| { |
| "best_metric": 0.041570067405700684, |
| "best_model_checkpoint": "./sql_lora_approach_b/checkpoint-34", |
| "epoch": 2.9565217391304346, |
| "eval_steps": 500, |
| "global_step": 34, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08695652173913043, |
| "grad_norm": 1.1549581289291382, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.7303, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.17391304347826086, |
| "grad_norm": 1.1289726495742798, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 1.7252, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 0.934922993183136, |
| "learning_rate": 0.0002, |
| "loss": 1.597, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.34782608695652173, |
| "grad_norm": 0.8451507091522217, |
| "learning_rate": 0.00019981755542233177, |
| "loss": 1.3325, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.9650647640228271, |
| "learning_rate": 0.0001992708874098054, |
| "loss": 1.038, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 1.6881967782974243, |
| "learning_rate": 0.00019836199069471437, |
| "loss": 0.7972, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.6086956521739131, |
| "grad_norm": 0.9939894080162048, |
| "learning_rate": 0.0001970941817426052, |
| "loss": 0.5526, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6956521739130435, |
| "grad_norm": 0.9496100544929504, |
| "learning_rate": 0.00019547208665085457, |
| "loss": 0.3339, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 0.7385075688362122, |
| "learning_rate": 0.0001935016242685415, |
| "loss": 0.1994, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.5156198740005493, |
| "learning_rate": 0.00019118998459920902, |
| "loss": 0.0954, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "grad_norm": 0.3693973124027252, |
| "learning_rate": 0.000188545602565321, |
| "loss": 0.06, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "eval_loss": 0.06161738932132721, |
| "eval_runtime": 16.8375, |
| "eval_samples_per_second": 0.535, |
| "eval_steps_per_second": 0.535, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.0434782608695652, |
| "grad_norm": 0.3475421965122223, |
| "learning_rate": 0.00018557812723014476, |
| "loss": 0.0668, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.1304347826086956, |
| "grad_norm": 0.2272304743528366, |
| "learning_rate": 0.00018229838658936564, |
| "loss": 0.0472, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.2173913043478262, |
| "grad_norm": 0.18348968029022217, |
| "learning_rate": 0.00017871834806090501, |
| "loss": 0.0408, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 0.1996564120054245, |
| "learning_rate": 0.00017485107481711012, |
| "loss": 0.0533, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.391304347826087, |
| "grad_norm": 0.17511172592639923, |
| "learning_rate": 0.00017071067811865476, |
| "loss": 0.042, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.4782608695652173, |
| "grad_norm": 0.14677977561950684, |
| "learning_rate": 0.00016631226582407952, |
| "loss": 0.0318, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.5652173913043477, |
| "grad_norm": 0.19209422171115875, |
| "learning_rate": 0.00016167188726285434, |
| "loss": 0.0478, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.6521739130434783, |
| "grad_norm": 0.222362220287323, |
| "learning_rate": 0.00015680647467311557, |
| "loss": 0.0578, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 0.1985371708869934, |
| "learning_rate": 0.00015173378141776568, |
| "loss": 0.039, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.8260869565217392, |
| "grad_norm": 0.19283267855644226, |
| "learning_rate": 0.00014647231720437686, |
| "loss": 0.0338, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.9130434782608696, |
| "grad_norm": 0.18836742639541626, |
| "learning_rate": 0.0001410412805452757, |
| "loss": 0.0367, |
| "step": 22 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.22117920219898224, |
| "learning_rate": 0.00013546048870425356, |
| "loss": 0.0562, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.042378202080726624, |
| "eval_runtime": 16.8523, |
| "eval_samples_per_second": 0.534, |
| "eval_steps_per_second": 0.534, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0869565217391304, |
| "grad_norm": 0.08625093847513199, |
| "learning_rate": 0.00012975030538552032, |
| "loss": 0.0223, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.1739130434782608, |
| "grad_norm": 0.10370675474405289, |
| "learning_rate": 0.0001239315664287558, |
| "loss": 0.0292, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.260869565217391, |
| "grad_norm": 0.15547294914722443, |
| "learning_rate": 0.0001180255037813906, |
| "loss": 0.0403, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.3478260869565215, |
| "grad_norm": 0.1734398603439331, |
| "learning_rate": 0.0001120536680255323, |
| "loss": 0.0341, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.4347826086956523, |
| "grad_norm": 0.12611858546733856, |
| "learning_rate": 0.00010603784974222861, |
| "loss": 0.025, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.5217391304347827, |
| "grad_norm": 0.11490053683519363, |
| "learning_rate": 0.0001, |
| "loss": 0.0254, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.608695652173913, |
| "grad_norm": 0.11299990862607956, |
| "learning_rate": 9.396215025777139e-05, |
| "loss": 0.0287, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.6956521739130435, |
| "grad_norm": 0.09447255730628967, |
| "learning_rate": 8.79463319744677e-05, |
| "loss": 0.0226, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.782608695652174, |
| "grad_norm": 0.13230058550834656, |
| "learning_rate": 8.197449621860943e-05, |
| "loss": 0.0277, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.869565217391304, |
| "grad_norm": 0.13557763397693634, |
| "learning_rate": 7.606843357124426e-05, |
| "loss": 0.0325, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.9565217391304346, |
| "grad_norm": 0.10920581966638565, |
| "learning_rate": 7.024969461447972e-05, |
| "loss": 0.0219, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.9565217391304346, |
| "eval_loss": 0.041570067405700684, |
| "eval_runtime": 16.9013, |
| "eval_samples_per_second": 0.533, |
| "eval_steps_per_second": 0.533, |
| "step": 34 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 55, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 1208798594408448.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
