| { | |
| "best_metric": 1.625058650970459, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.36764705882352944, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007352941176470588, | |
| "grad_norm": 68.04560852050781, | |
| "learning_rate": 5e-05, | |
| "loss": 110.8167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007352941176470588, | |
| "eval_loss": 7.1022138595581055, | |
| "eval_runtime": 2.6752, | |
| "eval_samples_per_second": 18.69, | |
| "eval_steps_per_second": 4.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014705882352941176, | |
| "grad_norm": 72.87908935546875, | |
| "learning_rate": 0.0001, | |
| "loss": 111.3563, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022058823529411766, | |
| "grad_norm": 64.92244720458984, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 109.7718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 80.29588317871094, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 99.6103, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03676470588235294, | |
| "grad_norm": 91.82904815673828, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 85.5878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04411764705882353, | |
| "grad_norm": 81.72701263427734, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 70.2781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051470588235294115, | |
| "grad_norm": 73.6423110961914, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 57.406, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 48.64445877075195, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 47.288, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0661764705882353, | |
| "grad_norm": 62.105186462402344, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 42.692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07352941176470588, | |
| "grad_norm": 62.77745056152344, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 39.1708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08088235294117647, | |
| "grad_norm": 34.73370361328125, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 35.9179, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 26.751127243041992, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 33.7748, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09558823529411764, | |
| "grad_norm": 28.686838150024414, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 31.8575, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10294117647058823, | |
| "grad_norm": 26.484050750732422, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 30.2484, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11029411764705882, | |
| "grad_norm": 17.590030670166016, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 29.2093, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 19.10483169555664, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 28.9873, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 20.43701171875, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 28.8653, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1323529411764706, | |
| "grad_norm": 14.138636589050293, | |
| "learning_rate": 7.75e-05, | |
| "loss": 28.1145, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13970588235294118, | |
| "grad_norm": 12.583146095275879, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 27.6716, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 11.084190368652344, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 28.0258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15441176470588236, | |
| "grad_norm": 86.46572875976562, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 28.0385, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16176470588235295, | |
| "grad_norm": 16.985321044921875, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 27.5637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16911764705882354, | |
| "grad_norm": 13.576494216918945, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 27.9078, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 14.166600227355957, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 27.7601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18382352941176472, | |
| "grad_norm": 42.71133804321289, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 27.5181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18382352941176472, | |
| "eval_loss": 1.7822033166885376, | |
| "eval_runtime": 2.7597, | |
| "eval_samples_per_second": 18.118, | |
| "eval_steps_per_second": 4.711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19117647058823528, | |
| "grad_norm": 25.85879135131836, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 28.0197, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.19852941176470587, | |
| "grad_norm": 17.14788055419922, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 27.5581, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20588235294117646, | |
| "grad_norm": 16.674339294433594, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 27.1966, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21323529411764705, | |
| "grad_norm": 12.14965534210205, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 27.3105, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22058823529411764, | |
| "grad_norm": 12.210734367370605, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 27.1443, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22794117647058823, | |
| "grad_norm": 11.805206298828125, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 26.9579, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 10.710463523864746, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 26.6279, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2426470588235294, | |
| "grad_norm": 12.47972583770752, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 26.9588, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 11.489084243774414, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 27.0147, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.25735294117647056, | |
| "grad_norm": 11.802462577819824, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 26.6679, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2647058823529412, | |
| "grad_norm": 14.10996150970459, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 26.6119, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27205882352941174, | |
| "grad_norm": 14.070399284362793, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 27.1049, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.27941176470588236, | |
| "grad_norm": 14.837409019470215, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 25.6963, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2867647058823529, | |
| "grad_norm": 15.15300464630127, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 25.0391, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 13.794343948364258, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 25.2274, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3014705882352941, | |
| "grad_norm": 11.98012924194336, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 25.0828, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3088235294117647, | |
| "grad_norm": 14.02513313293457, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 24.8935, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3161764705882353, | |
| "grad_norm": 12.323277473449707, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 25.7782, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3235294117647059, | |
| "grad_norm": 13.56668472290039, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 25.2721, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.33088235294117646, | |
| "grad_norm": 14.325328826904297, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 25.1985, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3382352941176471, | |
| "grad_norm": 17.331531524658203, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 25.0337, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.34558823529411764, | |
| "grad_norm": 14.459659576416016, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 25.9566, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 13.978584289550781, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 25.5556, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3602941176470588, | |
| "grad_norm": 15.276152610778809, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 26.2963, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.36764705882352944, | |
| "grad_norm": 16.24267578125, | |
| "learning_rate": 1e-05, | |
| "loss": 26.876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36764705882352944, | |
| "eval_loss": 1.625058650970459, | |
| "eval_runtime": 2.7746, | |
| "eval_samples_per_second": 18.02, | |
| "eval_steps_per_second": 4.685, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |