| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11584077323716135, |
| "eval_steps": 800, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.007240048327322585, |
| "grad_norm": 2.589949131011963, |
| "learning_rate": 1.4182344428364688e-06, |
| "loss": 0.0428, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01448009665464517, |
| "grad_norm": 10.996792793273926, |
| "learning_rate": 2.8654124457308254e-06, |
| "loss": 0.0118, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.021720144981967754, |
| "grad_norm": 1.4595743417739868, |
| "learning_rate": 4.3125904486251816e-06, |
| "loss": 0.0087, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02896019330929034, |
| "grad_norm": 1.1282789707183838, |
| "learning_rate": 5.759768451519537e-06, |
| "loss": 0.0064, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03620024163661292, |
| "grad_norm": 6.456222057342529, |
| "learning_rate": 7.206946454413893e-06, |
| "loss": 0.0069, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.04344028996393551, |
| "grad_norm": 0.03427216783165932, |
| "learning_rate": 8.65412445730825e-06, |
| "loss": 0.0088, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.05068033829125809, |
| "grad_norm": 1.5523200035095215, |
| "learning_rate": 1.0101302460202607e-05, |
| "loss": 0.0055, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.05792038661858068, |
| "grad_norm": 0.37769994139671326, |
| "learning_rate": 1.1548480463096963e-05, |
| "loss": 0.0067, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.06516043494590326, |
| "grad_norm": 0.15266789495944977, |
| "learning_rate": 1.2995658465991319e-05, |
| "loss": 0.0098, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.07240048327322585, |
| "grad_norm": 0.2500436305999756, |
| "learning_rate": 1.4442836468885674e-05, |
| "loss": 0.0096, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.07964053160054843, |
| "grad_norm": 0.6040284037590027, |
| "learning_rate": 1.5890014471780032e-05, |
| "loss": 0.0104, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.08688057992787102, |
| "grad_norm": 8.891999244689941, |
| "learning_rate": 1.7337192474674386e-05, |
| "loss": 0.0155, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.0941206282551936, |
| "grad_norm": 0.25315049290657043, |
| "learning_rate": 1.8784370477568743e-05, |
| "loss": 0.0109, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.10136067658251618, |
| "grad_norm": 8.926114082336426, |
| "learning_rate": 1.9974259974259977e-05, |
| "loss": 0.0144, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.10860072490983877, |
| "grad_norm": 4.814042091369629, |
| "learning_rate": 1.9813384813384816e-05, |
| "loss": 0.0109, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.11584077323716135, |
| "grad_norm": 1.084911823272705, |
| "learning_rate": 1.9652509652509656e-05, |
| "loss": 0.0107, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.11584077323716135, |
| "eval_dev-eval_cosine_accuracy@1": 0.308, |
| "eval_dev-eval_cosine_accuracy@10": 0.585, |
| "eval_dev-eval_cosine_accuracy@3": 0.437, |
| "eval_dev-eval_cosine_accuracy@5": 0.507, |
| "eval_dev-eval_cosine_map@100": 0.3994706245247452, |
| "eval_dev-eval_cosine_mrr@10": 0.39167420634920597, |
| "eval_dev-eval_cosine_ndcg@10": 0.43779247661127096, |
| "eval_dev-eval_cosine_precision@1": 0.308, |
| "eval_dev-eval_cosine_precision@10": 0.0585, |
| "eval_dev-eval_cosine_precision@3": 0.1456666666666667, |
| "eval_dev-eval_cosine_precision@5": 0.10139999999999998, |
| "eval_dev-eval_cosine_recall@1": 0.308, |
| "eval_dev-eval_cosine_recall@10": 0.585, |
| "eval_dev-eval_cosine_recall@3": 0.437, |
| "eval_dev-eval_cosine_recall@5": 0.507, |
| "eval_loss": 0.0, |
| "eval_runtime": 20003.9509, |
| "eval_samples_per_second": 5.524, |
| "eval_steps_per_second": 5.524, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 6907, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 800, |
| "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": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
