|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.8154943934760448, |
|
"eval_steps": 13, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0163098878695209, |
|
"grad_norm": 1.024299144744873, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0301, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0163098878695209, |
|
"eval_loss": 1.1028916835784912, |
|
"eval_runtime": 37.9426, |
|
"eval_samples_per_second": 10.885, |
|
"eval_steps_per_second": 2.741, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0326197757390418, |
|
"grad_norm": 1.0952816009521484, |
|
"learning_rate": 0.0001, |
|
"loss": 1.0255, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04892966360856269, |
|
"grad_norm": 0.874853789806366, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 1.005, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0652395514780836, |
|
"grad_norm": 0.7411254048347473, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 0.9346, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08154943934760449, |
|
"grad_norm": 0.737731397151947, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.8497, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09785932721712538, |
|
"grad_norm": 0.7540619969367981, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 0.8999, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.11416921508664628, |
|
"grad_norm": 0.6454194784164429, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 0.7982, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.1304791029561672, |
|
"grad_norm": 0.5729678273200989, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.821, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.14678899082568808, |
|
"grad_norm": 0.5690068602561951, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.7976, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.16309887869520898, |
|
"grad_norm": 0.524340033531189, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.84, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.17940876656472987, |
|
"grad_norm": 0.47216275334358215, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.8479, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.19571865443425077, |
|
"grad_norm": 0.4617241621017456, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.791, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.21202854230377166, |
|
"grad_norm": 0.5128786563873291, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.8122, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.21202854230377166, |
|
"eval_loss": 0.8193792104721069, |
|
"eval_runtime": 38.0332, |
|
"eval_samples_per_second": 10.859, |
|
"eval_steps_per_second": 2.734, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.22833843017329256, |
|
"grad_norm": 0.5429165959358215, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.8139, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.24464831804281345, |
|
"grad_norm": 0.44588130712509155, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.7791, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.2609582059123344, |
|
"grad_norm": 0.4463639259338379, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.8165, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.27726809378185524, |
|
"grad_norm": 0.5119205713272095, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.7869, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.29357798165137616, |
|
"grad_norm": 0.4943891763687134, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.7749, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.30988786952089703, |
|
"grad_norm": 0.41848573088645935, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.8104, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.32619775739041795, |
|
"grad_norm": 0.5443288087844849, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.8394, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.3425076452599388, |
|
"grad_norm": 0.43257173895835876, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.8379, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.35881753312945974, |
|
"grad_norm": 0.5105078220367432, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.7741, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.3751274209989806, |
|
"grad_norm": 0.4616767466068268, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.7985, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.39143730886850153, |
|
"grad_norm": 0.41591593623161316, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.7988, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.4077471967380224, |
|
"grad_norm": 0.4813802242279053, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.7526, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.4240570846075433, |
|
"grad_norm": 0.4680293798446655, |
|
"learning_rate": 5e-05, |
|
"loss": 0.7901, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.4240570846075433, |
|
"eval_loss": 0.7714418172836304, |
|
"eval_runtime": 38.5188, |
|
"eval_samples_per_second": 10.722, |
|
"eval_steps_per_second": 2.7, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.44036697247706424, |
|
"grad_norm": 0.4302608072757721, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 0.7152, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.4566768603465851, |
|
"grad_norm": 0.3711889386177063, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 0.7525, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.47298674821610603, |
|
"grad_norm": 0.47885867953300476, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.7355, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.4892966360856269, |
|
"grad_norm": 0.4034803807735443, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.8054, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.5056065239551478, |
|
"grad_norm": 0.455782026052475, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 0.7633, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.5219164118246687, |
|
"grad_norm": 0.5047242045402527, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.796, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.5382262996941896, |
|
"grad_norm": 0.3796207010746002, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 0.7821, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.5545361875637105, |
|
"grad_norm": 0.41559967398643494, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.7876, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.5708460754332314, |
|
"grad_norm": 0.44059449434280396, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.7923, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.5871559633027523, |
|
"grad_norm": 0.44257858395576477, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.7218, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.6034658511722731, |
|
"grad_norm": 0.36089643836021423, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 0.7391, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.6197757390417941, |
|
"grad_norm": 0.41137370467185974, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.8426, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.636085626911315, |
|
"grad_norm": 0.4219225347042084, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 0.7719, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.636085626911315, |
|
"eval_loss": 0.7565998435020447, |
|
"eval_runtime": 38.0072, |
|
"eval_samples_per_second": 10.866, |
|
"eval_steps_per_second": 2.736, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.6523955147808359, |
|
"grad_norm": 0.4775455594062805, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.7349, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.6687054026503568, |
|
"grad_norm": 0.38767868280410767, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.7301, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.6850152905198776, |
|
"grad_norm": 0.41658639907836914, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.746, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.7013251783893986, |
|
"grad_norm": 0.4417034685611725, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 0.6826, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.7176350662589195, |
|
"grad_norm": 0.4221656322479248, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.7321, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.7339449541284404, |
|
"grad_norm": 0.46607765555381775, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 0.7588, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.7502548419979612, |
|
"grad_norm": 0.4196472465991974, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.7583, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.7665647298674821, |
|
"grad_norm": 0.4299370050430298, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.7796, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.7828746177370031, |
|
"grad_norm": 0.4492173492908478, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 0.7992, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.799184505606524, |
|
"grad_norm": 0.47522222995758057, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 0.7723, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.8154943934760448, |
|
"grad_norm": 0.3986295461654663, |
|
"learning_rate": 0.0, |
|
"loss": 0.7772, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 13, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.1250078421352448e+18, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|