| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033297261300258055, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033297261300258056, | |
| "grad_norm": 11.810403823852539, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033297261300258056, | |
| "eval_loss": 3.272779703140259, | |
| "eval_runtime": 15.5246, | |
| "eval_samples_per_second": 81.483, | |
| "eval_steps_per_second": 40.774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006659452260051611, | |
| "grad_norm": 16.577980041503906, | |
| "learning_rate": 4e-05, | |
| "loss": 15.1844, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009989178390077415, | |
| "grad_norm": 13.144250869750977, | |
| "learning_rate": 6e-05, | |
| "loss": 13.6021, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009989178390077415, | |
| "eval_loss": 3.2567977905273438, | |
| "eval_runtime": 14.3557, | |
| "eval_samples_per_second": 88.118, | |
| "eval_steps_per_second": 44.094, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013318904520103223, | |
| "grad_norm": 11.238504409790039, | |
| "learning_rate": 8e-05, | |
| "loss": 13.347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016648630650129028, | |
| "grad_norm": 19.44588279724121, | |
| "learning_rate": 0.0001, | |
| "loss": 17.1388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001997835678015483, | |
| "grad_norm": 10.6722412109375, | |
| "learning_rate": 0.00012, | |
| "loss": 12.4696, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001997835678015483, | |
| "eval_loss": 3.158052682876587, | |
| "eval_runtime": 14.6741, | |
| "eval_samples_per_second": 86.206, | |
| "eval_steps_per_second": 43.137, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023308082910180636, | |
| "grad_norm": 15.243246078491211, | |
| "learning_rate": 0.00014, | |
| "loss": 10.5005, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0026637809040206445, | |
| "grad_norm": 12.916600227355957, | |
| "learning_rate": 0.00016, | |
| "loss": 13.0037, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002996753517023225, | |
| "grad_norm": 13.6755952835083, | |
| "learning_rate": 0.00018, | |
| "loss": 13.1308, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002996753517023225, | |
| "eval_loss": 2.942934513092041, | |
| "eval_runtime": 14.4751, | |
| "eval_samples_per_second": 87.391, | |
| "eval_steps_per_second": 43.73, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033297261300258055, | |
| "grad_norm": 12.82334041595459, | |
| "learning_rate": 0.0002, | |
| "loss": 10.2212, | |
| "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": 77314746482688.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |