|
{ |
|
"best_metric": 1.0433918237686157, |
|
"best_model_checkpoint": "autotrain-khjb3-w8jbx/checkpoint-474", |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 474, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.10548523206751055, |
|
"grad_norm": 34.03109359741211, |
|
"learning_rate": 1.0416666666666666e-05, |
|
"loss": 2.4397, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.2109704641350211, |
|
"grad_norm": 90.00489807128906, |
|
"learning_rate": 2.0833333333333333e-05, |
|
"loss": 1.986, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.31645569620253167, |
|
"grad_norm": 26.834562301635742, |
|
"learning_rate": 2.9859154929577468e-05, |
|
"loss": 1.881, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.4219409282700422, |
|
"grad_norm": 19.74114418029785, |
|
"learning_rate": 2.8685446009389673e-05, |
|
"loss": 1.8105, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.5274261603375527, |
|
"grad_norm": 22.13190460205078, |
|
"learning_rate": 2.751173708920188e-05, |
|
"loss": 1.7378, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.6329113924050633, |
|
"grad_norm": 20.573028564453125, |
|
"learning_rate": 2.6338028169014085e-05, |
|
"loss": 1.5942, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.7383966244725738, |
|
"grad_norm": 30.517986297607422, |
|
"learning_rate": 2.5164319248826293e-05, |
|
"loss": 1.4586, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.8438818565400844, |
|
"grad_norm": 23.457304000854492, |
|
"learning_rate": 2.3990610328638498e-05, |
|
"loss": 1.3904, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.9493670886075949, |
|
"grad_norm": 31.64182472229004, |
|
"learning_rate": 2.2816901408450703e-05, |
|
"loss": 1.4707, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.3109228610992432, |
|
"eval_runtime": 60.4201, |
|
"eval_samples_per_second": 2.714, |
|
"eval_steps_per_second": 0.182, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 1.0548523206751055, |
|
"grad_norm": 24.206829071044922, |
|
"learning_rate": 2.164319248826291e-05, |
|
"loss": 1.234, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.160337552742616, |
|
"grad_norm": 15.992789268493652, |
|
"learning_rate": 2.0469483568075116e-05, |
|
"loss": 1.1867, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 1.2658227848101267, |
|
"grad_norm": 38.054229736328125, |
|
"learning_rate": 1.9295774647887324e-05, |
|
"loss": 1.0103, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.371308016877637, |
|
"grad_norm": 23.401416778564453, |
|
"learning_rate": 1.812206572769953e-05, |
|
"loss": 1.088, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.4767932489451476, |
|
"grad_norm": 16.83168601989746, |
|
"learning_rate": 1.694835680751174e-05, |
|
"loss": 1.1066, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.5822784810126582, |
|
"grad_norm": 25.251529693603516, |
|
"learning_rate": 1.5774647887323945e-05, |
|
"loss": 1.049, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.6877637130801688, |
|
"grad_norm": 14.522319793701172, |
|
"learning_rate": 1.460093896713615e-05, |
|
"loss": 1.0639, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.7932489451476794, |
|
"grad_norm": 28.719419479370117, |
|
"learning_rate": 1.3427230046948357e-05, |
|
"loss": 1.1133, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.8987341772151898, |
|
"grad_norm": 23.55721664428711, |
|
"learning_rate": 1.2253521126760564e-05, |
|
"loss": 0.9188, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.0433918237686157, |
|
"eval_runtime": 63.4764, |
|
"eval_samples_per_second": 2.584, |
|
"eval_steps_per_second": 0.173, |
|
"step": 474 |
|
} |
|
], |
|
"logging_steps": 25, |
|
"max_steps": 711, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"early_stopping_threshold": 0.01 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|