| { | |
| "best_metric": 0.02460244856774807, | |
| "best_model_checkpoint": "/kaggle/working/output/checkpoint-73", | |
| "epoch": 26.0, | |
| "eval_steps": 500, | |
| "global_step": 91, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8571428571428571, | |
| "eval_LCC": -0.13996786173466005, | |
| "eval_SROCC": -0.1660984393757503, | |
| "eval_loss": 0.2684723138809204, | |
| "eval_runtime": 39.3373, | |
| "eval_samples_per_second": 1.271, | |
| "eval_steps_per_second": 0.051, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LCC": -0.13191836249511346, | |
| "eval_SROCC": -0.20710684273709484, | |
| "eval_loss": 0.06745556741952896, | |
| "eval_runtime": 37.0134, | |
| "eval_samples_per_second": 1.351, | |
| "eval_steps_per_second": 0.054, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 5.974637508392334, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_LCC": -0.11444761651756143, | |
| "eval_SROCC": -0.19721488595438177, | |
| "eval_loss": 0.13801459968090057, | |
| "eval_runtime": 37.041, | |
| "eval_samples_per_second": 1.35, | |
| "eval_steps_per_second": 0.054, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LCC": -0.11619739343449043, | |
| "eval_SROCC": -0.23620648259303723, | |
| "eval_loss": 0.0638759583234787, | |
| "eval_runtime": 37.3454, | |
| "eval_samples_per_second": 1.339, | |
| "eval_steps_per_second": 0.054, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.857142857142857, | |
| "eval_LCC": -0.1097281268596262, | |
| "eval_SROCC": -0.17599039615846337, | |
| "eval_loss": 0.06009223312139511, | |
| "eval_runtime": 39.2582, | |
| "eval_samples_per_second": 1.274, | |
| "eval_steps_per_second": 0.051, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": 1.5656846761703491, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.0607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LCC": -0.08523254844178266, | |
| "eval_SROCC": -0.12902761104441776, | |
| "eval_loss": 0.06266126781702042, | |
| "eval_runtime": 37.4159, | |
| "eval_samples_per_second": 1.336, | |
| "eval_steps_per_second": 0.053, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.857142857142857, | |
| "eval_LCC": -0.07908973191513438, | |
| "eval_SROCC": -0.10501800720288115, | |
| "eval_loss": 0.054282378405332565, | |
| "eval_runtime": 39.9947, | |
| "eval_samples_per_second": 1.25, | |
| "eval_steps_per_second": 0.05, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCC": -0.07022943984845728, | |
| "eval_SROCC": -0.0683313325330132, | |
| "eval_loss": 0.04083505645394325, | |
| "eval_runtime": 39.4734, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.571428571428571, | |
| "grad_norm": 0.6326273679733276, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.0212, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.857142857142858, | |
| "eval_LCC": -0.05666279490414187, | |
| "eval_SROCC": -0.06919567827130851, | |
| "eval_loss": 0.04194454103708267, | |
| "eval_runtime": 37.518, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.053, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LCC": -0.02743218726796948, | |
| "eval_SROCC": -0.037022809123649456, | |
| "eval_loss": 0.03434378281235695, | |
| "eval_runtime": 37.3074, | |
| "eval_samples_per_second": 1.34, | |
| "eval_steps_per_second": 0.054, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.857142857142858, | |
| "eval_LCC": -0.0012650189550020947, | |
| "eval_SROCC": -0.033949579831932766, | |
| "eval_loss": 0.03074028715491295, | |
| "eval_runtime": 39.2094, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.051, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.428571428571429, | |
| "grad_norm": 0.3264749348163605, | |
| "learning_rate": 1.6296296296296297e-05, | |
| "loss": 0.0168, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LCC": 0.02330881609272888, | |
| "eval_SROCC": -0.02809123649459784, | |
| "eval_loss": 0.029941115528345108, | |
| "eval_runtime": 39.1241, | |
| "eval_samples_per_second": 1.278, | |
| "eval_steps_per_second": 0.051, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.857142857142858, | |
| "eval_LCC": 0.03261216335612809, | |
| "eval_SROCC": -0.042785114045618244, | |
| "eval_loss": 0.03004513680934906, | |
| "eval_runtime": 36.9998, | |
| "eval_samples_per_second": 1.351, | |
| "eval_steps_per_second": 0.054, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_LCC": 0.051745647526359385, | |
| "eval_SROCC": -0.02376950780312125, | |
| "eval_loss": 0.028606927022337914, | |
| "eval_runtime": 36.9029, | |
| "eval_samples_per_second": 1.355, | |
| "eval_steps_per_second": 0.054, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.285714285714286, | |
| "grad_norm": 0.6258419156074524, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0143, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.857142857142858, | |
| "eval_LCC": 0.06012754354341758, | |
| "eval_SROCC": -0.018583433373349337, | |
| "eval_loss": 0.028338493779301643, | |
| "eval_runtime": 39.2004, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.051, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_LCC": 0.08678963760193395, | |
| "eval_SROCC": -0.0024489795918367346, | |
| "eval_loss": 0.027331581339240074, | |
| "eval_runtime": 39.1787, | |
| "eval_samples_per_second": 1.276, | |
| "eval_steps_per_second": 0.051, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.857142857142858, | |
| "eval_LCC": 0.11189936135943072, | |
| "eval_SROCC": 0.028283313325330132, | |
| "eval_loss": 0.02574434131383896, | |
| "eval_runtime": 37.6775, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.053, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.142857142857142, | |
| "grad_norm": 0.2967870831489563, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.013, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_LCC": 0.140408573006196, | |
| "eval_SROCC": 0.05421368547418968, | |
| "eval_loss": 0.024704232811927795, | |
| "eval_runtime": 39.5048, | |
| "eval_samples_per_second": 1.266, | |
| "eval_steps_per_second": 0.051, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.857142857142858, | |
| "eval_LCC": 0.15329553575685126, | |
| "eval_SROCC": 0.07025210084033613, | |
| "eval_loss": 0.0247227493673563, | |
| "eval_runtime": 37.5863, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 0.053, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.35133129358291626, | |
| "learning_rate": 1.1851851851851852e-05, | |
| "loss": 0.0111, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_LCC": 0.16704999475534, | |
| "eval_SROCC": 0.08004801920768306, | |
| "eval_loss": 0.02460792474448681, | |
| "eval_runtime": 39.6008, | |
| "eval_samples_per_second": 1.263, | |
| "eval_steps_per_second": 0.051, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.857142857142858, | |
| "eval_LCC": 0.17734737426317984, | |
| "eval_SROCC": 0.08955582232893158, | |
| "eval_loss": 0.02460244856774807, | |
| "eval_runtime": 39.3838, | |
| "eval_samples_per_second": 1.27, | |
| "eval_steps_per_second": 0.051, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_LCC": 0.183477067706457, | |
| "eval_SROCC": 0.09983193277310923, | |
| "eval_loss": 0.025651078671216965, | |
| "eval_runtime": 37.2011, | |
| "eval_samples_per_second": 1.344, | |
| "eval_steps_per_second": 0.054, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "grad_norm": 0.3938016891479492, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.0104, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_LCC": 0.1943336496302965, | |
| "eval_SROCC": 0.10165666266506602, | |
| "eval_loss": 0.02549559995532036, | |
| "eval_runtime": 39.3404, | |
| "eval_samples_per_second": 1.271, | |
| "eval_steps_per_second": 0.051, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_LCC": 0.20850983626278138, | |
| "eval_SROCC": 0.11490996398559422, | |
| "eval_loss": 0.02545199543237686, | |
| "eval_runtime": 39.5182, | |
| "eval_samples_per_second": 1.265, | |
| "eval_steps_per_second": 0.051, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.857142857142858, | |
| "eval_LCC": 0.21549093905447098, | |
| "eval_SROCC": 0.12451380552220888, | |
| "eval_loss": 0.025542089715600014, | |
| "eval_runtime": 37.4091, | |
| "eval_samples_per_second": 1.337, | |
| "eval_steps_per_second": 0.053, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.714285714285715, | |
| "grad_norm": 0.5060675740242004, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0088, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_LCC": 0.22575900814493188, | |
| "eval_SROCC": 0.13190876350540215, | |
| "eval_loss": 0.026240630075335503, | |
| "eval_runtime": 38.9035, | |
| "eval_samples_per_second": 1.285, | |
| "eval_steps_per_second": 0.051, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "step": 91, | |
| "total_flos": 2.2813585220126638e+18, | |
| "train_loss": 0.041763259517540646, | |
| "train_runtime": 5114.8643, | |
| "train_samples_per_second": 2.092, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "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": 2.2813585220126638e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |