| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01295788686768004, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033225350942769335, | |
| "eval_loss": 1.356743574142456, | |
| "eval_runtime": 69.6151, | |
| "eval_samples_per_second": 18.214, | |
| "eval_steps_per_second": 9.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016612675471384666, | |
| "grad_norm": 1.057161569595337, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2723, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003322535094276933, | |
| "grad_norm": 1.0211741924285889, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2354, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003322535094276933, | |
| "eval_loss": 1.090079426765442, | |
| "eval_runtime": 69.432, | |
| "eval_samples_per_second": 18.262, | |
| "eval_steps_per_second": 9.131, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0049838026414154, | |
| "grad_norm": 1.071433424949646, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0207, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006645070188553866, | |
| "grad_norm": 1.2155852317810059, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.873, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006645070188553866, | |
| "eval_loss": 0.8100319504737854, | |
| "eval_runtime": 70.2598, | |
| "eval_samples_per_second": 18.047, | |
| "eval_steps_per_second": 9.024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008306337735692334, | |
| "grad_norm": 1.0802018642425537, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0099676052828308, | |
| "grad_norm": 0.9234360456466675, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7435, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0099676052828308, | |
| "eval_loss": 0.7390913963317871, | |
| "eval_runtime": 69.6251, | |
| "eval_samples_per_second": 18.212, | |
| "eval_steps_per_second": 9.106, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011628872829969267, | |
| "grad_norm": 0.9415158629417419, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7966, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1950379589763072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |