| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002319468068656255, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.731560228854182e-05, | |
| "eval_loss": 0.7148739695549011, | |
| "eval_runtime": 487.5372, | |
| "eval_samples_per_second": 11.17, | |
| "eval_steps_per_second": 5.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002319468068656255, | |
| "grad_norm": 4.921934127807617, | |
| "learning_rate": 3e-05, | |
| "loss": 11.696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000463893613731251, | |
| "grad_norm": 5.798152923583984, | |
| "learning_rate": 6e-05, | |
| "loss": 9.8127, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006185248183083346, | |
| "eval_loss": 0.707319974899292, | |
| "eval_runtime": 489.9306, | |
| "eval_samples_per_second": 11.116, | |
| "eval_steps_per_second": 5.558, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006958404205968764, | |
| "grad_norm": 11.535150527954102, | |
| "learning_rate": 9e-05, | |
| "loss": 9.7368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000927787227462502, | |
| "grad_norm": 6.120208740234375, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 8.5474, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011597340343281275, | |
| "grad_norm": 21.290348052978516, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.543, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012370496366166692, | |
| "eval_loss": 0.7007141709327698, | |
| "eval_runtime": 490.0839, | |
| "eval_samples_per_second": 11.112, | |
| "eval_steps_per_second": 5.556, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013916808411937528, | |
| "grad_norm": 13.922175407409668, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 8.3382, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016236276480593784, | |
| "grad_norm": 5.696683406829834, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 5.5278, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001855574454925004, | |
| "grad_norm": 6.050934314727783, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 6.2744, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001855574454925004, | |
| "eval_loss": 0.67711341381073, | |
| "eval_runtime": 490.0157, | |
| "eval_samples_per_second": 11.114, | |
| "eval_steps_per_second": 5.557, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0020875212617906293, | |
| "grad_norm": 7.773568153381348, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 7.0816, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002319468068656255, | |
| "grad_norm": 4.683486461639404, | |
| "learning_rate": 0.0, | |
| "loss": 5.3879, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5957676102057984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |