| { | |
| "best_metric": 1.8047796487808228, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.007357674974707992, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036788374873539964, | |
| "grad_norm": 1.0344762802124023, | |
| "learning_rate": 2e-05, | |
| "loss": 9.9677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036788374873539964, | |
| "eval_loss": 2.4520018100738525, | |
| "eval_runtime": 208.954, | |
| "eval_samples_per_second": 5.48, | |
| "eval_steps_per_second": 2.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007357674974707993, | |
| "grad_norm": 0.8975549340248108, | |
| "learning_rate": 4e-05, | |
| "loss": 8.9078, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011036512462061989, | |
| "grad_norm": 0.8267841339111328, | |
| "learning_rate": 6e-05, | |
| "loss": 9.3107, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014715349949415985, | |
| "grad_norm": 1.0469233989715576, | |
| "learning_rate": 8e-05, | |
| "loss": 10.1692, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001839418743676998, | |
| "grad_norm": 1.09218430519104, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001839418743676998, | |
| "eval_loss": 2.440983533859253, | |
| "eval_runtime": 214.9804, | |
| "eval_samples_per_second": 5.326, | |
| "eval_steps_per_second": 2.665, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022073024924123977, | |
| "grad_norm": 1.3672481775283813, | |
| "learning_rate": 0.00012, | |
| "loss": 9.743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002575186241147797, | |
| "grad_norm": 1.3047765493392944, | |
| "learning_rate": 0.00014, | |
| "loss": 9.2113, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002943069989883197, | |
| "grad_norm": 1.8970640897750854, | |
| "learning_rate": 0.00016, | |
| "loss": 9.7024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033109537386185966, | |
| "grad_norm": 2.041234254837036, | |
| "learning_rate": 0.00018, | |
| "loss": 9.1206, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003678837487353996, | |
| "grad_norm": 2.0153932571411133, | |
| "learning_rate": 0.0002, | |
| "loss": 8.654, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003678837487353996, | |
| "eval_loss": 2.2052650451660156, | |
| "eval_runtime": 210.1367, | |
| "eval_samples_per_second": 5.449, | |
| "eval_steps_per_second": 2.727, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004046721236089396, | |
| "grad_norm": 2.4660604000091553, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 8.7234, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004414604984824795, | |
| "grad_norm": 1.8295977115631104, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 8.163, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004782488733560195, | |
| "grad_norm": 1.8968079090118408, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 8.6543, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005150372482295594, | |
| "grad_norm": 1.8276681900024414, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 8.8163, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005518256231030994, | |
| "grad_norm": 2.6726272106170654, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 7.6233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005518256231030994, | |
| "eval_loss": 1.9261927604675293, | |
| "eval_runtime": 209.4933, | |
| "eval_samples_per_second": 5.466, | |
| "eval_steps_per_second": 2.735, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005886139979766394, | |
| "grad_norm": 2.7427423000335693, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.5253, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006254023728501794, | |
| "grad_norm": 3.383516550064087, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 7.64, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006621907477237193, | |
| "grad_norm": 2.6983039379119873, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 7.0817, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006989791225972593, | |
| "grad_norm": 2.4711389541625977, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 6.7801, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007357674974707992, | |
| "grad_norm": 2.46940279006958, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.8213, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007357674974707992, | |
| "eval_loss": 1.8047796487808228, | |
| "eval_runtime": 209.7029, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 2.732, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3257498484080640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |