| { |
| "best_global_step": 20025, |
| "best_metric": 0.6554931335830212, |
| "best_model_checkpoint": "/content/drive/MyDrive/final/roberta_emotion_model/checkpoint-20025", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 20025, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12484394506866417, |
| "grad_norm": 48.22937774658203, |
| "learning_rate": 9.750811485642947e-06, |
| "loss": 3.1020751953125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.24968789013732834, |
| "grad_norm": 28.517393112182617, |
| "learning_rate": 9.50112359550562e-06, |
| "loss": 2.5971416015625, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.37453183520599254, |
| "grad_norm": 45.27549743652344, |
| "learning_rate": 9.25143570536829e-06, |
| "loss": 2.350372802734375, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.4993757802746567, |
| "grad_norm": 63.087188720703125, |
| "learning_rate": 9.001747815230962e-06, |
| "loss": 2.30302587890625, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.6242197253433208, |
| "grad_norm": 68.39694213867188, |
| "learning_rate": 8.752059925093633e-06, |
| "loss": 2.235894287109375, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.7490636704119851, |
| "grad_norm": 48.36997985839844, |
| "learning_rate": 8.502372034956306e-06, |
| "loss": 2.18744384765625, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.8739076154806492, |
| "grad_norm": 63.88243865966797, |
| "learning_rate": 8.252684144818976e-06, |
| "loss": 2.1574775390625, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.9987515605493134, |
| "grad_norm": 25.953285217285156, |
| "learning_rate": 8.002996254681649e-06, |
| "loss": 2.149793701171875, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5983770287141074, |
| "eval_loss": 1.0222212076187134, |
| "eval_runtime": 31.588, |
| "eval_samples_per_second": 507.154, |
| "eval_steps_per_second": 31.721, |
| "step": 4005 |
| }, |
| { |
| "epoch": 1.1235955056179776, |
| "grad_norm": 65.45611572265625, |
| "learning_rate": 7.753308364544321e-06, |
| "loss": 1.9485059814453125, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.2484394506866416, |
| "grad_norm": 79.43843078613281, |
| "learning_rate": 7.503620474406992e-06, |
| "loss": 1.950569580078125, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.373283395755306, |
| "grad_norm": 38.40707015991211, |
| "learning_rate": 7.253932584269664e-06, |
| "loss": 1.957847900390625, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.4981273408239701, |
| "grad_norm": 29.66714096069336, |
| "learning_rate": 7.004244694132335e-06, |
| "loss": 1.90708447265625, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.6229712858926342, |
| "grad_norm": 28.491024017333984, |
| "learning_rate": 6.754556803995007e-06, |
| "loss": 1.911080078125, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.7478152309612984, |
| "grad_norm": 94.18211364746094, |
| "learning_rate": 6.504868913857678e-06, |
| "loss": 1.8992110595703124, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.8726591760299627, |
| "grad_norm": 28.84901237487793, |
| "learning_rate": 6.25518102372035e-06, |
| "loss": 1.887749755859375, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.9975031210986267, |
| "grad_norm": 51.08824920654297, |
| "learning_rate": 6.005493133583021e-06, |
| "loss": 1.891501220703125, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6292759051186018, |
| "eval_loss": 0.942175567150116, |
| "eval_runtime": 31.7611, |
| "eval_samples_per_second": 504.391, |
| "eval_steps_per_second": 31.548, |
| "step": 8010 |
| }, |
| { |
| "epoch": 2.1223470661672907, |
| "grad_norm": 41.6335563659668, |
| "learning_rate": 5.755805243445693e-06, |
| "loss": 1.7376878662109374, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.247191011235955, |
| "grad_norm": 54.421661376953125, |
| "learning_rate": 5.506117353308364e-06, |
| "loss": 1.723041748046875, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.3720349563046192, |
| "grad_norm": 39.90679168701172, |
| "learning_rate": 5.256429463171036e-06, |
| "loss": 1.71384814453125, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.4968789013732833, |
| "grad_norm": 35.013450622558594, |
| "learning_rate": 5.006741573033709e-06, |
| "loss": 1.6872838134765624, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.6217228464419478, |
| "grad_norm": 26.661258697509766, |
| "learning_rate": 4.7570536828963795e-06, |
| "loss": 1.6985811767578125, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.746566791510612, |
| "grad_norm": 30.96997833251953, |
| "learning_rate": 4.5073657927590515e-06, |
| "loss": 1.66519970703125, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.871410736579276, |
| "grad_norm": 32.575050354003906, |
| "learning_rate": 4.257677902621723e-06, |
| "loss": 1.6637918701171874, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.9962546816479403, |
| "grad_norm": 44.792823791503906, |
| "learning_rate": 4.007990012484395e-06, |
| "loss": 1.6791025390625, |
| "step": 12000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6441323345817728, |
| "eval_loss": 0.9494165182113647, |
| "eval_runtime": 31.7182, |
| "eval_samples_per_second": 505.072, |
| "eval_steps_per_second": 31.591, |
| "step": 12015 |
| }, |
| { |
| "epoch": 3.1210986267166043, |
| "grad_norm": 66.56997680664062, |
| "learning_rate": 3.7583021223470666e-06, |
| "loss": 1.5335745849609375, |
| "step": 12500 |
| }, |
| { |
| "epoch": 3.2459425717852683, |
| "grad_norm": 63.02039337158203, |
| "learning_rate": 3.508614232209738e-06, |
| "loss": 1.51216015625, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.370786516853933, |
| "grad_norm": 60.7429313659668, |
| "learning_rate": 3.2589263420724098e-06, |
| "loss": 1.5589078369140625, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.495630461922597, |
| "grad_norm": 33.59284210205078, |
| "learning_rate": 3.0092384519350813e-06, |
| "loss": 1.554709228515625, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.620474406991261, |
| "grad_norm": 83.69245910644531, |
| "learning_rate": 2.759550561797753e-06, |
| "loss": 1.49451025390625, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.7453183520599254, |
| "grad_norm": 58.14004898071289, |
| "learning_rate": 2.5098626716604245e-06, |
| "loss": 1.511951904296875, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.8701622971285894, |
| "grad_norm": 47.35211944580078, |
| "learning_rate": 2.260174781523096e-06, |
| "loss": 1.5268017578125, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.9950062421972534, |
| "grad_norm": 64.91954040527344, |
| "learning_rate": 2.010486891385768e-06, |
| "loss": 1.512477294921875, |
| "step": 16000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6526841448189763, |
| "eval_loss": 0.9551559090614319, |
| "eval_runtime": 31.4775, |
| "eval_samples_per_second": 508.935, |
| "eval_steps_per_second": 31.832, |
| "step": 16020 |
| }, |
| { |
| "epoch": 4.119850187265918, |
| "grad_norm": 54.49357604980469, |
| "learning_rate": 1.7607990012484397e-06, |
| "loss": 1.39636083984375, |
| "step": 16500 |
| }, |
| { |
| "epoch": 4.2446941323345815, |
| "grad_norm": 91.57239532470703, |
| "learning_rate": 1.5111111111111112e-06, |
| "loss": 1.3841357421875, |
| "step": 17000 |
| }, |
| { |
| "epoch": 4.369538077403246, |
| "grad_norm": 103.39310455322266, |
| "learning_rate": 1.2614232209737828e-06, |
| "loss": 1.3866033935546875, |
| "step": 17500 |
| }, |
| { |
| "epoch": 4.49438202247191, |
| "grad_norm": 68.51345825195312, |
| "learning_rate": 1.0117353308364546e-06, |
| "loss": 1.3865987548828125, |
| "step": 18000 |
| }, |
| { |
| "epoch": 4.619225967540574, |
| "grad_norm": 61.58140563964844, |
| "learning_rate": 7.620474406991262e-07, |
| "loss": 1.413747802734375, |
| "step": 18500 |
| }, |
| { |
| "epoch": 4.7440699126092385, |
| "grad_norm": 24.058151245117188, |
| "learning_rate": 5.123595505617978e-07, |
| "loss": 1.393927978515625, |
| "step": 19000 |
| }, |
| { |
| "epoch": 4.868913857677903, |
| "grad_norm": 39.903724670410156, |
| "learning_rate": 2.6267166042446943e-07, |
| "loss": 1.436919677734375, |
| "step": 19500 |
| }, |
| { |
| "epoch": 4.9937578027465666, |
| "grad_norm": 59.79766845703125, |
| "learning_rate": 1.2983770287141074e-08, |
| "loss": 1.3762628173828124, |
| "step": 20000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6554931335830212, |
| "eval_loss": 0.9726009964942932, |
| "eval_runtime": 31.4744, |
| "eval_samples_per_second": 508.985, |
| "eval_steps_per_second": 31.835, |
| "step": 20025 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 20025, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": 2.107529463578112e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
