| { |
| "best_global_step": 2044, |
| "best_metric": 0.08643808960914612, |
| "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-2044", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 2044, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9784735812133072, |
| "grad_norm": 13.377490043640137, |
| "learning_rate": 1.5496489468405215e-05, |
| "loss": 0.3912, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.933435301315387, |
| "eval_loss": 0.18303145468235016, |
| "eval_model_preparation_time": 0.013, |
| "eval_runtime": 81.9678, |
| "eval_samples_per_second": 199.408, |
| "eval_steps_per_second": 24.937, |
| "step": 511 |
| }, |
| { |
| "epoch": 1.9569471624266144, |
| "grad_norm": 30.63884925842285, |
| "learning_rate": 1.0481444332998999e-05, |
| "loss": 0.1978, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9562557356989905, |
| "eval_loss": 0.12706944346427917, |
| "eval_model_preparation_time": 0.013, |
| "eval_runtime": 78.5588, |
| "eval_samples_per_second": 208.061, |
| "eval_steps_per_second": 26.019, |
| "step": 1022 |
| }, |
| { |
| "epoch": 2.935420743639922, |
| "grad_norm": 18.30719757080078, |
| "learning_rate": 5.4663991975927785e-06, |
| "loss": 0.1506, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.96690119302539, |
| "eval_loss": 0.09816861152648926, |
| "eval_model_preparation_time": 0.013, |
| "eval_runtime": 78.111, |
| "eval_samples_per_second": 209.254, |
| "eval_steps_per_second": 26.168, |
| "step": 1533 |
| }, |
| { |
| "epoch": 3.9138943248532287, |
| "grad_norm": 15.605788230895996, |
| "learning_rate": 4.5135406218655974e-07, |
| "loss": 0.1113, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9706332211685531, |
| "eval_loss": 0.08643808960914612, |
| "eval_model_preparation_time": 0.013, |
| "eval_runtime": 78.2892, |
| "eval_samples_per_second": 208.777, |
| "eval_steps_per_second": 26.108, |
| "step": 2044 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2044, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 1.2750306068312064e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
