| { | |
| "best_metric": 0.45772695541381836, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.43010752688172044, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008602150537634409, | |
| "grad_norm": 10.440855979919434, | |
| "learning_rate": 0.0001, | |
| "loss": 6.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008602150537634409, | |
| "eval_loss": 1.7076656818389893, | |
| "eval_runtime": 12.4166, | |
| "eval_samples_per_second": 3.946, | |
| "eval_steps_per_second": 2.013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017204301075268817, | |
| "grad_norm": 7.720833778381348, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 9.9528226852417, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.4864, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034408602150537634, | |
| "grad_norm": 7.00700569152832, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 5.4755, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 5.665371417999268, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.1736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05161290322580645, | |
| "grad_norm": 12.188865661621094, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 5.4912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.060215053763440864, | |
| "grad_norm": 7.096029281616211, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 3.2235, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06881720430107527, | |
| "grad_norm": 9.947226524353027, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.1206, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07741935483870968, | |
| "grad_norm": 10.909231185913086, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.9751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 14.274968147277832, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.7431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09462365591397849, | |
| "grad_norm": 10.314630508422852, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.7954, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": 7.7207489013671875, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.0051, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11182795698924732, | |
| "grad_norm": 6.550817489624023, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 2.0254, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12043010752688173, | |
| "grad_norm": 6.1834330558776855, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 6.17444372177124, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 2.5576, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13763440860215054, | |
| "grad_norm": 7.740011692047119, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.1765, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14623655913978495, | |
| "grad_norm": 8.635690689086914, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.8414, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15483870967741936, | |
| "grad_norm": 8.935779571533203, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.7599, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16344086021505377, | |
| "grad_norm": 7.77616024017334, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 2.2149, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 6.958274841308594, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.3381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18064516129032257, | |
| "grad_norm": 5.459251880645752, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.828, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18924731182795698, | |
| "grad_norm": 7.251789569854736, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 2.3322, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1978494623655914, | |
| "grad_norm": 6.924062728881836, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.6064, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 10.513365745544434, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.0946, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 6.92408561706543, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.0292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "eval_loss": 0.5663574934005737, | |
| "eval_runtime": 12.6339, | |
| "eval_samples_per_second": 3.878, | |
| "eval_steps_per_second": 1.979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22365591397849463, | |
| "grad_norm": 10.534406661987305, | |
| "learning_rate": 0.0001, | |
| "loss": 3.744, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23225806451612904, | |
| "grad_norm": 6.486779689788818, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.9199, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24086021505376345, | |
| "grad_norm": 9.214913368225098, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.5619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24946236559139784, | |
| "grad_norm": 10.509803771972656, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 2.3158, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 9.7291841506958, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.2134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 11.299739837646484, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 3.0947, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2752688172043011, | |
| "grad_norm": 8.215875625610352, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.1678, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2838709677419355, | |
| "grad_norm": 4.7149434089660645, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.4623, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2924731182795699, | |
| "grad_norm": 5.680448532104492, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5995, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3010752688172043, | |
| "grad_norm": 8.507613182067871, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.7745, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": 4.99240779876709, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.0125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31827956989247314, | |
| "grad_norm": 5.999588489532471, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.3784, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.32688172043010755, | |
| "grad_norm": 5.480283260345459, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 2.107, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.33548387096774196, | |
| "grad_norm": 3.4129068851470947, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.8842, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 4.122173309326172, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.2184, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35268817204301073, | |
| "grad_norm": 4.307172775268555, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.2531, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.36129032258064514, | |
| "grad_norm": 3.4182629585266113, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.0525, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.36989247311827955, | |
| "grad_norm": 6.133404731750488, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.8617, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37849462365591396, | |
| "grad_norm": 4.430727958679199, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.5402, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 6.002130031585693, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.6745, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3956989247311828, | |
| "grad_norm": 5.143777370452881, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.7129, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4043010752688172, | |
| "grad_norm": 5.8984551429748535, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.8639, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 6.393105506896973, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.57, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.421505376344086, | |
| "grad_norm": 5.643848896026611, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 1.3948, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 4.860955715179443, | |
| "learning_rate": 0.0, | |
| "loss": 1.7264, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "eval_loss": 0.45772695541381836, | |
| "eval_runtime": 12.6513, | |
| "eval_samples_per_second": 3.873, | |
| "eval_steps_per_second": 1.976, | |
| "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": 6.53458201903104e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |