|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.7094017094017095, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03418803418803419, |
|
"grad_norm": 0.2997426986694336, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9476, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03418803418803419, |
|
"eval_loss": 1.2048848867416382, |
|
"eval_runtime": 3.4576, |
|
"eval_samples_per_second": 14.461, |
|
"eval_steps_per_second": 3.76, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.06837606837606838, |
|
"grad_norm": 0.39732587337493896, |
|
"learning_rate": 0.0001, |
|
"loss": 1.0399, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.10256410256410256, |
|
"grad_norm": 0.41230157017707825, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 1.0647, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.13675213675213677, |
|
"grad_norm": 0.3619644343852997, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 1.0962, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.17094017094017094, |
|
"grad_norm": 0.5769338011741638, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 1.228, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.20512820512820512, |
|
"grad_norm": 0.7016761898994446, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 1.1309, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.23931623931623933, |
|
"grad_norm": 1.0003128051757812, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 1.1807, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.27350427350427353, |
|
"grad_norm": 0.8136112689971924, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.9264, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.3076923076923077, |
|
"grad_norm": 0.7829558253288269, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.9914, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.3418803418803419, |
|
"grad_norm": 0.5833770036697388, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.9621, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.37606837606837606, |
|
"grad_norm": 0.42219626903533936, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.9636, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.41025641025641024, |
|
"grad_norm": 0.5771196484565735, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 1.0986, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.4444444444444444, |
|
"grad_norm": 0.7427020072937012, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 1.2312, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.47863247863247865, |
|
"grad_norm": 0.6502723693847656, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 1.0046, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.5128205128205128, |
|
"grad_norm": 0.2675360143184662, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.805, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.5470085470085471, |
|
"grad_norm": 0.24937307834625244, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.8361, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.5811965811965812, |
|
"grad_norm": 0.32915517687797546, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.8624, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.6153846153846154, |
|
"grad_norm": 0.3165777027606964, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.9041, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.6495726495726496, |
|
"grad_norm": 0.29354873299598694, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.9773, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.6837606837606838, |
|
"grad_norm": 0.3859802186489105, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 1.107, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.717948717948718, |
|
"grad_norm": 0.47748714685440063, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.9861, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.7521367521367521, |
|
"grad_norm": 0.28590238094329834, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.7694, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.7863247863247863, |
|
"grad_norm": 0.26038798689842224, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.8208, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.8205128205128205, |
|
"grad_norm": 0.2839949131011963, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.8718, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.8547008547008547, |
|
"grad_norm": 0.2815213203430176, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.8584, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.8547008547008547, |
|
"eval_loss": 0.9388629794120789, |
|
"eval_runtime": 3.503, |
|
"eval_samples_per_second": 14.274, |
|
"eval_steps_per_second": 3.711, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 0.28909528255462646, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.9418, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.9230769230769231, |
|
"grad_norm": 0.38391032814979553, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 1.0341, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.9572649572649573, |
|
"grad_norm": 0.44489622116088867, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.9819, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.9914529914529915, |
|
"grad_norm": 0.6754913330078125, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.9653, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.0256410256410255, |
|
"grad_norm": 0.5481194853782654, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 1.4565, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.0598290598290598, |
|
"grad_norm": 0.2325354814529419, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.7719, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.0940170940170941, |
|
"grad_norm": 0.26181185245513916, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.8039, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.1282051282051282, |
|
"grad_norm": 0.2746793329715729, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.8383, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.1623931623931625, |
|
"grad_norm": 0.28374120593070984, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.905, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.1965811965811965, |
|
"grad_norm": 0.4092039167881012, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 1.0047, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.2307692307692308, |
|
"grad_norm": 0.5275164246559143, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.8573, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.264957264957265, |
|
"grad_norm": 0.2732887864112854, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.664, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.2991452991452992, |
|
"grad_norm": 0.23111304640769958, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.7862, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.3333333333333333, |
|
"grad_norm": 0.2312902808189392, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.7616, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.3675213675213675, |
|
"grad_norm": 0.25998955965042114, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.837, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.4017094017094016, |
|
"grad_norm": 0.3226254880428314, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.9217, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.435897435897436, |
|
"grad_norm": 0.476153165102005, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 1.006, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.4700854700854702, |
|
"grad_norm": 0.47047027945518494, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.7943, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.5042735042735043, |
|
"grad_norm": 0.2968030571937561, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.5807, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.5384615384615383, |
|
"grad_norm": 0.2597537934780121, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.8635, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.5726495726495726, |
|
"grad_norm": 0.2324274331331253, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.7664, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.606837606837607, |
|
"grad_norm": 0.249767005443573, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.7848, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.641025641025641, |
|
"grad_norm": 0.29912737011909485, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.8973, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.6752136752136753, |
|
"grad_norm": 0.40372592210769653, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.9817, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.7094017094017095, |
|
"grad_norm": 0.47870293259620667, |
|
"learning_rate": 1e-05, |
|
"loss": 0.8148, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.7094017094017095, |
|
"eval_loss": 0.8940553069114685, |
|
"eval_runtime": 3.5034, |
|
"eval_samples_per_second": 14.272, |
|
"eval_steps_per_second": 3.711, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"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": 5.968083617316864e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|