| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.04479684630202034, |
| "eval_steps": 1000, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.002239842315101017, |
| "grad_norm": 71.10852813720703, |
| "learning_rate": 0.0001, |
| "loss": 3.5057, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.004479684630202034, |
| "grad_norm": 57.756534576416016, |
| "learning_rate": 9.9998756572327e-05, |
| "loss": 0.8254, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.006719526945303051, |
| "grad_norm": 44.61080551147461, |
| "learning_rate": 9.999502635115246e-05, |
| "loss": 0.6935, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.008959369260404068, |
| "grad_norm": 50.82619094848633, |
| "learning_rate": 9.998880952200681e-05, |
| "loss": 0.5972, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.011199211575505085, |
| "grad_norm": 44.26677703857422, |
| "learning_rate": 9.998010639409713e-05, |
| "loss": 0.5408, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.013439053890606102, |
| "grad_norm": 42.8045654296875, |
| "learning_rate": 9.996891740029186e-05, |
| "loss": 0.5509, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.01567889620570712, |
| "grad_norm": 30.989139556884766, |
| "learning_rate": 9.995524309709913e-05, |
| "loss": 0.4823, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.017918738520808136, |
| "grad_norm": 34.01952362060547, |
| "learning_rate": 9.993908416463927e-05, |
| "loss": 0.5111, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.020158580835909153, |
| "grad_norm": 34.079307556152344, |
| "learning_rate": 9.992044140661079e-05, |
| "loss": 0.4635, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.02239842315101017, |
| "grad_norm": 26.16071128845215, |
| "learning_rate": 9.989931575025056e-05, |
| "loss": 0.4883, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.02239842315101017, |
| "eval_avg_non_pair_similarity": 0.0020343252948339737, |
| "eval_avg_pair_similarity": 0.008852629057131708, |
| "eval_loss": 0.5431402921676636, |
| "eval_runtime": 19.6178, |
| "eval_samples_per_second": 25.487, |
| "eval_similarity_ratio": 4.35162905343228, |
| "eval_steps_per_second": 0.816, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.024638265466111187, |
| "grad_norm": 35.38695526123047, |
| "learning_rate": 9.987570824628759e-05, |
| "loss": 0.4655, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.026878107781212204, |
| "grad_norm": 32.071346282958984, |
| "learning_rate": 9.984962006889084e-05, |
| "loss": 0.4342, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.029117950096313218, |
| "grad_norm": 39.6610221862793, |
| "learning_rate": 9.982105251561082e-05, |
| "loss": 0.458, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.03135779241141424, |
| "grad_norm": 31.493322372436523, |
| "learning_rate": 9.979000700731491e-05, |
| "loss": 0.4525, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.03359763472651525, |
| "grad_norm": 34.453399658203125, |
| "learning_rate": 9.975648508811693e-05, |
| "loss": 0.41, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.03583747704161627, |
| "grad_norm": 33.990074157714844, |
| "learning_rate": 9.972048842530012e-05, |
| "loss": 0.4097, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.038077319356717286, |
| "grad_norm": 30.44228172302246, |
| "learning_rate": 9.968201880923439e-05, |
| "loss": 0.4257, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.040317161671818307, |
| "grad_norm": 31.427162170410156, |
| "learning_rate": 9.964107815328711e-05, |
| "loss": 0.3821, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.04255700398691932, |
| "grad_norm": 25.877887725830078, |
| "learning_rate": 9.959766849372808e-05, |
| "loss": 0.3788, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.04479684630202034, |
| "grad_norm": 25.36798095703125, |
| "learning_rate": 9.955179198962817e-05, |
| "loss": 0.3854, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.04479684630202034, |
| "eval_avg_non_pair_similarity": 0.0016289287904792565, |
| "eval_avg_pair_similarity": 0.0032495629731565715, |
| "eval_loss": 0.4394480586051941, |
| "eval_runtime": 19.5064, |
| "eval_samples_per_second": 25.633, |
| "eval_similarity_ratio": 1.9949079371360972, |
| "eval_steps_per_second": 0.82, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 44646, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "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": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
