| { |
| "best_metric": 7.642526149749756, |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", |
| "epoch": 0.07804878048780488, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0031219512195121953, |
| "grad_norm": 5.459062099456787, |
| "learning_rate": 5e-05, |
| "loss": 9.1044, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0031219512195121953, |
| "eval_loss": 8.4755859375, |
| "eval_runtime": 0.9418, |
| "eval_samples_per_second": 53.09, |
| "eval_steps_per_second": 53.09, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.006243902439024391, |
| "grad_norm": 5.766212463378906, |
| "learning_rate": 0.0001, |
| "loss": 8.8885, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.009365853658536585, |
| "grad_norm": 5.27004861831665, |
| "learning_rate": 9.958086757163489e-05, |
| "loss": 8.6246, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.012487804878048781, |
| "grad_norm": 5.087274551391602, |
| "learning_rate": 9.833127793065098e-05, |
| "loss": 8.5958, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.015609756097560976, |
| "grad_norm": 5.238975524902344, |
| "learning_rate": 9.627450856774539e-05, |
| "loss": 8.4973, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01873170731707317, |
| "grad_norm": 4.5957489013671875, |
| "learning_rate": 9.3448873204592e-05, |
| "loss": 8.1857, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.021853658536585364, |
| "grad_norm": 3.9758787155151367, |
| "learning_rate": 8.990700808169889e-05, |
| "loss": 8.0822, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.024975609756097562, |
| "grad_norm": 3.484137773513794, |
| "learning_rate": 8.571489144483944e-05, |
| "loss": 8.0934, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.028097560975609757, |
| "grad_norm": 3.338285207748413, |
| "learning_rate": 8.095061449516903e-05, |
| "loss": 8.0251, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03121951219512195, |
| "grad_norm": 2.8886618614196777, |
| "learning_rate": 7.570292669790186e-05, |
| "loss": 7.8113, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03434146341463415, |
| "grad_norm": 2.729102849960327, |
| "learning_rate": 7.006958254769438e-05, |
| "loss": 7.8799, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03746341463414634, |
| "grad_norm": 2.3049380779266357, |
| "learning_rate": 6.415552058736854e-05, |
| "loss": 7.7871, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04058536585365854, |
| "grad_norm": 1.9474453926086426, |
| "learning_rate": 5.80709086014102e-05, |
| "loss": 7.7129, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.04370731707317073, |
| "grad_norm": 1.7848256826400757, |
| "learning_rate": 5.192909139858981e-05, |
| "loss": 7.8224, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.04682926829268293, |
| "grad_norm": 1.7634596824645996, |
| "learning_rate": 4.584447941263149e-05, |
| "loss": 7.8094, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.049951219512195125, |
| "grad_norm": 1.7062458992004395, |
| "learning_rate": 3.9930417452305626e-05, |
| "loss": 7.6345, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.053073170731707316, |
| "grad_norm": 1.6087889671325684, |
| "learning_rate": 3.4297073302098156e-05, |
| "loss": 7.5839, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.056195121951219514, |
| "grad_norm": 1.5590335130691528, |
| "learning_rate": 2.9049385504830985e-05, |
| "loss": 7.6765, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.059317073170731704, |
| "grad_norm": 1.6086766719818115, |
| "learning_rate": 2.4285108555160577e-05, |
| "loss": 7.6771, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.0624390243902439, |
| "grad_norm": 1.5486078262329102, |
| "learning_rate": 2.0092991918301108e-05, |
| "loss": 7.6274, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0655609756097561, |
| "grad_norm": 1.5740314722061157, |
| "learning_rate": 1.6551126795408016e-05, |
| "loss": 7.6517, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0686829268292683, |
| "grad_norm": 1.5726820230484009, |
| "learning_rate": 1.3725491432254624e-05, |
| "loss": 7.5514, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.07180487804878048, |
| "grad_norm": 1.544975996017456, |
| "learning_rate": 1.1668722069349041e-05, |
| "loss": 7.613, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.07492682926829268, |
| "grad_norm": 1.5659458637237549, |
| "learning_rate": 1.0419132428365116e-05, |
| "loss": 7.5893, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07804878048780488, |
| "grad_norm": 1.5587267875671387, |
| "learning_rate": 1e-05, |
| "loss": 7.4812, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07804878048780488, |
| "eval_loss": 7.642526149749756, |
| "eval_runtime": 0.971, |
| "eval_samples_per_second": 51.495, |
| "eval_steps_per_second": 51.495, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 25, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 1, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 29037976879104.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
