| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0392156862745098, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00392156862745098, | |
| "grad_norm": 0.5202540159225464, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00392156862745098, | |
| "eval_loss": 3.2287890911102295, | |
| "eval_runtime": 4.4275, | |
| "eval_samples_per_second": 24.393, | |
| "eval_steps_per_second": 12.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00784313725490196, | |
| "grad_norm": 0.6282548904418945, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0168, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "grad_norm": 0.6707961559295654, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "eval_loss": 3.2221531867980957, | |
| "eval_runtime": 3.296, | |
| "eval_samples_per_second": 32.767, | |
| "eval_steps_per_second": 16.384, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01568627450980392, | |
| "grad_norm": 0.6845298409461975, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1449, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 0.8228346109390259, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3021, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "grad_norm": 0.8989683985710144, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2464, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "eval_loss": 3.1364099979400635, | |
| "eval_runtime": 3.3155, | |
| "eval_samples_per_second": 32.574, | |
| "eval_steps_per_second": 16.287, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027450980392156862, | |
| "grad_norm": 1.0998562574386597, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0584, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03137254901960784, | |
| "grad_norm": 0.7477495074272156, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0858, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "grad_norm": 0.6923421621322632, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "eval_loss": 2.9242029190063477, | |
| "eval_runtime": 3.2906, | |
| "eval_samples_per_second": 32.821, | |
| "eval_steps_per_second": 16.41, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 0.8409781455993652, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8148, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1647822923366400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |