| { | |
| "best_metric": 0.6890727877616882, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.34587116299178555, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006917423259835711, | |
| "grad_norm": 790.2554321289062, | |
| "learning_rate": 5e-05, | |
| "loss": 134.0684, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006917423259835711, | |
| "eval_loss": 8.13693618774414, | |
| "eval_runtime": 4.67, | |
| "eval_samples_per_second": 10.707, | |
| "eval_steps_per_second": 2.784, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013834846519671422, | |
| "grad_norm": 746.5008544921875, | |
| "learning_rate": 0.0001, | |
| "loss": 132.2386, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020752269779507133, | |
| "grad_norm": 526.3362426757812, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 91.3663, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027669693039342844, | |
| "grad_norm": 530.220703125, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 39.3475, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03458711629917856, | |
| "grad_norm": 166.1348114013672, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 16.5734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.041504539559014265, | |
| "grad_norm": 172.0724334716797, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 14.6946, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04842196281884998, | |
| "grad_norm": 139.84767150878906, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 12.4791, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05533938607868569, | |
| "grad_norm": 54.628971099853516, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.4158, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 84.83878326416016, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.5588, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06917423259835712, | |
| "grad_norm": 54.20598220825195, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.2957, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07609165585819282, | |
| "grad_norm": 142.3564453125, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 12.3199, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08300907911802853, | |
| "grad_norm": 24.020206451416016, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.0949, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08992650237786425, | |
| "grad_norm": 24.632556915283203, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.9799, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09684392563769996, | |
| "grad_norm": 65.8178482055664, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.6228, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10376134889753567, | |
| "grad_norm": 38.240047454833984, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.3225, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11067877215737137, | |
| "grad_norm": 17.695785522460938, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.995, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11759619541720709, | |
| "grad_norm": 14.087479591369629, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.9745, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 60.94573974609375, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.3823, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13143104193687852, | |
| "grad_norm": 51.727134704589844, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.4921, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13834846519671423, | |
| "grad_norm": 45.008323669433594, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.578, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14526588845654995, | |
| "grad_norm": 31.297468185424805, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.1494, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15218331171638563, | |
| "grad_norm": 39.989479064941406, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.2147, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15910073497622135, | |
| "grad_norm": 27.28616714477539, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.2717, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16601815823605706, | |
| "grad_norm": 34.64227294921875, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.2599, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17293558149589278, | |
| "grad_norm": 14.136774063110352, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.0432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17293558149589278, | |
| "eval_loss": 0.6890727877616882, | |
| "eval_runtime": 4.7098, | |
| "eval_samples_per_second": 10.616, | |
| "eval_steps_per_second": 2.76, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1798530047557285, | |
| "grad_norm": 31.32541275024414, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.9615, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 11.566988945007324, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.8916, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19368785127539992, | |
| "grad_norm": 26.623291015625, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.2515, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20060527453523563, | |
| "grad_norm": 12.670833587646484, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.0147, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20752269779507135, | |
| "grad_norm": 18.8542423248291, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.2094, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21444012105490703, | |
| "grad_norm": 22.972414016723633, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.0838, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22135754431474275, | |
| "grad_norm": 18.56379508972168, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.187, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22827496757457846, | |
| "grad_norm": 20.60142707824707, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.1898, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23519239083441418, | |
| "grad_norm": 27.812822341918945, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.2153, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2421098140942499, | |
| "grad_norm": 9.875837326049805, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.1487, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": 13.512711524963379, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.0882, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2559446606139213, | |
| "grad_norm": 11.75142765045166, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.0221, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.26286208387375704, | |
| "grad_norm": 11.987626075744629, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.0416, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2697795071335927, | |
| "grad_norm": 10.277228355407715, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.1801, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27669693039342846, | |
| "grad_norm": 11.25522518157959, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.1051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28361435365326415, | |
| "grad_norm": 12.054732322692871, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.0765, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2905317769130999, | |
| "grad_norm": 7.122025489807129, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.0064, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2974492001729356, | |
| "grad_norm": 16.80191993713379, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.9657, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.30436662343277127, | |
| "grad_norm": 10.954202651977539, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.0736, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.311284046692607, | |
| "grad_norm": 7.031284332275391, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.9168, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3182014699524427, | |
| "grad_norm": 13.944522857666016, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.2041, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32511889321227844, | |
| "grad_norm": 8.850104331970215, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.1053, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3320363164721141, | |
| "grad_norm": 19.365779876708984, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.1555, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.33895373973194987, | |
| "grad_norm": 9.599617004394531, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.9737, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.34587116299178555, | |
| "grad_norm": 8.487637519836426, | |
| "learning_rate": 1e-05, | |
| "loss": 10.9277, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34587116299178555, | |
| "eval_loss": 0.693572998046875, | |
| "eval_runtime": 4.7237, | |
| "eval_samples_per_second": 10.585, | |
| "eval_steps_per_second": 2.752, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |