| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007312614259597806, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "grad_norm": 3.1223161220550537, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "eval_loss": 2.5146937370300293, | |
| "eval_runtime": 17.2647, | |
| "eval_samples_per_second": 33.363, | |
| "eval_steps_per_second": 16.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014625228519195613, | |
| "grad_norm": 1.7607024908065796, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0419, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "grad_norm": 1.8213695287704468, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "eval_loss": 2.506520986557007, | |
| "eval_runtime": 16.6193, | |
| "eval_samples_per_second": 34.659, | |
| "eval_steps_per_second": 17.329, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029250457038391227, | |
| "grad_norm": 2.198183059692383, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6307, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003656307129798903, | |
| "grad_norm": 3.022437334060669, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2612, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "grad_norm": 2.302635908126831, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "eval_loss": 2.2467222213745117, | |
| "eval_runtime": 16.694, | |
| "eval_samples_per_second": 34.503, | |
| "eval_steps_per_second": 17.252, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005118829981718464, | |
| "grad_norm": 3.5332112312316895, | |
| "learning_rate": 0.00014, | |
| "loss": 2.6293, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005850091407678245, | |
| "grad_norm": 3.0854251384735107, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0073, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "grad_norm": 2.4246997833251953, | |
| "learning_rate": 0.00018, | |
| "loss": 1.4883, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "eval_loss": 1.412724256515503, | |
| "eval_runtime": 16.7227, | |
| "eval_samples_per_second": 34.444, | |
| "eval_steps_per_second": 17.222, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007312614259597806, | |
| "grad_norm": 3.4759838581085205, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5372, | |
| "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": 1742636046090240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |