| { | |
| "best_metric": 0.8120872974395752, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.013358268768367619, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005343307507347048, | |
| "grad_norm": 1.9597400426864624, | |
| "learning_rate": 2e-05, | |
| "loss": 4.8835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005343307507347048, | |
| "eval_loss": 1.2078794240951538, | |
| "eval_runtime": 171.5758, | |
| "eval_samples_per_second": 4.593, | |
| "eval_steps_per_second": 2.296, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010686615014694097, | |
| "grad_norm": 2.208524227142334, | |
| "learning_rate": 4e-05, | |
| "loss": 4.0019, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016029922522041143, | |
| "grad_norm": 2.122452974319458, | |
| "learning_rate": 6e-05, | |
| "loss": 4.6899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021373230029388193, | |
| "grad_norm": 1.9214311838150024, | |
| "learning_rate": 8e-05, | |
| "loss": 4.4438, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026716537536735237, | |
| "grad_norm": 2.9775564670562744, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026716537536735237, | |
| "eval_loss": 1.1925312280654907, | |
| "eval_runtime": 171.436, | |
| "eval_samples_per_second": 4.596, | |
| "eval_steps_per_second": 2.298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032059845044082286, | |
| "grad_norm": 2.498185396194458, | |
| "learning_rate": 0.00012, | |
| "loss": 4.3008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037403152551429334, | |
| "grad_norm": 2.962278366088867, | |
| "learning_rate": 0.00014, | |
| "loss": 4.8447, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004274646005877639, | |
| "grad_norm": 2.893937110900879, | |
| "learning_rate": 0.00016, | |
| "loss": 4.5715, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004808976756612343, | |
| "grad_norm": 2.95237398147583, | |
| "learning_rate": 0.00018, | |
| "loss": 4.1868, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0053433075073470475, | |
| "grad_norm": 3.5613887310028076, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0053433075073470475, | |
| "eval_loss": 0.9832201600074768, | |
| "eval_runtime": 171.8289, | |
| "eval_samples_per_second": 4.586, | |
| "eval_steps_per_second": 2.293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005877638258081752, | |
| "grad_norm": 3.8575327396392822, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.5685, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006411969008816457, | |
| "grad_norm": 3.1404190063476562, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.4437, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006946299759551162, | |
| "grad_norm": 3.9936773777008057, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.7143, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007480630510285867, | |
| "grad_norm": 4.532442092895508, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.8547, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008014961261020572, | |
| "grad_norm": 4.569597244262695, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.3982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008014961261020572, | |
| "eval_loss": 0.8725337982177734, | |
| "eval_runtime": 171.3387, | |
| "eval_samples_per_second": 4.599, | |
| "eval_steps_per_second": 2.3, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008549292011755277, | |
| "grad_norm": 4.278989791870117, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.8996, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009083622762489982, | |
| "grad_norm": 4.710971355438232, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.6165, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009617953513224685, | |
| "grad_norm": 5.305459976196289, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.6981, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01015228426395939, | |
| "grad_norm": 4.7451934814453125, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.6357, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010686615014694095, | |
| "grad_norm": 4.512779712677002, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.6611, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010686615014694095, | |
| "eval_loss": 0.8237693309783936, | |
| "eval_runtime": 171.3489, | |
| "eval_samples_per_second": 4.599, | |
| "eval_steps_per_second": 2.299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0112209457654288, | |
| "grad_norm": 4.862582206726074, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.1713, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011755276516163505, | |
| "grad_norm": 4.579098701477051, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.1525, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01228960726689821, | |
| "grad_norm": 4.197018146514893, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.01, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012823938017632914, | |
| "grad_norm": 4.057913780212402, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.2771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013358268768367619, | |
| "grad_norm": 4.654407501220703, | |
| "learning_rate": 0.0, | |
| "loss": 3.787, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013358268768367619, | |
| "eval_loss": 0.8120872974395752, | |
| "eval_runtime": 170.5567, | |
| "eval_samples_per_second": 4.62, | |
| "eval_steps_per_second": 2.31, | |
| "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": 8143665679564800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |