| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024484299442982187, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004896859888596437, | |
| "grad_norm": 1.2263964414596558, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5135, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004896859888596437, | |
| "eval_loss": 2.948885202407837, | |
| "eval_runtime": 0.2759, | |
| "eval_samples_per_second": 181.249, | |
| "eval_steps_per_second": 47.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009793719777192874, | |
| "grad_norm": 1.2112072706222534, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5855, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014690579665789312, | |
| "grad_norm": 0.9360902309417725, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.6966, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001958743955438575, | |
| "grad_norm": 0.8518800735473633, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7641, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002448429944298219, | |
| "grad_norm": 0.8834726214408875, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.9042, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029381159331578624, | |
| "grad_norm": 0.8616137504577637, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.9161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034278019220175065, | |
| "grad_norm": 0.8168938755989075, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.8557, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00391748791087715, | |
| "grad_norm": 0.8130121231079102, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.8595, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004407173899736794, | |
| "grad_norm": 0.7470634579658508, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.8008, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004896859888596438, | |
| "grad_norm": 1.0472534894943237, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.8381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005386545877456081, | |
| "grad_norm": 1.1647361516952515, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.778, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005876231866315725, | |
| "grad_norm": 1.7423428297042847, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.1016, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0063659178551753685, | |
| "grad_norm": 2.792858600616455, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.7081, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006855603844035013, | |
| "grad_norm": 1.7778291702270508, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.1948, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0073452898328946565, | |
| "grad_norm": 1.1315784454345703, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.4119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0078349758217543, | |
| "grad_norm": 0.7707390785217285, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.3693, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008324661810613945, | |
| "grad_norm": 0.5361566543579102, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.4151, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008814347799473588, | |
| "grad_norm": 0.5095396637916565, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3681, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009304033788333232, | |
| "grad_norm": 0.5492768287658691, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.4018, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009793719777192875, | |
| "grad_norm": 0.6054216027259827, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.5802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010283405766052519, | |
| "grad_norm": 0.696754515171051, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.3895, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010773091754912163, | |
| "grad_norm": 0.7960914373397827, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.5298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011262777743771806, | |
| "grad_norm": 0.8042302131652832, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.5852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01175246373263145, | |
| "grad_norm": 0.8440700769424438, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.4785, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012242149721491093, | |
| "grad_norm": 1.2707189321517944, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.835, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012242149721491093, | |
| "eval_loss": 2.3700783252716064, | |
| "eval_runtime": 0.2842, | |
| "eval_samples_per_second": 175.947, | |
| "eval_steps_per_second": 45.746, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012731835710350737, | |
| "grad_norm": 0.7631580233573914, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.1083, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01322152169921038, | |
| "grad_norm": 0.5331470966339111, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.1472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013711207688070026, | |
| "grad_norm": 0.35138264298439026, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.2704, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01420089367692967, | |
| "grad_norm": 0.3977912962436676, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.3569, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.014690579665789313, | |
| "grad_norm": 0.3736828863620758, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2964, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015180265654648957, | |
| "grad_norm": 0.43734219670295715, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.3422, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0156699516435086, | |
| "grad_norm": 0.44669973850250244, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.4332, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.016159637632368246, | |
| "grad_norm": 0.537625789642334, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.3066, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01664932362122789, | |
| "grad_norm": 0.5136464238166809, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.355, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017139009610087533, | |
| "grad_norm": 0.5538141131401062, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.3112, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017628695598947176, | |
| "grad_norm": 0.6463606357574463, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.4078, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01811838158780682, | |
| "grad_norm": 0.7594169974327087, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.3715, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018608067576666464, | |
| "grad_norm": 0.6575441956520081, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.1358, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019097753565526107, | |
| "grad_norm": 0.5268840789794922, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.0396, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01958743955438575, | |
| "grad_norm": 0.4376309812068939, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.2036, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020077125543245394, | |
| "grad_norm": 0.36531275510787964, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2019, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.020566811532105038, | |
| "grad_norm": 0.3618994355201721, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.258, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02105649752096468, | |
| "grad_norm": 0.40304815769195557, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.238, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.021546183509824325, | |
| "grad_norm": 0.42903730273246765, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.26, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02203586949868397, | |
| "grad_norm": 0.4184610843658447, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2523, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022525555487543612, | |
| "grad_norm": 0.4531133472919464, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.3025, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.023015241476403256, | |
| "grad_norm": 0.4802965819835663, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.2356, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0235049274652629, | |
| "grad_norm": 0.585109531879425, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.1812, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.023994613454122543, | |
| "grad_norm": 0.6771403551101685, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.3029, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.024484299442982187, | |
| "grad_norm": 1.08399498462677, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024484299442982187, | |
| "eval_loss": 2.2547683715820312, | |
| "eval_runtime": 0.2852, | |
| "eval_samples_per_second": 175.287, | |
| "eval_steps_per_second": 45.575, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1375501499170816e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |