| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5714285714285714, | |
| "eval_steps": 20, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009523809523809525, | |
| "eval_loss": 2.1661489009857178, | |
| "eval_runtime": 27.6834, | |
| "eval_samples_per_second": 54.22, | |
| "eval_steps_per_second": 6.791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 10.75, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7308, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 239.0, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 2.4483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "eval_loss": 7.531261920928955, | |
| "eval_runtime": 26.8047, | |
| "eval_samples_per_second": 55.998, | |
| "eval_steps_per_second": 7.014, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 149.0, | |
| "learning_rate": 0.0002, | |
| "loss": 11.0101, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 28.875, | |
| "learning_rate": 0.00019984815164333163, | |
| "loss": 8.9176, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "eval_loss": 7.494989395141602, | |
| "eval_runtime": 43.1971, | |
| "eval_samples_per_second": 34.748, | |
| "eval_steps_per_second": 4.352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 7.34375, | |
| "learning_rate": 0.00019939306773179497, | |
| "loss": 7.4643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 13.375, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 7.4183, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "eval_loss": 7.3631272315979, | |
| "eval_runtime": 46.4427, | |
| "eval_samples_per_second": 32.319, | |
| "eval_steps_per_second": 4.048, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.194038141524378e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |