| { | |
| "best_global_step": 4805, | |
| "best_metric": 0.05839185044169426, | |
| "best_model_checkpoint": "siglip2-finetune-full/checkpoint-4805", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4805, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1040582726326743, | |
| "grad_norm": 44.86325454711914, | |
| "learning_rate": 9.053627760252366e-07, | |
| "loss": 1.8108, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2081165452653486, | |
| "grad_norm": 35.94168472290039, | |
| "learning_rate": 8.002103049421662e-07, | |
| "loss": 0.4382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31217481789802287, | |
| "grad_norm": 15.327913284301758, | |
| "learning_rate": 6.950578338590957e-07, | |
| "loss": 0.2398, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4162330905306972, | |
| "grad_norm": 42.22140884399414, | |
| "learning_rate": 5.899053627760253e-07, | |
| "loss": 0.1731, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5202913631633714, | |
| "grad_norm": 52.25971603393555, | |
| "learning_rate": 4.847528916929548e-07, | |
| "loss": 0.144, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6243496357960457, | |
| "grad_norm": 29.09841537475586, | |
| "learning_rate": 3.7960042060988434e-07, | |
| "loss": 0.1267, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.72840790842872, | |
| "grad_norm": 56.122318267822266, | |
| "learning_rate": 2.744479495268139e-07, | |
| "loss": 0.1061, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8324661810613944, | |
| "grad_norm": 36.10615158081055, | |
| "learning_rate": 1.6929547844374343e-07, | |
| "loss": 0.0977, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9365244536940687, | |
| "grad_norm": 41.66591262817383, | |
| "learning_rate": 6.414300736067297e-08, | |
| "loss": 0.0934, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9832959313103717, | |
| "eval_loss": 0.05839185044169426, | |
| "eval_model_preparation_time": 0.004, | |
| "eval_runtime": 2181.6249, | |
| "eval_samples_per_second": 70.468, | |
| "eval_steps_per_second": 8.809, | |
| "step": 4805 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4805, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.2877966316954511e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |