| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11323641928079571, |
| "eval_steps": 5, |
| "global_step": 37, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00306044376434583, |
| "eval_loss": 1.1051609516143799, |
| "eval_runtime": 26.5057, |
| "eval_samples_per_second": 5.206, |
| "eval_steps_per_second": 2.603, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.009181331293037491, |
| "grad_norm": 0.49553486704826355, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.0599, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.015302218821729151, |
| "eval_loss": 1.0945595502853394, |
| "eval_runtime": 25.9873, |
| "eval_samples_per_second": 5.31, |
| "eval_steps_per_second": 2.655, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.018362662586074982, |
| "grad_norm": 0.5389537811279297, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.1064, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.02754399387911247, |
| "grad_norm": 0.4423370361328125, |
| "learning_rate": 0.0001, |
| "loss": 0.975, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.030604437643458302, |
| "eval_loss": 0.9807908535003662, |
| "eval_runtime": 25.9978, |
| "eval_samples_per_second": 5.308, |
| "eval_steps_per_second": 2.654, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.036725325172149964, |
| "grad_norm": 0.6366612315177917, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 0.9206, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.045906656465187455, |
| "grad_norm": 0.6869972944259644, |
| "learning_rate": 0.0001666666666666667, |
| "loss": 0.8698, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.045906656465187455, |
| "eval_loss": 0.8133208751678467, |
| "eval_runtime": 25.9999, |
| "eval_samples_per_second": 5.308, |
| "eval_steps_per_second": 2.654, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.05508798775822494, |
| "grad_norm": 0.7443881034851074, |
| "learning_rate": 0.0002, |
| "loss": 0.7708, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.061208875286916604, |
| "eval_loss": 0.7175387144088745, |
| "eval_runtime": 26.0285, |
| "eval_samples_per_second": 5.302, |
| "eval_steps_per_second": 2.651, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06426931905126243, |
| "grad_norm": 0.667968213558197, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 0.7045, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.07345065034429993, |
| "grad_norm": 0.618311882019043, |
| "learning_rate": 0.00015469481581224272, |
| "loss": 0.6921, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.07651109410864575, |
| "eval_loss": 0.6743873953819275, |
| "eval_runtime": 26.0301, |
| "eval_samples_per_second": 5.302, |
| "eval_steps_per_second": 2.651, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.08263198163733741, |
| "grad_norm": 0.48745396733283997, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 0.6098, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.09181331293037491, |
| "grad_norm": 0.530785083770752, |
| "learning_rate": 5.983045753470308e-05, |
| "loss": 0.611, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09181331293037491, |
| "eval_loss": 0.6592618227005005, |
| "eval_runtime": 26.2376, |
| "eval_samples_per_second": 5.26, |
| "eval_steps_per_second": 2.63, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1009946442234124, |
| "grad_norm": 0.5798205733299255, |
| "learning_rate": 2.1085949060360654e-05, |
| "loss": 0.7136, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.10711553175210406, |
| "eval_loss": 0.6530157923698425, |
| "eval_runtime": 26.1128, |
| "eval_samples_per_second": 5.285, |
| "eval_steps_per_second": 2.642, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.11017597551644988, |
| "grad_norm": 0.5891212821006775, |
| "learning_rate": 1.3638696597277679e-06, |
| "loss": 0.6765, |
| "step": 36 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 37, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 18, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3779253648687104e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
