| { | |
| "best_metric": 0.7716913223266602, | |
| "best_model_checkpoint": "autotrain-6k3et-c7br0/checkpoint-51", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 17.922496795654297, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.3714, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 23.795621871948242, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1954, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5294117647058824, | |
| "grad_norm": 14.98381233215332, | |
| "learning_rate": 2.8e-05, | |
| "loss": 1.1055, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 12.722396850585938, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.9275, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 13.562817573547363, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.7038, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9882338643074036, | |
| "eval_runtime": 0.3701, | |
| "eval_samples_per_second": 94.572, | |
| "eval_steps_per_second": 8.106, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 10.743192672729492, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.7652, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.2352941176470589, | |
| "grad_norm": 8.609188079833984, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.4272, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 8.594082832336426, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.5581, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5882352941176472, | |
| "grad_norm": 10.913146018981934, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.4515, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 6.585514068603516, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.6145, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9411764705882353, | |
| "grad_norm": 6.181787967681885, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.6234, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.8181360960006714, | |
| "eval_runtime": 0.3087, | |
| "eval_samples_per_second": 113.374, | |
| "eval_steps_per_second": 9.718, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 3.0840885639190674, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.4453, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.2941176470588234, | |
| "grad_norm": 4.636595726013184, | |
| "learning_rate": 8e-06, | |
| "loss": 0.6209, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 9.451086044311523, | |
| "learning_rate": 6e-06, | |
| "loss": 0.5695, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.6470588235294117, | |
| "grad_norm": 7.00937557220459, | |
| "learning_rate": 4e-06, | |
| "loss": 0.4684, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 4.03523063659668, | |
| "learning_rate": 2e-06, | |
| "loss": 0.3162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 4.497876167297363, | |
| "learning_rate": 0.0, | |
| "loss": 0.3467, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.7716913223266602, | |
| "eval_runtime": 0.3027, | |
| "eval_samples_per_second": 115.64, | |
| "eval_steps_per_second": 9.912, | |
| "step": 51 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 51, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |