| { |
| "best_metric": 0.3127017021179199, |
| "best_model_checkpoint": "finetuned_models/qwen-32b-multi-stock-v1_202603051920/checkpoint-54", |
| "epoch": 1.1771117166212535, |
| "eval_steps": 27, |
| "global_step": 54, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.021798365122615803, |
| "grad_norm": 6.165101528167725, |
| "learning_rate": 7.142857142857143e-06, |
| "loss": 17.3071, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.043596730245231606, |
| "grad_norm": 4.365502834320068, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 17.1928, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0653950953678474, |
| "grad_norm": 4.507502555847168, |
| "learning_rate": 2.1428571428571428e-05, |
| "loss": 17.0196, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.08719346049046321, |
| "grad_norm": 4.440822601318359, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 16.5418, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.10899182561307902, |
| "grad_norm": 5.166988849639893, |
| "learning_rate": 3.571428571428572e-05, |
| "loss": 16.7408, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.1307901907356948, |
| "grad_norm": 7.1465654373168945, |
| "learning_rate": 4.2857142857142856e-05, |
| "loss": 16.0273, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.15258855585831063, |
| "grad_norm": 14.216585159301758, |
| "learning_rate": 5e-05, |
| "loss": 14.3316, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.17438692098092642, |
| "grad_norm": 23.32270050048828, |
| "learning_rate": 4.9609375000000005e-05, |
| "loss": 11.1795, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.19618528610354224, |
| "grad_norm": 18.680166244506836, |
| "learning_rate": 4.921875e-05, |
| "loss": 7.61, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.21798365122615804, |
| "grad_norm": 15.084885597229004, |
| "learning_rate": 4.8828125e-05, |
| "loss": 4.6502, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.23978201634877383, |
| "grad_norm": 17.5118408203125, |
| "learning_rate": 4.8437500000000005e-05, |
| "loss": 3.3325, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.2615803814713896, |
| "grad_norm": 10.667753219604492, |
| "learning_rate": 4.8046875e-05, |
| "loss": 2.0176, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.28337874659400547, |
| "grad_norm": 5.880115032196045, |
| "learning_rate": 4.765625e-05, |
| "loss": 1.2728, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.30517711171662126, |
| "grad_norm": 3.440869092941284, |
| "learning_rate": 4.7265625000000005e-05, |
| "loss": 0.9443, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.32697547683923706, |
| "grad_norm": 2.7611007690429688, |
| "learning_rate": 4.6875e-05, |
| "loss": 0.6396, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.34877384196185285, |
| "grad_norm": 1.4035634994506836, |
| "learning_rate": 4.6484375e-05, |
| "loss": 0.5446, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.37057220708446864, |
| "grad_norm": 0.5275142788887024, |
| "learning_rate": 4.609375e-05, |
| "loss": 0.4912, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.3923705722070845, |
| "grad_norm": 0.4913148283958435, |
| "learning_rate": 4.5703125e-05, |
| "loss": 0.5211, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.4141689373297003, |
| "grad_norm": 0.3805868923664093, |
| "learning_rate": 4.5312500000000004e-05, |
| "loss": 0.4556, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.4359673024523161, |
| "grad_norm": 0.32233572006225586, |
| "learning_rate": 4.4921875e-05, |
| "loss": 0.4433, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.45776566757493187, |
| "grad_norm": 0.27392125129699707, |
| "learning_rate": 4.453125e-05, |
| "loss": 0.4108, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.47956403269754766, |
| "grad_norm": 0.4670204818248749, |
| "learning_rate": 4.4140625000000004e-05, |
| "loss": 0.4149, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.5013623978201635, |
| "grad_norm": 0.2106008529663086, |
| "learning_rate": 4.375e-05, |
| "loss": 0.3944, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.5231607629427792, |
| "grad_norm": 0.2013174593448639, |
| "learning_rate": 4.3359375e-05, |
| "loss": 0.3953, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5449591280653951, |
| "grad_norm": 0.1582355797290802, |
| "learning_rate": 4.2968750000000004e-05, |
| "loss": 0.3797, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5667574931880109, |
| "grad_norm": 0.1465764045715332, |
| "learning_rate": 4.2578125e-05, |
| "loss": 0.3854, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.5885558583106267, |
| "grad_norm": 0.12099988013505936, |
| "learning_rate": 4.21875e-05, |
| "loss": 0.3565, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.5885558583106267, |
| "eval_loss": 0.37613359093666077, |
| "eval_runtime": 1238.4482, |
| "eval_samples_per_second": 0.296, |
| "eval_steps_per_second": 0.296, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.6103542234332425, |
| "grad_norm": 0.11796984821557999, |
| "learning_rate": 4.1796875000000005e-05, |
| "loss": 0.3647, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.6321525885558583, |
| "grad_norm": 0.11851071566343307, |
| "learning_rate": 4.140625e-05, |
| "loss": 0.3579, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.6539509536784741, |
| "grad_norm": 0.10708547383546829, |
| "learning_rate": 4.1015625e-05, |
| "loss": 0.3426, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6757493188010899, |
| "grad_norm": 0.09716629981994629, |
| "learning_rate": 4.0625000000000005e-05, |
| "loss": 0.3677, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.6975476839237057, |
| "grad_norm": 0.1687636524438858, |
| "learning_rate": 4.0234375e-05, |
| "loss": 0.3664, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.7193460490463215, |
| "grad_norm": 0.08153154700994492, |
| "learning_rate": 3.984375e-05, |
| "loss": 0.3198, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.7411444141689373, |
| "grad_norm": 0.0886109471321106, |
| "learning_rate": 3.9453125000000005e-05, |
| "loss": 0.3492, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.7629427792915532, |
| "grad_norm": 0.1751064509153366, |
| "learning_rate": 3.90625e-05, |
| "loss": 0.3256, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.784741144414169, |
| "grad_norm": 0.10816111415624619, |
| "learning_rate": 3.8671875e-05, |
| "loss": 0.3453, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.8065395095367848, |
| "grad_norm": 0.10576913505792618, |
| "learning_rate": 3.828125e-05, |
| "loss": 0.3213, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.8283378746594006, |
| "grad_norm": 0.08771315962076187, |
| "learning_rate": 3.7890625e-05, |
| "loss": 0.3487, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.8501362397820164, |
| "grad_norm": 0.07865849882364273, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.3221, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.8719346049046321, |
| "grad_norm": 0.14595365524291992, |
| "learning_rate": 3.7109375e-05, |
| "loss": 0.3374, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8937329700272479, |
| "grad_norm": 0.0940738096833229, |
| "learning_rate": 3.671875e-05, |
| "loss": 0.3233, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.9155313351498637, |
| "grad_norm": 0.07646500319242477, |
| "learning_rate": 3.6328125000000004e-05, |
| "loss": 0.3139, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.9373297002724795, |
| "grad_norm": 0.08323980122804642, |
| "learning_rate": 3.59375e-05, |
| "loss": 0.3265, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.9591280653950953, |
| "grad_norm": 0.09472781419754028, |
| "learning_rate": 3.5546875e-05, |
| "loss": 0.3221, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.9809264305177112, |
| "grad_norm": 0.08437415212392807, |
| "learning_rate": 3.5156250000000004e-05, |
| "loss": 0.3238, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.002724795640327, |
| "grad_norm": 0.09361174702644348, |
| "learning_rate": 3.4765625e-05, |
| "loss": 0.3103, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.0245231607629428, |
| "grad_norm": 0.08738863468170166, |
| "learning_rate": 3.4375e-05, |
| "loss": 0.3167, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.0463215258855585, |
| "grad_norm": 0.1336049884557724, |
| "learning_rate": 3.3984375000000004e-05, |
| "loss": 0.3037, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.0681198910081744, |
| "grad_norm": 0.06754359602928162, |
| "learning_rate": 3.359375e-05, |
| "loss": 0.3083, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.0899182561307903, |
| "grad_norm": 0.07606881111860275, |
| "learning_rate": 3.3203125e-05, |
| "loss": 0.322, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.111716621253406, |
| "grad_norm": 0.0796089842915535, |
| "learning_rate": 3.2812500000000005e-05, |
| "loss": 0.3162, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.1335149863760219, |
| "grad_norm": 0.0840163454413414, |
| "learning_rate": 3.2421875e-05, |
| "loss": 0.3241, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.1553133514986376, |
| "grad_norm": 0.0950520932674408, |
| "learning_rate": 3.203125e-05, |
| "loss": 0.3083, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.1771117166212535, |
| "grad_norm": 0.0708131417632103, |
| "learning_rate": 3.1640625e-05, |
| "loss": 0.3309, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.1771117166212535, |
| "eval_loss": 0.3127017021179199, |
| "eval_runtime": 1234.7377, |
| "eval_samples_per_second": 0.297, |
| "eval_steps_per_second": 0.297, |
| "step": 54 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 135, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 27, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.140162772225024e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
