| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04550625711035267, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004550625711035267, | |
| "grad_norm": 75.894287109375, | |
| "learning_rate": 2e-05, | |
| "loss": 9.1111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004550625711035267, | |
| "eval_loss": 8.72750473022461, | |
| "eval_runtime": 2.6439, | |
| "eval_samples_per_second": 35.176, | |
| "eval_steps_per_second": 17.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 59.834877014160156, | |
| "learning_rate": 4e-05, | |
| "loss": 7.4004, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "grad_norm": 61.54233169555664, | |
| "learning_rate": 6e-05, | |
| "loss": 8.4554, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "eval_loss": 8.171257019042969, | |
| "eval_runtime": 1.6722, | |
| "eval_samples_per_second": 55.615, | |
| "eval_steps_per_second": 28.107, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 72.09519958496094, | |
| "learning_rate": 8e-05, | |
| "loss": 8.5107, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022753128555176336, | |
| "grad_norm": 74.13758087158203, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6485, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "grad_norm": 52.351417541503906, | |
| "learning_rate": 0.00012, | |
| "loss": 5.3262, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "eval_loss": 4.183811664581299, | |
| "eval_runtime": 1.7018, | |
| "eval_samples_per_second": 54.648, | |
| "eval_steps_per_second": 27.618, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03185437997724687, | |
| "grad_norm": 71.99066162109375, | |
| "learning_rate": 0.00014, | |
| "loss": 3.9438, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03640500568828214, | |
| "grad_norm": 20.329301834106445, | |
| "learning_rate": 0.00016, | |
| "loss": 3.8839, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.040955631399317405, | |
| "grad_norm": 17.403549194335938, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3409, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.040955631399317405, | |
| "eval_loss": 2.8907394409179688, | |
| "eval_runtime": 1.7017, | |
| "eval_samples_per_second": 54.652, | |
| "eval_steps_per_second": 27.62, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04550625711035267, | |
| "grad_norm": 8.729594230651855, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0727, | |
| "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": 255791978250240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |