| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.042735042735042736, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008547008547008547, | |
| "eval_loss": 2.457526922225952, | |
| "eval_runtime": 300.1632, | |
| "eval_samples_per_second": 6.566, | |
| "eval_steps_per_second": 0.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002564102564102564, | |
| "grad_norm": 6.798144817352295, | |
| "learning_rate": 3e-05, | |
| "loss": 9.8904, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004273504273504274, | |
| "eval_loss": 2.0101470947265625, | |
| "eval_runtime": 301.4439, | |
| "eval_samples_per_second": 6.539, | |
| "eval_steps_per_second": 0.819, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005128205128205128, | |
| "grad_norm": 5.1715922355651855, | |
| "learning_rate": 6e-05, | |
| "loss": 8.8719, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": 4.066858768463135, | |
| "learning_rate": 9e-05, | |
| "loss": 6.4529, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008547008547008548, | |
| "eval_loss": 1.1293551921844482, | |
| "eval_runtime": 301.3709, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 0.82, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010256410256410256, | |
| "grad_norm": 5.805121421813965, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.5561, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "grad_norm": 2.3249106407165527, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.43, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "eval_loss": 0.795749306678772, | |
| "eval_runtime": 301.5134, | |
| "eval_samples_per_second": 6.537, | |
| "eval_steps_per_second": 0.819, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015384615384615385, | |
| "grad_norm": 1.7674269676208496, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.9702, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "eval_loss": 0.6842172741889954, | |
| "eval_runtime": 301.3897, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 0.82, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017948717948717947, | |
| "grad_norm": 2.400944709777832, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 2.7548, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020512820512820513, | |
| "grad_norm": 2.2111105918884277, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 2.8021, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021367521367521368, | |
| "eval_loss": 0.6264845132827759, | |
| "eval_runtime": 301.4841, | |
| "eval_samples_per_second": 6.538, | |
| "eval_steps_per_second": 0.819, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023076923076923078, | |
| "grad_norm": 1.8316013813018799, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 2.4214, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 1.9308996200561523, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4971, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "eval_loss": 0.5809954404830933, | |
| "eval_runtime": 301.5058, | |
| "eval_samples_per_second": 6.537, | |
| "eval_steps_per_second": 0.819, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028205128205128206, | |
| "grad_norm": 1.8765429258346558, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 2.1488, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.029914529914529916, | |
| "eval_loss": 0.5602862238883972, | |
| "eval_runtime": 301.3722, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 0.82, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03076923076923077, | |
| "grad_norm": 1.5551074743270874, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 2.21, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 1.4433046579360962, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 2.2309, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "eval_loss": 0.5497083067893982, | |
| "eval_runtime": 301.4563, | |
| "eval_samples_per_second": 6.538, | |
| "eval_steps_per_second": 0.819, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.035897435897435895, | |
| "grad_norm": 1.7005305290222168, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.0872, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 1.8922603130340576, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.437, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "eval_loss": 0.5421185493469238, | |
| "eval_runtime": 301.2894, | |
| "eval_samples_per_second": 6.542, | |
| "eval_steps_per_second": 0.82, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.041025641025641026, | |
| "grad_norm": 1.4888923168182373, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 2.1201, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "eval_loss": 0.5405860543251038, | |
| "eval_runtime": 301.4329, | |
| "eval_samples_per_second": 6.539, | |
| "eval_steps_per_second": 0.819, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.28802361442304e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |