| { | |
| "best_metric": 0.03524893894791603, | |
| "best_model_checkpoint": "/kaggle/working/output/checkpoint-84", | |
| "epoch": 29.925925925925927, | |
| "eval_steps": 500, | |
| "global_step": 101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_LCC": -0.11469366908669681, | |
| "eval_SROCC": -0.15860744297719087, | |
| "eval_loss": 0.4400586783885956, | |
| "eval_runtime": 42.4739, | |
| "eval_samples_per_second": 1.177, | |
| "eval_steps_per_second": 0.047, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "eval_LCC": -0.1545349416495121, | |
| "eval_SROCC": -0.2675150060024009, | |
| "eval_loss": 0.22064876556396484, | |
| "eval_runtime": 42.0384, | |
| "eval_samples_per_second": 1.189, | |
| "eval_steps_per_second": 0.048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 16.114206314086914, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.3084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "eval_LCC": -0.1813303002138391, | |
| "eval_SROCC": -0.27539015606242495, | |
| "eval_loss": 0.1909903734922409, | |
| "eval_runtime": 42.3941, | |
| "eval_samples_per_second": 1.179, | |
| "eval_steps_per_second": 0.047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.851851851851852, | |
| "eval_LCC": -0.1510725671786146, | |
| "eval_SROCC": -0.2169987995198079, | |
| "eval_loss": 0.23344503343105316, | |
| "eval_runtime": 42.0983, | |
| "eval_samples_per_second": 1.188, | |
| "eval_steps_per_second": 0.048, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_LCC": -0.1309558195202113, | |
| "eval_SROCC": -0.2, | |
| "eval_loss": 0.14843837916851044, | |
| "eval_runtime": 42.2346, | |
| "eval_samples_per_second": 1.184, | |
| "eval_steps_per_second": 0.047, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 12.447588920593262, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.0852, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "eval_LCC": -0.08517980393535173, | |
| "eval_SROCC": -0.10213685474189677, | |
| "eval_loss": 0.12589265406131744, | |
| "eval_runtime": 42.2026, | |
| "eval_samples_per_second": 1.185, | |
| "eval_steps_per_second": 0.047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.814814814814815, | |
| "eval_LCC": -0.05947795499623739, | |
| "eval_SROCC": -0.07092436974789915, | |
| "eval_loss": 0.15516823530197144, | |
| "eval_runtime": 42.1659, | |
| "eval_samples_per_second": 1.186, | |
| "eval_steps_per_second": 0.047, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCC": -0.0584113029101595, | |
| "eval_SROCC": -0.09483793517406962, | |
| "eval_loss": 0.09420724213123322, | |
| "eval_runtime": 42.5672, | |
| "eval_samples_per_second": 1.175, | |
| "eval_steps_per_second": 0.047, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 6.68361759185791, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.0406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "eval_LCC": -0.05502642204622495, | |
| "eval_SROCC": -0.04797118847539015, | |
| "eval_loss": 0.08413399010896683, | |
| "eval_runtime": 42.0478, | |
| "eval_samples_per_second": 1.189, | |
| "eval_steps_per_second": 0.048, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.777777777777779, | |
| "eval_LCC": -0.044815400478992636, | |
| "eval_SROCC": -0.0575750300120048, | |
| "eval_loss": 0.08856825530529022, | |
| "eval_runtime": 42.1399, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 10.962962962962964, | |
| "eval_LCC": -0.04737793047406845, | |
| "eval_SROCC": -0.07726290516206481, | |
| "eval_loss": 0.07205035537481308, | |
| "eval_runtime": 42.2456, | |
| "eval_samples_per_second": 1.184, | |
| "eval_steps_per_second": 0.047, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 11.851851851851851, | |
| "grad_norm": 1.6507503986358643, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.851851851851851, | |
| "eval_LCC": -0.03637477859676811, | |
| "eval_SROCC": -0.04460984393757503, | |
| "eval_loss": 0.06969437748193741, | |
| "eval_runtime": 42.0276, | |
| "eval_samples_per_second": 1.19, | |
| "eval_steps_per_second": 0.048, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.74074074074074, | |
| "eval_LCC": -0.00905185691215031, | |
| "eval_SROCC": -0.021656662665066023, | |
| "eval_loss": 0.05769188702106476, | |
| "eval_runtime": 42.1379, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 13.925925925925926, | |
| "eval_LCC": 0.011204733733650302, | |
| "eval_SROCC": -0.03135654261704682, | |
| "eval_loss": 0.06662916392087936, | |
| "eval_runtime": 41.9846, | |
| "eval_samples_per_second": 1.191, | |
| "eval_steps_per_second": 0.048, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 0.8441389799118042, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.0136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "eval_LCC": 0.006038695767176178, | |
| "eval_SROCC": -0.05008403361344538, | |
| "eval_loss": 0.052547648549079895, | |
| "eval_runtime": 42.0346, | |
| "eval_samples_per_second": 1.189, | |
| "eval_steps_per_second": 0.048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LCC": 0.05035447924360885, | |
| "eval_SROCC": -0.01781512605042017, | |
| "eval_loss": 0.06257949769496918, | |
| "eval_runtime": 42.0741, | |
| "eval_samples_per_second": 1.188, | |
| "eval_steps_per_second": 0.048, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 16.88888888888889, | |
| "eval_LCC": 0.08269606829608296, | |
| "eval_SROCC": 0.015894357743097238, | |
| "eval_loss": 0.043766554445028305, | |
| "eval_runtime": 42.063, | |
| "eval_samples_per_second": 1.189, | |
| "eval_steps_per_second": 0.048, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 1.5869125127792358, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.0113, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "eval_LCC": 0.10735678232307705, | |
| "eval_SROCC": 0.074093637454982, | |
| "eval_loss": 0.05027168616652489, | |
| "eval_runtime": 42.0969, | |
| "eval_samples_per_second": 1.188, | |
| "eval_steps_per_second": 0.048, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.962962962962962, | |
| "eval_LCC": 0.11292358158916863, | |
| "eval_SROCC": 0.08177671068427371, | |
| "eval_loss": 0.04287625476717949, | |
| "eval_runtime": 42.1066, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 19.85185185185185, | |
| "eval_LCC": 0.11877825314298533, | |
| "eval_SROCC": 0.08744297719087635, | |
| "eval_loss": 0.04554678872227669, | |
| "eval_runtime": 42.3014, | |
| "eval_samples_per_second": 1.182, | |
| "eval_steps_per_second": 0.047, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 20.74074074074074, | |
| "grad_norm": 2.4397213459014893, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.0097, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.74074074074074, | |
| "eval_LCC": 0.1315746635210365, | |
| "eval_SROCC": 0.09262905162064825, | |
| "eval_loss": 0.05967041850090027, | |
| "eval_runtime": 42.314, | |
| "eval_samples_per_second": 1.182, | |
| "eval_steps_per_second": 0.047, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 21.925925925925927, | |
| "eval_LCC": 0.14461751047124533, | |
| "eval_SROCC": 0.06141656662665066, | |
| "eval_loss": 0.03967233747243881, | |
| "eval_runtime": 41.6175, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.048, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 22.814814814814813, | |
| "eval_LCC": 0.1636524681044405, | |
| "eval_SROCC": 0.07783913565426169, | |
| "eval_loss": 0.052949074655771255, | |
| "eval_runtime": 42.4694, | |
| "eval_samples_per_second": 1.177, | |
| "eval_steps_per_second": 0.047, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 23.703703703703702, | |
| "grad_norm": 1.3437652587890625, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.0084, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LCC": 0.17607777965634505, | |
| "eval_SROCC": 0.07159663865546219, | |
| "eval_loss": 0.03660748153924942, | |
| "eval_runtime": 41.9971, | |
| "eval_samples_per_second": 1.191, | |
| "eval_steps_per_second": 0.048, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 24.88888888888889, | |
| "eval_LCC": 0.18198076982766778, | |
| "eval_SROCC": 0.0683313325330132, | |
| "eval_loss": 0.03524893894791603, | |
| "eval_runtime": 42.1358, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 25.77777777777778, | |
| "eval_LCC": 0.1847607546132782, | |
| "eval_SROCC": 0.09695078031212485, | |
| "eval_loss": 0.04908595234155655, | |
| "eval_runtime": 42.3591, | |
| "eval_samples_per_second": 1.18, | |
| "eval_steps_per_second": 0.047, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 1.1412720680236816, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.0078, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.962962962962962, | |
| "eval_LCC": 0.18306996734895817, | |
| "eval_SROCC": 0.09839135654261706, | |
| "eval_loss": 0.039556559175252914, | |
| "eval_runtime": 42.0202, | |
| "eval_samples_per_second": 1.19, | |
| "eval_steps_per_second": 0.048, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 27.85185185185185, | |
| "eval_LCC": 0.18556425091617126, | |
| "eval_SROCC": 0.1011764705882353, | |
| "eval_loss": 0.039471760392189026, | |
| "eval_runtime": 42.1635, | |
| "eval_samples_per_second": 1.186, | |
| "eval_steps_per_second": 0.047, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.74074074074074, | |
| "eval_LCC": 0.19561082710345667, | |
| "eval_SROCC": 0.10972388955582232, | |
| "eval_loss": 0.04257187247276306, | |
| "eval_runtime": 42.1398, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 29.62962962962963, | |
| "grad_norm": 0.5356392860412598, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.0063, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 29.925925925925927, | |
| "eval_LCC": 0.19841940652904885, | |
| "eval_SROCC": 0.10021608643457382, | |
| "eval_loss": 0.03704619035124779, | |
| "eval_runtime": 42.1404, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.047, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 29.925925925925927, | |
| "step": 101, | |
| "total_flos": 5.9133993779567e+18, | |
| "train_loss": 0.050966506113879165, | |
| "train_runtime": 7148.5533, | |
| "train_samples_per_second": 1.497, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 5.9133993779567e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |