| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031338138514572234, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031338138514572234, | |
| "grad_norm": 3.1054439544677734, | |
| "learning_rate": 2e-05, | |
| "loss": 3.4776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031338138514572234, | |
| "eval_loss": 3.1475110054016113, | |
| "eval_runtime": 30.4147, | |
| "eval_samples_per_second": 44.189, | |
| "eval_steps_per_second": 22.095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006267627702914447, | |
| "grad_norm": 2.9077043533325195, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9316, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000940144155437167, | |
| "grad_norm": 2.368230104446411, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1299, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000940144155437167, | |
| "eval_loss": 3.12211537361145, | |
| "eval_runtime": 29.9453, | |
| "eval_samples_per_second": 44.882, | |
| "eval_steps_per_second": 22.441, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012535255405828893, | |
| "grad_norm": 3.153538227081299, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6861, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015669069257286117, | |
| "grad_norm": 3.6661782264709473, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1437, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001880288310874334, | |
| "grad_norm": 1.4186253547668457, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0638, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001880288310874334, | |
| "eval_loss": 2.968801975250244, | |
| "eval_runtime": 29.8749, | |
| "eval_samples_per_second": 44.988, | |
| "eval_steps_per_second": 22.494, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021936696960200563, | |
| "grad_norm": 0.9197999835014343, | |
| "learning_rate": 0.00014, | |
| "loss": 2.8142, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025070510811657787, | |
| "grad_norm": 0.8338276147842407, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8289, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002820432466311501, | |
| "grad_norm": 0.7536571025848389, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8663, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002820432466311501, | |
| "eval_loss": 2.910203218460083, | |
| "eval_runtime": 29.4647, | |
| "eval_samples_per_second": 45.614, | |
| "eval_steps_per_second": 22.807, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031338138514572234, | |
| "grad_norm": 0.7594237923622131, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9355, | |
| "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": 153447605207040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |