| { | |
| "best_metric": 0.1300944834947586, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.32480714575720665, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012992285830288266, | |
| "grad_norm": 36.630287170410156, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.1038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012992285830288266, | |
| "eval_loss": 8.06094741821289, | |
| "eval_runtime": 1.481, | |
| "eval_samples_per_second": 33.762, | |
| "eval_steps_per_second": 8.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025984571660576532, | |
| "grad_norm": 36.71709060668945, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.9426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0389768574908648, | |
| "grad_norm": 31.190719604492188, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.051969143321153065, | |
| "grad_norm": 27.901527404785156, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 5.3213, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06496142915144133, | |
| "grad_norm": 19.23626708984375, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 3.1653, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0779537149817296, | |
| "grad_norm": 25.957687377929688, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0286, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09094600081201787, | |
| "grad_norm": 21.65407371520996, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.2344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10393828664230613, | |
| "grad_norm": 6.849808692932129, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.6661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11693057247259439, | |
| "grad_norm": 8.28010368347168, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12992285830288267, | |
| "grad_norm": 6.745442867279053, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.4975, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14291514413317094, | |
| "grad_norm": 7.655923366546631, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.3611, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1559074299634592, | |
| "grad_norm": 7.9347124099731445, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.2793, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16889971579374746, | |
| "grad_norm": 4.294223785400391, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.1923, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18189200162403574, | |
| "grad_norm": 1.2570604085922241, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.1265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19488428745432398, | |
| "grad_norm": 2.589317798614502, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20787657328461226, | |
| "grad_norm": 1.269200325012207, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0922, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22086885911490053, | |
| "grad_norm": 11.871465682983398, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.1883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23386114494518878, | |
| "grad_norm": 6.418728828430176, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1336, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24685343077547706, | |
| "grad_norm": 3.559746026992798, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.091, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25984571660576533, | |
| "grad_norm": 3.894230604171753, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.1084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2728380024360536, | |
| "grad_norm": 2.0176477432250977, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2858302882663419, | |
| "grad_norm": 3.4982409477233887, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.1054, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2988225740966301, | |
| "grad_norm": 0.9820318818092346, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0746, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3118148599269184, | |
| "grad_norm": 3.725250482559204, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1343, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32480714575720665, | |
| "grad_norm": 4.605804920196533, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.1789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32480714575720665, | |
| "eval_loss": 0.1300944834947586, | |
| "eval_runtime": 1.4881, | |
| "eval_samples_per_second": 33.599, | |
| "eval_steps_per_second": 8.736, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.47650456322048e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |