| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.620408163265306, |
| "eval_steps": 200, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16326530612244897, |
| "grad_norm": 0.6756201386451721, |
| "learning_rate": 0.0001981178176898239, |
| "loss": 0.770789909362793, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.32653061224489793, |
| "grad_norm": 0.6545600295066833, |
| "learning_rate": 0.00018687117365181512, |
| "loss": 0.7264016151428223, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4897959183673469, |
| "grad_norm": 0.683688223361969, |
| "learning_rate": 0.00016659152250116812, |
| "loss": 0.7400761127471924, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6530612244897959, |
| "grad_norm": 0.47568151354789734, |
| "learning_rate": 0.00013938757562492873, |
| "loss": 0.7011314392089844, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.42000776529312134, |
| "learning_rate": 0.00010808804403614043, |
| "loss": 0.672628116607666, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9795918367346939, |
| "grad_norm": 0.4876711070537567, |
| "learning_rate": 7.594750436337467e-05, |
| "loss": 0.5931291103363037, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1306122448979592, |
| "grad_norm": 0.5444473624229431, |
| "learning_rate": 4.630798263510162e-05, |
| "loss": 0.6527483463287354, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2938775510204081, |
| "grad_norm": 0.6376090049743652, |
| "learning_rate": 2.2251444932035094e-05, |
| "loss": 0.576920461654663, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.457142857142857, |
| "grad_norm": 0.541858971118927, |
| "learning_rate": 6.2793294993656494e-06, |
| "loss": 0.5700631141662598, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.620408163265306, |
| "grad_norm": 0.4305003583431244, |
| "learning_rate": 5.2443095448506674e-08, |
| "loss": 0.5232778549194336, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.620408163265306, |
| "eval_loss": 0.8235033750534058, |
| "eval_runtime": 0.6803, |
| "eval_samples_per_second": 29.398, |
| "eval_steps_per_second": 7.349, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3287268790345728.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
