| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001886080724254998, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001886080724254998, | |
| "grad_norm": 11.620072364807129, | |
| "learning_rate": 2e-05, | |
| "loss": 3.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001886080724254998, | |
| "eval_loss": 1.0258384943008423, | |
| "eval_runtime": 72.4949, | |
| "eval_samples_per_second": 30.802, | |
| "eval_steps_per_second": 15.408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003772161448509996, | |
| "grad_norm": 9.528853416442871, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3093, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005658242172764995, | |
| "grad_norm": 9.460070610046387, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005658242172764995, | |
| "eval_loss": 1.0034009218215942, | |
| "eval_runtime": 70.92, | |
| "eval_samples_per_second": 31.486, | |
| "eval_steps_per_second": 15.75, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 9.758016586303711, | |
| "learning_rate": 8e-05, | |
| "loss": 3.4399, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000943040362127499, | |
| "grad_norm": 19.836227416992188, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7794, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001131648434552999, | |
| "grad_norm": 12.299468040466309, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0613, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001131648434552999, | |
| "eval_loss": 0.9074329733848572, | |
| "eval_runtime": 68.176, | |
| "eval_samples_per_second": 32.753, | |
| "eval_steps_per_second": 16.384, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013202565069784986, | |
| "grad_norm": 18.84109115600586, | |
| "learning_rate": 0.00014, | |
| "loss": 4.0897, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 12.41354751586914, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6245, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016974726518294984, | |
| "grad_norm": 9.773690223693848, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016974726518294984, | |
| "eval_loss": 0.7293293476104736, | |
| "eval_runtime": 70.9246, | |
| "eval_samples_per_second": 31.484, | |
| "eval_steps_per_second": 15.749, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001886080724254998, | |
| "grad_norm": 13.274161338806152, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9545, | |
| "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": 1752671799214080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |