| { |
| "best_metric": 0.35378891229629517, |
| "best_model_checkpoint": "emotion-detect-siglip2/checkpoint-1449", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1449, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8240471105934123, |
| "eval_loss": 0.46621787548065186, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 272.0398, |
| "eval_samples_per_second": 56.804, |
| "eval_steps_per_second": 7.102, |
| "step": 483 |
| }, |
| { |
| "epoch": 1.0351966873706004, |
| "grad_norm": 39.48198699951172, |
| "learning_rate": 2.2826780021253984e-06, |
| "loss": 0.8459, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8499320520287322, |
| "eval_loss": 0.39572280645370483, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 272.1416, |
| "eval_samples_per_second": 56.783, |
| "eval_steps_per_second": 7.099, |
| "step": 966 |
| }, |
| { |
| "epoch": 2.070393374741201, |
| "grad_norm": 36.067955017089844, |
| "learning_rate": 1.485653560042508e-06, |
| "loss": 0.4851, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.866045428072219, |
| "eval_loss": 0.35378891229629517, |
| "eval_model_preparation_time": 0.0024, |
| "eval_runtime": 274.1161, |
| "eval_samples_per_second": 56.374, |
| "eval_steps_per_second": 7.048, |
| "step": 1449 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1932, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.8829498227935027e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
