AtmicQuoterv1 / trainer_state.json
SriRamanaYash's picture
Upload folder using huggingface_hub
eda9fbc verified
Raw
History Blame Contribute Delete
3.66 kB
{
"best_global_step": 479,
"best_metric": 0.7493041057759224,
"best_model_checkpoint": "runs/atmicquoter_v1/checkpoint-479",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 479,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.10438413361169102,
"grad_norm": 13.321887969970703,
"learning_rate": 1.0208333333333334e-05,
"loss": 1.2508454132080078,
"step": 50
},
{
"epoch": 0.20876826722338204,
"grad_norm": 18.411792755126953,
"learning_rate": 1.9930394431554527e-05,
"loss": 0.6564566802978515,
"step": 100
},
{
"epoch": 0.31315240083507306,
"grad_norm": 14.963032722473145,
"learning_rate": 1.877030162412993e-05,
"loss": 0.47880451202392577,
"step": 150
},
{
"epoch": 0.4175365344467641,
"grad_norm": 7.18877649307251,
"learning_rate": 1.7610208816705337e-05,
"loss": 0.4233243179321289,
"step": 200
},
{
"epoch": 0.5219206680584552,
"grad_norm": 10.051350593566895,
"learning_rate": 1.6450116009280744e-05,
"loss": 0.44428573608398436,
"step": 250
},
{
"epoch": 0.6263048016701461,
"grad_norm": 15.613698959350586,
"learning_rate": 1.529002320185615e-05,
"loss": 0.4010167694091797,
"step": 300
},
{
"epoch": 0.7306889352818372,
"grad_norm": 5.872715473175049,
"learning_rate": 1.4129930394431555e-05,
"loss": 0.35241954803466796,
"step": 350
},
{
"epoch": 0.8350730688935282,
"grad_norm": 7.686646938323975,
"learning_rate": 1.2969837587006962e-05,
"loss": 0.3802318954467773,
"step": 400
},
{
"epoch": 0.9394572025052192,
"grad_norm": 4.72100830078125,
"learning_rate": 1.1809744779582369e-05,
"loss": 0.35252872467041013,
"step": 450
},
{
"epoch": 1.0,
"eval_atmic-val_cosine_accuracy@1": 0.6784968684759917,
"eval_atmic-val_cosine_accuracy@10": 0.930062630480167,
"eval_atmic-val_cosine_accuracy@3": 0.837160751565762,
"eval_atmic-val_cosine_accuracy@5": 0.884133611691023,
"eval_atmic-val_cosine_map@100": 0.7698044826032898,
"eval_atmic-val_cosine_mrr@10": 0.7665548265235117,
"eval_atmic-val_cosine_mrr@3": 0.7493041057759224,
"eval_atmic-val_cosine_ndcg@10": 0.806461348862587,
"eval_atmic-val_cosine_ndcg@3": 0.7719058085781421,
"eval_atmic-val_cosine_precision@1": 0.6784968684759917,
"eval_atmic-val_cosine_precision@10": 0.09300626304801671,
"eval_atmic-val_cosine_precision@3": 0.27905358385525403,
"eval_atmic-val_cosine_precision@5": 0.1768267223382046,
"eval_atmic-val_cosine_recall@1": 0.6784968684759917,
"eval_atmic-val_cosine_recall@10": 0.930062630480167,
"eval_atmic-val_cosine_recall@3": 0.837160751565762,
"eval_atmic-val_cosine_recall@5": 0.884133611691023,
"eval_runtime": 8.8682,
"eval_samples_per_second": 0.0,
"eval_steps_per_second": 0.0,
"step": 479
}
],
"logging_steps": 50,
"max_steps": 958,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"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
}