| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2696326255476913, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010785305021907651, | |
| "grad_norm": 4.344828128814697, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010785305021907651, | |
| "eval_loss": 4.603348731994629, | |
| "eval_runtime": 2.6307, | |
| "eval_samples_per_second": 19.006, | |
| "eval_steps_per_second": 4.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021570610043815303, | |
| "grad_norm": 5.045979022979736, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7432, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.032355915065722954, | |
| "grad_norm": 4.547981262207031, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.1515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.043141220087630605, | |
| "grad_norm": 3.4077675342559814, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.4805, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.053926525109538256, | |
| "grad_norm": 2.6199681758880615, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06471183013144591, | |
| "grad_norm": 2.0004589557647705, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.2886, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07549713515335356, | |
| "grad_norm": 1.5946983098983765, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.8103, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08628244017526121, | |
| "grad_norm": 1.276253342628479, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.3543, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09706774519716886, | |
| "grad_norm": 1.0471776723861694, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.954, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10785305021907651, | |
| "grad_norm": 0.9004111289978027, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.7611, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11863835524098416, | |
| "grad_norm": 0.5792182087898254, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.666, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12942366026289182, | |
| "grad_norm": 0.24996623396873474, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.3539, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14020896528479945, | |
| "grad_norm": 3.6459882259368896, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.8301, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15099427030670712, | |
| "grad_norm": 2.7042088508605957, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.3308, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16177957532861476, | |
| "grad_norm": 2.0865371227264404, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17256488035052242, | |
| "grad_norm": 1.6845545768737793, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.199, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18335018537243006, | |
| "grad_norm": 1.4420006275177002, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.8033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19413549039433772, | |
| "grad_norm": 1.2050021886825562, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.4628, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20492079541624536, | |
| "grad_norm": 1.108812689781189, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.1717, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21570610043815303, | |
| "grad_norm": 0.9539301991462708, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.8746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22649140546006066, | |
| "grad_norm": 0.5657325387001038, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.7393, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23727671048196833, | |
| "grad_norm": 0.4725482761859894, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.5845, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.5372779965400696, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.6176, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.25884732052578363, | |
| "grad_norm": 0.42209765315055847, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.391, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2696326255476913, | |
| "grad_norm": 0.32752636075019836, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.4172, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2696326255476913, | |
| "eval_loss": 3.2214887142181396, | |
| "eval_runtime": 2.2412, | |
| "eval_samples_per_second": 22.31, | |
| "eval_steps_per_second": 5.801, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.81197642825728e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |