| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8774193548387097, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.7787522077560425, | |
| "learning_rate": 4.984786304919372e-05, | |
| "loss": 0.9092, | |
| "mean_token_accuracy": 0.7503577440977096, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.9605578184127808, | |
| "learning_rate": 4.815986240480617e-05, | |
| "loss": 0.7348, | |
| "mean_token_accuracy": 0.7808357656002045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.601085364818573, | |
| "learning_rate": 4.473599997017701e-05, | |
| "loss": 0.6564, | |
| "mean_token_accuracy": 0.7980892196297645, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 512.1144409179688, | |
| "learning_rate": 3.9863952006593134e-05, | |
| "loss": 1.6224, | |
| "mean_token_accuracy": 0.6946261065346854, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 0.6288492679595947, | |
| "learning_rate": 3.3953072735999534e-05, | |
| "loss": 0.6195, | |
| "mean_token_accuracy": 0.8052686437964439, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5161290322580645, | |
| "grad_norm": 0.4004594385623932, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.5815, | |
| "mean_token_accuracy": 0.8156079143285752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7741935483870968, | |
| "grad_norm": 0.3189852833747864, | |
| "learning_rate": 2.1046927264000475e-05, | |
| "loss": 0.5735, | |
| "mean_token_accuracy": 0.8173265308141708, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3097386360168457, | |
| "learning_rate": 1.5136047993406865e-05, | |
| "loss": 0.5678, | |
| "mean_token_accuracy": 0.819041873727526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.258064516129032, | |
| "grad_norm": 0.26866406202316284, | |
| "learning_rate": 1.0264000029822999e-05, | |
| "loss": 0.5328, | |
| "mean_token_accuracy": 0.8284321025013923, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.5161290322580645, | |
| "grad_norm": 0.24466799199581146, | |
| "learning_rate": 6.840137595193838e-06, | |
| "loss": 0.5318, | |
| "mean_token_accuracy": 0.8282432556152344, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.774193548387097, | |
| "grad_norm": 0.22442595660686493, | |
| "learning_rate": 5.152136950806283e-06, | |
| "loss": 0.5416, | |
| "mean_token_accuracy": 0.8250808849930763, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.8774193548387097, | |
| "mean_token_accuracy": 0.8287803158164024, | |
| "step": 57, | |
| "total_flos": 84573274767360.0, | |
| "train_loss": 0.7089759466940897, | |
| "train_runtime": 1518.5199, | |
| "train_samples_per_second": 4.876, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 57, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 84573274767360.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |