| { | |
| "best_metric": 4.602016925811768, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.002138259884106314, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.553039536425257e-05, | |
| "grad_norm": 6.667639255523682, | |
| "learning_rate": 2e-05, | |
| "loss": 18.4066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.553039536425257e-05, | |
| "eval_loss": 5.1203293800354, | |
| "eval_runtime": 316.6141, | |
| "eval_samples_per_second": 15.549, | |
| "eval_steps_per_second": 7.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017106079072850514, | |
| "grad_norm": 12.6857328414917, | |
| "learning_rate": 4e-05, | |
| "loss": 23.7557, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002565911860927577, | |
| "grad_norm": 8.143623352050781, | |
| "learning_rate": 6e-05, | |
| "loss": 20.2172, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003421215814570103, | |
| "grad_norm": 6.832309246063232, | |
| "learning_rate": 8e-05, | |
| "loss": 20.6539, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042765197682126285, | |
| "grad_norm": 8.713631629943848, | |
| "learning_rate": 0.0001, | |
| "loss": 19.1846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042765197682126285, | |
| "eval_loss": 5.010995864868164, | |
| "eval_runtime": 321.8501, | |
| "eval_samples_per_second": 15.296, | |
| "eval_steps_per_second": 7.65, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005131823721855154, | |
| "grad_norm": 5.7573957443237305, | |
| "learning_rate": 0.00012, | |
| "loss": 19.6999, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000598712767549768, | |
| "grad_norm": 4.511601448059082, | |
| "learning_rate": 0.00014, | |
| "loss": 15.9342, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006842431629140206, | |
| "grad_norm": 4.244760036468506, | |
| "learning_rate": 0.00016, | |
| "loss": 14.2788, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007697735582782732, | |
| "grad_norm": 4.569301605224609, | |
| "learning_rate": 0.00018, | |
| "loss": 17.2963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008553039536425257, | |
| "grad_norm": 5.242503643035889, | |
| "learning_rate": 0.0002, | |
| "loss": 19.8172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008553039536425257, | |
| "eval_loss": 4.822195529937744, | |
| "eval_runtime": 312.8502, | |
| "eval_samples_per_second": 15.736, | |
| "eval_steps_per_second": 7.87, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009408343490067783, | |
| "grad_norm": 6.4473876953125, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 18.1537, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010263647443710308, | |
| "grad_norm": 6.688948154449463, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 19.5688, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011118951397352834, | |
| "grad_norm": 4.838939666748047, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 19.5337, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001197425535099536, | |
| "grad_norm": 5.898268699645996, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 18.0697, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012829559304637886, | |
| "grad_norm": 7.900224685668945, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 18.5075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012829559304637886, | |
| "eval_loss": 4.680049419403076, | |
| "eval_runtime": 312.4004, | |
| "eval_samples_per_second": 15.759, | |
| "eval_steps_per_second": 7.881, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013684863258280411, | |
| "grad_norm": 5.822889804840088, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 17.4591, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014540167211922936, | |
| "grad_norm": 10.43186092376709, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 14.6405, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015395471165565464, | |
| "grad_norm": 6.680084705352783, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 15.9788, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016250775119207989, | |
| "grad_norm": 6.787518501281738, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 18.7588, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017106079072850514, | |
| "grad_norm": 6.086184024810791, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 18.686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017106079072850514, | |
| "eval_loss": 4.618816375732422, | |
| "eval_runtime": 312.441, | |
| "eval_samples_per_second": 15.757, | |
| "eval_steps_per_second": 7.88, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001796138302649304, | |
| "grad_norm": 6.364172458648682, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 18.7242, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018816686980135566, | |
| "grad_norm": 7.940497875213623, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 15.5531, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001967199093377809, | |
| "grad_norm": 5.847348213195801, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 19.1526, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0020527294887420617, | |
| "grad_norm": 7.737930774688721, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 20.7491, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002138259884106314, | |
| "grad_norm": 7.768985271453857, | |
| "learning_rate": 0.0, | |
| "loss": 19.9509, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002138259884106314, | |
| "eval_loss": 4.602016925811768, | |
| "eval_runtime": 311.7646, | |
| "eval_samples_per_second": 15.791, | |
| "eval_steps_per_second": 7.897, | |
| "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": 197057839104000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |