|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.6855184233076264, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.013710368466152529, |
|
"grad_norm": 0.710936427116394, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0758, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.013710368466152529, |
|
"eval_loss": 2.061342716217041, |
|
"eval_runtime": 3.9437, |
|
"eval_samples_per_second": 12.679, |
|
"eval_steps_per_second": 3.296, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.027420736932305057, |
|
"grad_norm": 0.8320467472076416, |
|
"learning_rate": 0.0001, |
|
"loss": 1.1469, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04113110539845758, |
|
"grad_norm": 0.7723894119262695, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 1.1238, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.054841473864610114, |
|
"grad_norm": 0.9301310777664185, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 1.0834, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.06855184233076264, |
|
"grad_norm": 0.7016130685806274, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 1.1492, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08226221079691516, |
|
"grad_norm": 1.1457853317260742, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 1.1118, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0959725792630677, |
|
"grad_norm": 1.1349098682403564, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 1.19, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.10968294772922023, |
|
"grad_norm": 0.9559301137924194, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 1.0589, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.12339331619537275, |
|
"grad_norm": 1.8211188316345215, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 1.1746, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.13710368466152528, |
|
"grad_norm": 1.5976638793945312, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 1.1548, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.15081405312767782, |
|
"grad_norm": 1.985264778137207, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 1.2768, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.16452442159383032, |
|
"grad_norm": 2.735917568206787, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 1.3655, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.17823479005998286, |
|
"grad_norm": 0.7363784909248352, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.9593, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.1919451585261354, |
|
"grad_norm": 0.7441702485084534, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.8904, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.20565552699228792, |
|
"grad_norm": 0.5978178381919861, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.9095, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.21936589545844046, |
|
"grad_norm": 0.47444233298301697, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.887, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.23307626392459296, |
|
"grad_norm": 0.4872004985809326, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.9216, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.2467866323907455, |
|
"grad_norm": 0.6350117921829224, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.9977, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.26049700085689803, |
|
"grad_norm": 0.693742036819458, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.9968, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.27420736932305056, |
|
"grad_norm": 0.6729600429534912, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.9535, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2879177377892031, |
|
"grad_norm": 0.731232225894928, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.9938, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.30162810625535563, |
|
"grad_norm": 1.0316616296768188, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 1.0353, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.31533847472150817, |
|
"grad_norm": 1.3064064979553223, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.985, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.32904884318766064, |
|
"grad_norm": 1.7107923030853271, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 1.1319, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.3427592116538132, |
|
"grad_norm": 2.4135003089904785, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 1.0646, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.3427592116538132, |
|
"eval_loss": 1.0578700304031372, |
|
"eval_runtime": 4.0436, |
|
"eval_samples_per_second": 12.365, |
|
"eval_steps_per_second": 3.215, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.3564695801199657, |
|
"grad_norm": 0.4161844551563263, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.859, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.37017994858611825, |
|
"grad_norm": 0.4057946801185608, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.8209, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.3838903170522708, |
|
"grad_norm": 0.45725005865097046, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.8762, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.3976006855184233, |
|
"grad_norm": 0.5133175849914551, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.8786, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.41131105398457585, |
|
"grad_norm": 0.6212847232818604, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.9259, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.4250214224507284, |
|
"grad_norm": 0.6563170552253723, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.9841, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.4387317909168809, |
|
"grad_norm": 0.6918400526046753, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.9366, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.4524421593830334, |
|
"grad_norm": 0.7071172595024109, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.9409, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.4661525278491859, |
|
"grad_norm": 0.9048558473587036, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.9652, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.47986289631533846, |
|
"grad_norm": 1.1677721738815308, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.9168, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.493573264781491, |
|
"grad_norm": 2.0543811321258545, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 1.0244, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.5072836332476436, |
|
"grad_norm": 1.9809794425964355, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.957, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.5209940017137961, |
|
"grad_norm": 0.4107670485973358, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.9078, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.5347043701799485, |
|
"grad_norm": 0.2933681607246399, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.8194, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.5484147386461011, |
|
"grad_norm": 0.3296855688095093, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.7945, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5621251071122536, |
|
"grad_norm": 0.36227262020111084, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.851, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.5758354755784062, |
|
"grad_norm": 0.4559353291988373, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.897, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.5895458440445587, |
|
"grad_norm": 0.45754337310791016, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.8841, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.6032562125107113, |
|
"grad_norm": 0.5436176657676697, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.9113, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.6169665809768637, |
|
"grad_norm": 0.6519604325294495, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.9513, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.6306769494430163, |
|
"grad_norm": 0.6538817286491394, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.9248, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.6443873179091688, |
|
"grad_norm": 0.8654205203056335, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.9545, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.6580976863753213, |
|
"grad_norm": 1.1048208475112915, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 1.0274, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.6718080548414739, |
|
"grad_norm": 1.4500497579574585, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 1.0133, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.6855184233076264, |
|
"grad_norm": 1.932473063468933, |
|
"learning_rate": 1e-05, |
|
"loss": 0.8543, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.6855184233076264, |
|
"eval_loss": 0.9967225790023804, |
|
"eval_runtime": 4.0537, |
|
"eval_samples_per_second": 12.335, |
|
"eval_steps_per_second": 3.207, |
|
"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": 6.174479344467968e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|