| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19011406844106463, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038022813688212928, | |
| "eval_loss": 2.3726208209991455, | |
| "eval_runtime": 7.5387, | |
| "eval_samples_per_second": 14.724, | |
| "eval_steps_per_second": 7.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019011406844106463, | |
| "grad_norm": 3.648099422454834, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2169, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03802281368821293, | |
| "grad_norm": 3.267825126647949, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03802281368821293, | |
| "eval_loss": 1.1096165180206299, | |
| "eval_runtime": 7.5802, | |
| "eval_samples_per_second": 14.643, | |
| "eval_steps_per_second": 7.388, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.057034220532319393, | |
| "grad_norm": 4.337152004241943, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7037, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07604562737642585, | |
| "grad_norm": 4.381193161010742, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07604562737642585, | |
| "eval_loss": 0.44711190462112427, | |
| "eval_runtime": 7.5968, | |
| "eval_samples_per_second": 14.611, | |
| "eval_steps_per_second": 7.372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09505703422053231, | |
| "grad_norm": 3.5168604850769043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2719, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11406844106463879, | |
| "grad_norm": 1.5816749334335327, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11406844106463879, | |
| "eval_loss": 0.27313661575317383, | |
| "eval_runtime": 7.6687, | |
| "eval_samples_per_second": 14.474, | |
| "eval_steps_per_second": 7.302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13307984790874525, | |
| "grad_norm": 1.9869533777236938, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3243, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1520912547528517, | |
| "grad_norm": 2.389986991882324, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3914, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1520912547528517, | |
| "eval_loss": 0.2599426507949829, | |
| "eval_runtime": 7.5737, | |
| "eval_samples_per_second": 14.656, | |
| "eval_steps_per_second": 7.394, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17110266159695817, | |
| "grad_norm": 1.5311264991760254, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2876, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19011406844106463, | |
| "grad_norm": 1.4557512998580933, | |
| "learning_rate": 0.0, | |
| "loss": 0.1591, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19011406844106463, | |
| "eval_loss": 0.2307048887014389, | |
| "eval_runtime": 7.6113, | |
| "eval_samples_per_second": 14.584, | |
| "eval_steps_per_second": 7.358, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |