| { | |
| "best_metric": 2.009561777114868, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e2l57-l/checkpoint-9500", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 10856, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09211495946941783, | |
| "grad_norm": 0.00766215892508626, | |
| "learning_rate": 4.769712601326456e-05, | |
| "loss": 0.7207, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09211495946941783, | |
| "eval_loss": 2.078455924987793, | |
| "eval_runtime": 73.0449, | |
| "eval_samples_per_second": 16.524, | |
| "eval_steps_per_second": 2.067, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "grad_norm": 0.016227997839450836, | |
| "learning_rate": 4.539425202652911e-05, | |
| "loss": 0.702, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "eval_loss": 2.0786073207855225, | |
| "eval_runtime": 73.7466, | |
| "eval_samples_per_second": 16.367, | |
| "eval_steps_per_second": 2.048, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "grad_norm": 3.326040029525757, | |
| "learning_rate": 4.309137803979367e-05, | |
| "loss": 0.7058, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "eval_loss": 2.0656001567840576, | |
| "eval_runtime": 75.4832, | |
| "eval_samples_per_second": 15.99, | |
| "eval_steps_per_second": 2.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "grad_norm": 5.95470666885376, | |
| "learning_rate": 4.078850405305822e-05, | |
| "loss": 0.7117, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "eval_loss": 2.113447427749634, | |
| "eval_runtime": 75.7404, | |
| "eval_samples_per_second": 15.936, | |
| "eval_steps_per_second": 1.994, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "grad_norm": 1.3789223432540894, | |
| "learning_rate": 3.848563006632277e-05, | |
| "loss": 0.7163, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "eval_loss": 2.0306718349456787, | |
| "eval_runtime": 75.7822, | |
| "eval_samples_per_second": 15.927, | |
| "eval_steps_per_second": 1.993, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "grad_norm": 17.15974998474121, | |
| "learning_rate": 3.6182756079587326e-05, | |
| "loss": 0.6794, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "eval_loss": 2.613356590270996, | |
| "eval_runtime": 75.7313, | |
| "eval_samples_per_second": 15.938, | |
| "eval_steps_per_second": 1.994, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "grad_norm": 6.376380443572998, | |
| "learning_rate": 3.3879882092851885e-05, | |
| "loss": 0.6818, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "eval_loss": 2.0862319469451904, | |
| "eval_runtime": 75.9967, | |
| "eval_samples_per_second": 15.882, | |
| "eval_steps_per_second": 1.987, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7369196757553427, | |
| "grad_norm": 4.5618391036987305, | |
| "learning_rate": 3.157700810611644e-05, | |
| "loss": 0.6693, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7369196757553427, | |
| "eval_loss": 2.0294671058654785, | |
| "eval_runtime": 74.4695, | |
| "eval_samples_per_second": 16.208, | |
| "eval_steps_per_second": 2.028, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8290346352247605, | |
| "grad_norm": 4.356328964233398, | |
| "learning_rate": 2.927413411938099e-05, | |
| "loss": 0.6798, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8290346352247605, | |
| "eval_loss": 2.1398818492889404, | |
| "eval_runtime": 76.5616, | |
| "eval_samples_per_second": 15.765, | |
| "eval_steps_per_second": 1.972, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9211495946941783, | |
| "grad_norm": 1.5961418151855469, | |
| "learning_rate": 2.6971260132645544e-05, | |
| "loss": 0.6915, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9211495946941783, | |
| "eval_loss": 2.0116002559661865, | |
| "eval_runtime": 75.2588, | |
| "eval_samples_per_second": 16.038, | |
| "eval_steps_per_second": 2.006, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.013264554163596, | |
| "grad_norm": 0.672991931438446, | |
| "learning_rate": 2.4668386145910096e-05, | |
| "loss": 0.6623, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.013264554163596, | |
| "eval_loss": 2.1612467765808105, | |
| "eval_runtime": 75.2829, | |
| "eval_samples_per_second": 16.033, | |
| "eval_steps_per_second": 2.006, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.105379513633014, | |
| "grad_norm": 5.576838493347168, | |
| "learning_rate": 2.2365512159174652e-05, | |
| "loss": 0.6803, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.105379513633014, | |
| "eval_loss": 2.0493156909942627, | |
| "eval_runtime": 74.734, | |
| "eval_samples_per_second": 16.151, | |
| "eval_steps_per_second": 2.02, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.1974944731024317, | |
| "grad_norm": 1.1342592239379883, | |
| "learning_rate": 2.0062638172439205e-05, | |
| "loss": 0.6729, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.1974944731024317, | |
| "eval_loss": 2.051811933517456, | |
| "eval_runtime": 74.1516, | |
| "eval_samples_per_second": 16.277, | |
| "eval_steps_per_second": 2.036, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.2896094325718497, | |
| "grad_norm": 2.215428113937378, | |
| "learning_rate": 1.7759764185703758e-05, | |
| "loss": 0.6851, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.2896094325718497, | |
| "eval_loss": 2.039102077484131, | |
| "eval_runtime": 74.3318, | |
| "eval_samples_per_second": 16.238, | |
| "eval_steps_per_second": 2.031, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.3817243920412676, | |
| "grad_norm": 4.479649066925049, | |
| "learning_rate": 1.5456890198968314e-05, | |
| "loss": 0.6686, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.3817243920412676, | |
| "eval_loss": 2.06972074508667, | |
| "eval_runtime": 74.3941, | |
| "eval_samples_per_second": 16.224, | |
| "eval_steps_per_second": 2.03, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.4738393515106853, | |
| "grad_norm": 9.912164688110352, | |
| "learning_rate": 1.3154016212232867e-05, | |
| "loss": 0.6637, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.4738393515106853, | |
| "eval_loss": 2.045731782913208, | |
| "eval_runtime": 74.4167, | |
| "eval_samples_per_second": 16.219, | |
| "eval_steps_per_second": 2.029, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.565954310980103, | |
| "grad_norm": 7.797455310821533, | |
| "learning_rate": 1.0851142225497421e-05, | |
| "loss": 0.6331, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.565954310980103, | |
| "eval_loss": 2.1388187408447266, | |
| "eval_runtime": 74.2931, | |
| "eval_samples_per_second": 16.246, | |
| "eval_steps_per_second": 2.032, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.658069270449521, | |
| "grad_norm": 14.766168594360352, | |
| "learning_rate": 8.548268238761976e-06, | |
| "loss": 0.6529, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.658069270449521, | |
| "eval_loss": 2.0181920528411865, | |
| "eval_runtime": 74.6522, | |
| "eval_samples_per_second": 16.168, | |
| "eval_steps_per_second": 2.023, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.750184229918939, | |
| "grad_norm": 10.570740699768066, | |
| "learning_rate": 6.245394252026529e-06, | |
| "loss": 0.6377, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.750184229918939, | |
| "eval_loss": 2.009561777114868, | |
| "eval_runtime": 74.3801, | |
| "eval_samples_per_second": 16.227, | |
| "eval_steps_per_second": 2.03, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.8422991893883567, | |
| "grad_norm": 3.4046995639801025, | |
| "learning_rate": 3.942520265291084e-06, | |
| "loss": 0.6207, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.8422991893883567, | |
| "eval_loss": 2.0490310192108154, | |
| "eval_runtime": 74.7879, | |
| "eval_samples_per_second": 16.139, | |
| "eval_steps_per_second": 2.019, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.9344141488577744, | |
| "grad_norm": 2.0113770961761475, | |
| "learning_rate": 1.6396462785556374e-06, | |
| "loss": 0.6626, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.9344141488577744, | |
| "eval_loss": 2.0148627758026123, | |
| "eval_runtime": 74.8678, | |
| "eval_samples_per_second": 16.122, | |
| "eval_steps_per_second": 2.017, | |
| "step": 10500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10856, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3906256177981080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |