| { |
| "best_global_step": 955, |
| "best_metric": 0.3973127603530884, |
| "best_model_checkpoint": "finbert_model/checkpoint-955", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 955, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02617801047120419, |
| "grad_norm": 5.389065742492676, |
| "learning_rate": 1.9832460732984295e-05, |
| "loss": 1.0684, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.05235602094240838, |
| "grad_norm": 10.32921314239502, |
| "learning_rate": 1.9657940663176267e-05, |
| "loss": 0.7284, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.07853403141361257, |
| "grad_norm": 6.734121322631836, |
| "learning_rate": 1.948342059336824e-05, |
| "loss": 0.7981, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.10471204188481675, |
| "grad_norm": 8.204632759094238, |
| "learning_rate": 1.930890052356021e-05, |
| "loss": 0.5878, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.13089005235602094, |
| "grad_norm": 10.211732864379883, |
| "learning_rate": 1.9134380453752185e-05, |
| "loss": 0.7182, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.15706806282722513, |
| "grad_norm": 9.390113830566406, |
| "learning_rate": 1.8959860383944157e-05, |
| "loss": 0.72, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.18324607329842932, |
| "grad_norm": 11.717000007629395, |
| "learning_rate": 1.8785340314136128e-05, |
| "loss": 0.6367, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.2094240837696335, |
| "grad_norm": 8.935040473937988, |
| "learning_rate": 1.86108202443281e-05, |
| "loss": 0.6106, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2356020942408377, |
| "grad_norm": 11.59050464630127, |
| "learning_rate": 1.843630017452007e-05, |
| "loss": 0.6202, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2617801047120419, |
| "grad_norm": 7.747163772583008, |
| "learning_rate": 1.8261780104712043e-05, |
| "loss": 0.669, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2879581151832461, |
| "grad_norm": 16.7243595123291, |
| "learning_rate": 1.8087260034904015e-05, |
| "loss": 0.4931, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.31413612565445026, |
| "grad_norm": 7.23421049118042, |
| "learning_rate": 1.7912739965095986e-05, |
| "loss": 0.5974, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3403141361256545, |
| "grad_norm": 6.768913269042969, |
| "learning_rate": 1.773821989528796e-05, |
| "loss": 0.4926, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.36649214659685864, |
| "grad_norm": 3.186237096786499, |
| "learning_rate": 1.7563699825479933e-05, |
| "loss": 0.4709, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.39267015706806285, |
| "grad_norm": 12.499926567077637, |
| "learning_rate": 1.7389179755671904e-05, |
| "loss": 0.5128, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.418848167539267, |
| "grad_norm": 8.35361099243164, |
| "learning_rate": 1.7214659685863876e-05, |
| "loss": 0.5878, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.44502617801047123, |
| "grad_norm": 6.956220626831055, |
| "learning_rate": 1.7040139616055848e-05, |
| "loss": 0.4794, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.4712041884816754, |
| "grad_norm": 15.914446830749512, |
| "learning_rate": 1.686561954624782e-05, |
| "loss": 0.5827, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4973821989528796, |
| "grad_norm": 15.149320602416992, |
| "learning_rate": 1.669109947643979e-05, |
| "loss": 0.5467, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.5235602094240838, |
| "grad_norm": 10.100659370422363, |
| "learning_rate": 1.6516579406631763e-05, |
| "loss": 0.525, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5497382198952879, |
| "grad_norm": 8.821247100830078, |
| "learning_rate": 1.6342059336823738e-05, |
| "loss": 0.5345, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.5759162303664922, |
| "grad_norm": 14.301637649536133, |
| "learning_rate": 1.616753926701571e-05, |
| "loss": 0.5115, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.6020942408376964, |
| "grad_norm": 14.779314994812012, |
| "learning_rate": 1.599301919720768e-05, |
| "loss": 0.5034, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.6282722513089005, |
| "grad_norm": 9.956971168518066, |
| "learning_rate": 1.5818499127399652e-05, |
| "loss": 0.3719, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6544502617801047, |
| "grad_norm": 17.58684730529785, |
| "learning_rate": 1.5643979057591624e-05, |
| "loss": 0.5269, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.680628272251309, |
| "grad_norm": 10.585662841796875, |
| "learning_rate": 1.5469458987783596e-05, |
| "loss": 0.574, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.7068062827225131, |
| "grad_norm": 17.19683074951172, |
| "learning_rate": 1.5294938917975567e-05, |
| "loss": 0.4294, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.7329842931937173, |
| "grad_norm": 14.906782150268555, |
| "learning_rate": 1.5120418848167539e-05, |
| "loss": 0.4861, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7591623036649214, |
| "grad_norm": 12.943304061889648, |
| "learning_rate": 1.4945898778359514e-05, |
| "loss": 0.4121, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.7853403141361257, |
| "grad_norm": 0.5662004351615906, |
| "learning_rate": 1.4771378708551485e-05, |
| "loss": 0.5198, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.8115183246073299, |
| "grad_norm": 7.927789211273193, |
| "learning_rate": 1.4596858638743457e-05, |
| "loss": 0.4721, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.837696335078534, |
| "grad_norm": 6.3558855056762695, |
| "learning_rate": 1.4422338568935429e-05, |
| "loss": 0.3977, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8638743455497382, |
| "grad_norm": 17.170700073242188, |
| "learning_rate": 1.4247818499127402e-05, |
| "loss": 0.3493, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.8900523560209425, |
| "grad_norm": 15.060056686401367, |
| "learning_rate": 1.4073298429319373e-05, |
| "loss": 0.5364, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.9162303664921466, |
| "grad_norm": 11.084234237670898, |
| "learning_rate": 1.3898778359511345e-05, |
| "loss": 0.4815, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.9424083769633508, |
| "grad_norm": 11.328404426574707, |
| "learning_rate": 1.3724258289703317e-05, |
| "loss": 0.5914, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.9685863874345549, |
| "grad_norm": 14.335894584655762, |
| "learning_rate": 1.354973821989529e-05, |
| "loss": 0.4111, |
| "step": 925 |
| }, |
| { |
| "epoch": 0.9947643979057592, |
| "grad_norm": 11.200068473815918, |
| "learning_rate": 1.3375218150087262e-05, |
| "loss": 0.4069, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8690413829229964, |
| "eval_f1": 0.8665004404377881, |
| "eval_loss": 0.3973127603530884, |
| "eval_runtime": 4.1083, |
| "eval_samples_per_second": 464.669, |
| "eval_steps_per_second": 58.175, |
| "step": 955 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2865, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 502151957733888.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
