| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 6, |
| "global_step": 31, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03225806451612903, |
| "grad_norm": 2.39890456199646, |
| "learning_rate": 0.0, |
| "loss": 1.736328125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.06451612903225806, |
| "grad_norm": 2.554351329803467, |
| "learning_rate": 2.5e-06, |
| "loss": 1.7060546875, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0967741935483871, |
| "grad_norm": 2.6744349002838135, |
| "learning_rate": 5e-06, |
| "loss": 1.6474609375, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.12903225806451613, |
| "grad_norm": 2.8339805603027344, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 1.6865234375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.16129032258064516, |
| "grad_norm": 2.64522123336792, |
| "learning_rate": 1e-05, |
| "loss": 1.64453125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1935483870967742, |
| "grad_norm": 2.179842710494995, |
| "learning_rate": 9.969572609838745e-06, |
| "loss": 1.6220703125, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.22580645161290322, |
| "grad_norm": 2.2128775119781494, |
| "learning_rate": 9.878701917609208e-06, |
| "loss": 1.650390625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.22580645161290322, |
| "eval_loss": 1.48046875, |
| "eval_runtime": 2.6339, |
| "eval_samples_per_second": 0.759, |
| "eval_steps_per_second": 0.38, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.25806451612903225, |
| "grad_norm": 2.7124762535095215, |
| "learning_rate": 9.728616793536588e-06, |
| "loss": 1.6220703125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.2903225806451613, |
| "grad_norm": 1.7431614398956299, |
| "learning_rate": 9.521346881455356e-06, |
| "loss": 1.4306640625, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 1.9239155054092407, |
| "learning_rate": 9.259695151358215e-06, |
| "loss": 1.427734375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3548387096774194, |
| "grad_norm": 2.201296806335449, |
| "learning_rate": 8.947199994035402e-06, |
| "loss": 1.5146484375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.3870967741935484, |
| "grad_norm": 1.9941728115081787, |
| "learning_rate": 8.588087370409303e-06, |
| "loss": 1.4658203125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.41935483870967744, |
| "grad_norm": 1.4463545083999634, |
| "learning_rate": 8.187213662662539e-06, |
| "loss": 1.3359375, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.41935483870967744, |
| "eval_loss": 1.3125, |
| "eval_runtime": 2.6299, |
| "eval_samples_per_second": 0.76, |
| "eval_steps_per_second": 0.38, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.45161290322580644, |
| "grad_norm": 1.8634389638900757, |
| "learning_rate": 7.75e-06, |
| "loss": 1.3623046875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.4838709677419355, |
| "grad_norm": 1.3964911699295044, |
| "learning_rate": 7.282358947176207e-06, |
| "loss": 1.3232421875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5161290322580645, |
| "grad_norm": 1.4567354917526245, |
| "learning_rate": 6.790614547199908e-06, |
| "loss": 1.3125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.5483870967741935, |
| "grad_norm": 1.2070086002349854, |
| "learning_rate": 6.281416799501188e-06, |
| "loss": 1.263671875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.5806451612903226, |
| "grad_norm": 1.337532639503479, |
| "learning_rate": 5.761651730097142e-06, |
| "loss": 1.396484375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.6129032258064516, |
| "grad_norm": 1.2737104892730713, |
| "learning_rate": 5.23834826990286e-06, |
| "loss": 1.314453125, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.6129032258064516, |
| "eval_loss": 1.2265625, |
| "eval_runtime": 2.629, |
| "eval_samples_per_second": 0.761, |
| "eval_steps_per_second": 0.38, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 1.2080662250518799, |
| "learning_rate": 4.718583200498814e-06, |
| "loss": 1.2978515625, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6774193548387096, |
| "grad_norm": 0.7336212992668152, |
| "learning_rate": 4.2093854528000955e-06, |
| "loss": 1.388671875, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.7096774193548387, |
| "grad_norm": 0.6965171694755554, |
| "learning_rate": 3.717641052823795e-06, |
| "loss": 1.3662109375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.7419354838709677, |
| "grad_norm": 1.1687854528427124, |
| "learning_rate": 3.2500000000000015e-06, |
| "loss": 1.2197265625, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.7741935483870968, |
| "grad_norm": 1.0150550603866577, |
| "learning_rate": 2.8127863373374637e-06, |
| "loss": 1.2353515625, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.8064516129032258, |
| "grad_norm": 1.0265108346939087, |
| "learning_rate": 2.4119126295906997e-06, |
| "loss": 1.2353515625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.8064516129032258, |
| "eval_loss": 1.19140625, |
| "eval_runtime": 2.622, |
| "eval_samples_per_second": 0.763, |
| "eval_steps_per_second": 0.381, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.8387096774193549, |
| "grad_norm": 0.872216522693634, |
| "learning_rate": 2.0528000059646e-06, |
| "loss": 1.158203125, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.8709677419354839, |
| "grad_norm": 0.6529123783111572, |
| "learning_rate": 1.740304848641787e-06, |
| "loss": 1.31494140625, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.9032258064516129, |
| "grad_norm": 1.0117592811584473, |
| "learning_rate": 1.4786531185446455e-06, |
| "loss": 1.2607421875, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.9354838709677419, |
| "grad_norm": 0.8021711111068726, |
| "learning_rate": 1.2713832064634127e-06, |
| "loss": 1.2509765625, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 0.6989158391952515, |
| "learning_rate": 1.121298082390793e-06, |
| "loss": 1.349609375, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.8156901001930237, |
| "learning_rate": 1.0304273901612566e-06, |
| "loss": 1.11328125, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.17578125, |
| "eval_runtime": 2.6331, |
| "eval_samples_per_second": 0.76, |
| "eval_steps_per_second": 0.38, |
| "step": 31 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 31, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.361719431579566e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
