| { | |
| "best_metric": 0.48906123638153076, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010608953957139827, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000424358158285593, | |
| "grad_norm": 0.7389106154441833, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7689, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000424358158285593, | |
| "eval_loss": 0.8173423409461975, | |
| "eval_runtime": 184.5673, | |
| "eval_samples_per_second": 5.38, | |
| "eval_steps_per_second": 2.693, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000848716316571186, | |
| "grad_norm": 1.1682950258255005, | |
| "learning_rate": 4e-05, | |
| "loss": 0.849, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001273074474856779, | |
| "grad_norm": 0.8521813750267029, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001697432633142372, | |
| "grad_norm": 0.6821925044059753, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021217907914279654, | |
| "grad_norm": 0.698543906211853, | |
| "learning_rate": 0.0001, | |
| "loss": 0.673, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021217907914279654, | |
| "eval_loss": 0.7805271744728088, | |
| "eval_runtime": 181.8847, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 2.733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002546148949713558, | |
| "grad_norm": 0.7639641761779785, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002970507107999151, | |
| "grad_norm": 0.8664016127586365, | |
| "learning_rate": 0.00014, | |
| "loss": 0.787, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003394865266284744, | |
| "grad_norm": 0.8074246644973755, | |
| "learning_rate": 0.00016, | |
| "loss": 0.7071, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0038192234245703373, | |
| "grad_norm": 0.9447957873344421, | |
| "learning_rate": 0.00018, | |
| "loss": 0.659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004243581582855931, | |
| "grad_norm": 0.9978194832801819, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5989, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004243581582855931, | |
| "eval_loss": 0.6148068308830261, | |
| "eval_runtime": 181.9226, | |
| "eval_samples_per_second": 5.458, | |
| "eval_steps_per_second": 2.732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0046679397411415234, | |
| "grad_norm": 0.9498071670532227, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.5765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005092297899427116, | |
| "grad_norm": 1.1527200937271118, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.4933, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00551665605771271, | |
| "grad_norm": 1.1410077810287476, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.4746, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005941014215998302, | |
| "grad_norm": 1.3380974531173706, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.5881, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006365372374283896, | |
| "grad_norm": 0.948268711566925, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.4787, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006365372374283896, | |
| "eval_loss": 0.5229542255401611, | |
| "eval_runtime": 183.1912, | |
| "eval_samples_per_second": 5.421, | |
| "eval_steps_per_second": 2.713, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006789730532569488, | |
| "grad_norm": 1.055385708808899, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6458, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007214088690855082, | |
| "grad_norm": 0.8721186518669128, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.487, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0076384468491406746, | |
| "grad_norm": 0.9416680335998535, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.501, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008062805007426267, | |
| "grad_norm": 0.9576472043991089, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5011, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008487163165711862, | |
| "grad_norm": 0.7585878372192383, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.475, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008487163165711862, | |
| "eval_loss": 0.49634602665901184, | |
| "eval_runtime": 182.8238, | |
| "eval_samples_per_second": 5.431, | |
| "eval_steps_per_second": 2.718, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008911521323997454, | |
| "grad_norm": 0.7227087616920471, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.4094, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009335879482283047, | |
| "grad_norm": 0.7042548656463623, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.4363, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00976023764056864, | |
| "grad_norm": 1.0040162801742554, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.4639, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010184595798854232, | |
| "grad_norm": 0.7967023253440857, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.4846, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010608953957139827, | |
| "grad_norm": 0.7558794021606445, | |
| "learning_rate": 0.0, | |
| "loss": 0.4604, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010608953957139827, | |
| "eval_loss": 0.48906123638153076, | |
| "eval_runtime": 185.4008, | |
| "eval_samples_per_second": 5.356, | |
| "eval_steps_per_second": 2.681, | |
| "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": 8461756435267584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |