| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010947107226915288, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "eval_loss": 2.270890951156616, | |
| "eval_runtime": 863.5161, | |
| "eval_samples_per_second": 13.363, | |
| "eval_steps_per_second": 6.682, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "grad_norm": 1.7231369018554688, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "grad_norm": 1.331156611442566, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8914, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00029192285938440767, | |
| "eval_loss": 1.7924015522003174, | |
| "eval_runtime": 861.2251, | |
| "eval_samples_per_second": 13.398, | |
| "eval_steps_per_second": 6.7, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "grad_norm": 1.7245151996612549, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004378842890766115, | |
| "grad_norm": 1.895203709602356, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7148, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005473553613457644, | |
| "grad_norm": 1.1740204095840454, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.6693, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005838457187688153, | |
| "eval_loss": 1.5610108375549316, | |
| "eval_runtime": 861.494, | |
| "eval_samples_per_second": 13.394, | |
| "eval_steps_per_second": 6.698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006568264336149173, | |
| "grad_norm": 1.226759433746338, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6198, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007662975058840702, | |
| "grad_norm": 1.0266218185424805, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.5081, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.000875768578153223, | |
| "grad_norm": 1.0099457502365112, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.5154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000875768578153223, | |
| "eval_loss": 1.5118098258972168, | |
| "eval_runtime": 861.1832, | |
| "eval_samples_per_second": 13.399, | |
| "eval_steps_per_second": 6.7, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009852396504223758, | |
| "grad_norm": 1.1712850332260132, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.503, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010947107226915288, | |
| "grad_norm": 1.214179277420044, | |
| "learning_rate": 0.0, | |
| "loss": 1.5166, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2819192562581504e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |