| { | |
| "best_metric": 0.1271306425333023, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 2.704318936877076, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 16.144733428955078, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "eval_loss": 4.792490005493164, | |
| "eval_runtime": 1.2864, | |
| "eval_samples_per_second": 38.869, | |
| "eval_steps_per_second": 10.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 15.608192443847656, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6739, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 14.042940139770508, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.3826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 16.18175506591797, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.236, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 9.477006912231445, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.051, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31893687707641194, | |
| "grad_norm": 6.747547149658203, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0292, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 3.7970376014709473, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6351, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42524916943521596, | |
| "grad_norm": 3.995140314102173, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.5011, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47840531561461797, | |
| "grad_norm": 3.99289608001709, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 2.5063412189483643, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.2656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.584717607973422, | |
| "grad_norm": 1.6351100206375122, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.235, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6378737541528239, | |
| "grad_norm": 1.896690845489502, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1664, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6910299003322259, | |
| "grad_norm": 1.7002002000808716, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1649, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 3.440533399581909, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2211, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7973421926910299, | |
| "grad_norm": 2.0268311500549316, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8504983388704319, | |
| "grad_norm": 2.489518404006958, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1835, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9036544850498339, | |
| "grad_norm": 2.5720105171203613, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9568106312292359, | |
| "grad_norm": 2.0609378814697266, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1873, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0332225913621262, | |
| "grad_norm": 5.151944637298584, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3486, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0863787375415281, | |
| "grad_norm": 1.6826090812683105, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1395348837209303, | |
| "grad_norm": 1.0322390794754028, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0483, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1926910299003322, | |
| "grad_norm": 0.5722368955612183, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0898, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2458471760797343, | |
| "grad_norm": 1.1440904140472412, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1622, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2990033222591362, | |
| "grad_norm": 0.8407073616981506, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0988, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.352159468438538, | |
| "grad_norm": 1.039757251739502, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1143, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.352159468438538, | |
| "eval_loss": 0.1271306425333023, | |
| "eval_runtime": 0.7183, | |
| "eval_samples_per_second": 69.606, | |
| "eval_steps_per_second": 18.098, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4053156146179402, | |
| "grad_norm": 0.520526647567749, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0646, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4584717607973423, | |
| "grad_norm": 1.3327345848083496, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0993, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "grad_norm": 1.7566813230514526, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0945, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.564784053156146, | |
| "grad_norm": 4.805406093597412, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0618, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6179401993355482, | |
| "grad_norm": 0.9493386149406433, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.135, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6710963455149501, | |
| "grad_norm": 0.8112987279891968, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0761, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7242524916943522, | |
| "grad_norm": 1.9758391380310059, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1024, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7774086378737541, | |
| "grad_norm": 0.5663211941719055, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0501, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.830564784053156, | |
| "grad_norm": 0.7831739783287048, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.092, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8837209302325582, | |
| "grad_norm": 1.0481925010681152, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1153, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9368770764119603, | |
| "grad_norm": 0.7795256972312927, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1191, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0132890365448506, | |
| "grad_norm": 0.9911825060844421, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1322, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.0664451827242525, | |
| "grad_norm": 0.6058715581893921, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0589, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.1196013289036544, | |
| "grad_norm": 0.5736090540885925, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0648, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1727574750830563, | |
| "grad_norm": 0.7126216888427734, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0467, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2259136212624586, | |
| "grad_norm": 0.5185224413871765, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0806, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2790697674418605, | |
| "grad_norm": 0.7146442532539368, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1057, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.3322259136212624, | |
| "grad_norm": 0.48135268688201904, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0501, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.3853820598006643, | |
| "grad_norm": 0.6691005825996399, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0646, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.438538205980066, | |
| "grad_norm": 0.4291771948337555, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0691, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.4916943521594686, | |
| "grad_norm": 0.6109609007835388, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0705, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.5448504983388704, | |
| "grad_norm": 0.7353491187095642, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0619, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.5980066445182723, | |
| "grad_norm": 0.4926731586456299, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0537, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6511627906976747, | |
| "grad_norm": 0.6144967079162598, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0533, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.704318936877076, | |
| "grad_norm": 0.7941309213638306, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.704318936877076, | |
| "eval_loss": 0.14437605440616608, | |
| "eval_runtime": 0.739, | |
| "eval_samples_per_second": 67.658, | |
| "eval_steps_per_second": 17.591, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.54445405339648e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |