|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0023535410987114364, |
|
"eval_steps": 5, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 7.845136995704788e-05, |
|
"eval_loss": 2.1316537857055664, |
|
"eval_runtime": 398.2803, |
|
"eval_samples_per_second": 13.478, |
|
"eval_steps_per_second": 6.739, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00023535410987114363, |
|
"grad_norm": 1.5519322156906128, |
|
"learning_rate": 3e-05, |
|
"loss": 2.1763, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00039225684978523936, |
|
"eval_loss": 2.100531816482544, |
|
"eval_runtime": 397.8053, |
|
"eval_samples_per_second": 13.494, |
|
"eval_steps_per_second": 6.747, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00047070821974228727, |
|
"grad_norm": 1.0145130157470703, |
|
"learning_rate": 6e-05, |
|
"loss": 2.0835, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0007060623296134309, |
|
"grad_norm": 0.7395471930503845, |
|
"learning_rate": 9e-05, |
|
"loss": 2.0064, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0007845136995704787, |
|
"eval_loss": 1.954451560974121, |
|
"eval_runtime": 397.9486, |
|
"eval_samples_per_second": 13.489, |
|
"eval_steps_per_second": 6.745, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0009414164394845745, |
|
"grad_norm": 0.9870898127555847, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 1.9395, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0011767705493557182, |
|
"grad_norm": 0.6839460134506226, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.8902, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0011767705493557182, |
|
"eval_loss": 1.8211544752120972, |
|
"eval_runtime": 397.5395, |
|
"eval_samples_per_second": 13.503, |
|
"eval_steps_per_second": 6.752, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0014121246592268617, |
|
"grad_norm": 0.7939899563789368, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 1.6145, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0015690273991409574, |
|
"eval_loss": 1.722493290901184, |
|
"eval_runtime": 398.2577, |
|
"eval_samples_per_second": 13.479, |
|
"eval_steps_per_second": 6.739, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0016474787690980053, |
|
"grad_norm": 0.8007903099060059, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 1.7372, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.001882832878969149, |
|
"grad_norm": 1.1209689378738403, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 1.6574, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0019612842489261967, |
|
"eval_loss": 1.6789103746414185, |
|
"eval_runtime": 398.2796, |
|
"eval_samples_per_second": 13.478, |
|
"eval_steps_per_second": 6.739, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.002118186988840293, |
|
"grad_norm": 0.8475488424301147, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 1.6364, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0023535410987114364, |
|
"grad_norm": 0.7514108419418335, |
|
"learning_rate": 0.0, |
|
"loss": 1.6479, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0023535410987114364, |
|
"eval_loss": 1.6707888841629028, |
|
"eval_runtime": 398.2873, |
|
"eval_samples_per_second": 13.478, |
|
"eval_steps_per_second": 6.739, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 30, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.2819192562581504e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|