| { | |
| "best_metric": 1.4780610799789429, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01063264221158958, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "grad_norm": 22.06287956237793, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1922, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 1.5707638263702393, | |
| "eval_runtime": 62.6418, | |
| "eval_samples_per_second": 15.804, | |
| "eval_steps_per_second": 7.902, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": 20.821876525878906, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 18.974714279174805, | |
| "learning_rate": 6e-05, | |
| "loss": 6.379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": 22.095287322998047, | |
| "learning_rate": 8e-05, | |
| "loss": 6.7096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "grad_norm": 25.34409523010254, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0309, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002126528442317916, | |
| "eval_loss": 1.5572835206985474, | |
| "eval_runtime": 60.7475, | |
| "eval_samples_per_second": 16.297, | |
| "eval_steps_per_second": 8.148, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 22.834753036499023, | |
| "learning_rate": 0.00012, | |
| "loss": 6.2256, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029771398192450825, | |
| "grad_norm": 16.482425689697266, | |
| "learning_rate": 0.00014, | |
| "loss": 6.4575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": 18.84016227722168, | |
| "learning_rate": 0.00016, | |
| "loss": 6.3556, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 14.55759048461914, | |
| "learning_rate": 0.00018, | |
| "loss": 6.7139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": 18.770845413208008, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "eval_loss": 1.5156612396240234, | |
| "eval_runtime": 61.0041, | |
| "eval_samples_per_second": 16.228, | |
| "eval_steps_per_second": 8.114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 45.95751953125, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.2321, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 17.54123878479004, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 5.4011, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005528973950026581, | |
| "grad_norm": 18.338685989379883, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.1812, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005954279638490165, | |
| "grad_norm": 18.87067413330078, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 6.1219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 18.159162521362305, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.4642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "eval_loss": 1.487715482711792, | |
| "eval_runtime": 60.2255, | |
| "eval_samples_per_second": 16.438, | |
| "eval_steps_per_second": 8.219, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "grad_norm": 16.359085083007812, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.1706, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007230196703880914, | |
| "grad_norm": 23.439176559448242, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.5563, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 26.228099822998047, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 5.9734, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00808080808080808, | |
| "grad_norm": 19.510398864746094, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 6.3272, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": 25.489709854125977, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.0794, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "eval_loss": 1.4817118644714355, | |
| "eval_runtime": 61.227, | |
| "eval_samples_per_second": 16.169, | |
| "eval_steps_per_second": 8.085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 18.555313110351562, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 6.0527, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 19.77273941040039, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.6609, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009782030834662414, | |
| "grad_norm": 19.876432418823242, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 5.8107, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 16.81047821044922, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.8589, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "grad_norm": 15.21854019165039, | |
| "learning_rate": 0.0, | |
| "loss": 5.6738, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01063264221158958, | |
| "eval_loss": 1.4780610799789429, | |
| "eval_runtime": 60.261, | |
| "eval_samples_per_second": 16.429, | |
| "eval_steps_per_second": 8.214, | |
| "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": 399164974301184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |