.3798819780349731, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.8308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 1.4967929124832153, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "eval_loss": 3.565016269683838, | |
| "eval_runtime": 72.8542, | |
| "eval_samples_per_second": 6.41, | |
| "eval_steps_per_second": 3.212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018961625282167043, | |
| "grad_norm": 1.2683284282684326, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.4791, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019864559819413093, | |
| "grad_norm": 1.385071873664856, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.6829, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02076749435665914, | |
| "grad_norm": 1.4484951496124268, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.4422, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02167042889390519, | |
| "grad_norm": 1.30351722240448, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.6403, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 1.307582974433899, | |
| "learning_rate": 0.0, | |
| "loss": 3.5491, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "eval_loss": 3.5254595279693604, | |
| "eval_runtime": 72.7632, | |
| "eval_samples_per_second": 6.418, | |
| "eval_steps_per_second": 3.216, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 4530853719834624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |