| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 2252, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.045956578105688095, | |
| "learning_rate": 0.00019564831261101244, | |
| "loss": 0.322, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.03815697133541107, | |
| "learning_rate": 0.00019120781527531084, | |
| "loss": 0.1842, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.061464082449674606, | |
| "learning_rate": 0.00018676731793960925, | |
| "loss": 0.1801, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.0637449324131012, | |
| "learning_rate": 0.00018232682060390765, | |
| "loss": 0.1773, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.053989194333553314, | |
| "learning_rate": 0.00017788632326820605, | |
| "loss": 0.17, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.06381799280643463, | |
| "learning_rate": 0.00017344582593250445, | |
| "loss": 0.1527, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.07270950824022293, | |
| "learning_rate": 0.00016900532859680286, | |
| "loss": 0.1594, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.051719773560762405, | |
| "learning_rate": 0.00016456483126110126, | |
| "loss": 0.1535, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.06734076142311096, | |
| "learning_rate": 0.00016012433392539966, | |
| "loss": 0.1431, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.04238704591989517, | |
| "learning_rate": 0.00015568383658969806, | |
| "loss": 0.1439, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.056586671620607376, | |
| "learning_rate": 0.00015124333925399647, | |
| "loss": 0.1333, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0657777777777777, | |
| "grad_norm": 0.05698104947805405, | |
| "learning_rate": 0.00014680284191829484, | |
| "loss": 0.1474, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1546666666666667, | |
| "grad_norm": 0.054345980286598206, | |
| "learning_rate": 0.00014236234458259324, | |
| "loss": 0.1253, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.2435555555555555, | |
| "grad_norm": 0.04708417132496834, | |
| "learning_rate": 0.00013792184724689165, | |
| "loss": 0.1349, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.3324444444444445, | |
| "grad_norm": 0.06845518201589584, | |
| "learning_rate": 0.00013348134991119005, | |
| "loss": 0.1144, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4213333333333333, | |
| "grad_norm": 0.0530928298830986, | |
| "learning_rate": 0.00012904085257548845, | |
| "loss": 0.1168, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5102222222222221, | |
| "grad_norm": 0.08338514715433121, | |
| "learning_rate": 0.00012460035523978685, | |
| "loss": 0.1237, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5991111111111111, | |
| "grad_norm": 0.06609191745519638, | |
| "learning_rate": 0.00012015985790408525, | |
| "loss": 0.141, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.688, | |
| "grad_norm": 0.08270981907844543, | |
| "learning_rate": 0.00011571936056838366, | |
| "loss": 0.1256, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.7768888888888887, | |
| "grad_norm": 0.048950765281915665, | |
| "learning_rate": 0.00011127886323268206, | |
| "loss": 0.1175, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.8657777777777778, | |
| "grad_norm": 0.06318267434835434, | |
| "learning_rate": 0.00010683836589698046, | |
| "loss": 0.1275, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.9546666666666668, | |
| "grad_norm": 0.07041537761688232, | |
| "learning_rate": 0.00010239786856127886, | |
| "loss": 0.124, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.042666666666667, | |
| "grad_norm": 0.0656278058886528, | |
| "learning_rate": 9.795737122557727e-05, | |
| "loss": 0.1327, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.1315555555555554, | |
| "grad_norm": 0.06331595033407211, | |
| "learning_rate": 9.351687388987567e-05, | |
| "loss": 0.1069, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.2204444444444444, | |
| "grad_norm": 0.04332101345062256, | |
| "learning_rate": 8.907637655417407e-05, | |
| "loss": 0.1024, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.3093333333333335, | |
| "grad_norm": 0.06444103270769119, | |
| "learning_rate": 8.463587921847247e-05, | |
| "loss": 0.1026, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.398222222222222, | |
| "grad_norm": 0.06379590928554535, | |
| "learning_rate": 8.019538188277088e-05, | |
| "loss": 0.1189, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.487111111111111, | |
| "grad_norm": 0.0656711533665657, | |
| "learning_rate": 7.575488454706926e-05, | |
| "loss": 0.1085, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.576, | |
| "grad_norm": 0.07427001744508743, | |
| "learning_rate": 7.131438721136767e-05, | |
| "loss": 0.1245, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.664888888888889, | |
| "grad_norm": 0.06245647370815277, | |
| "learning_rate": 6.687388987566607e-05, | |
| "loss": 0.1118, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.7537777777777777, | |
| "grad_norm": 0.08108062297105789, | |
| "learning_rate": 6.243339253996447e-05, | |
| "loss": 0.1137, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.8426666666666667, | |
| "grad_norm": 0.061958227306604385, | |
| "learning_rate": 5.7992895204262874e-05, | |
| "loss": 0.1001, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.9315555555555557, | |
| "grad_norm": 0.056670840829610825, | |
| "learning_rate": 5.3552397868561276e-05, | |
| "loss": 0.1172, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 3.0195555555555558, | |
| "grad_norm": 0.07005661725997925, | |
| "learning_rate": 4.9111900532859686e-05, | |
| "loss": 0.1099, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.1084444444444443, | |
| "grad_norm": 0.0712517499923706, | |
| "learning_rate": 4.467140319715809e-05, | |
| "loss": 0.0932, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.1973333333333334, | |
| "grad_norm": 0.07057236135005951, | |
| "learning_rate": 4.0230905861456483e-05, | |
| "loss": 0.0982, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.2862222222222224, | |
| "grad_norm": 0.07291365414857864, | |
| "learning_rate": 3.5790408525754886e-05, | |
| "loss": 0.1008, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.375111111111111, | |
| "grad_norm": 0.11394993960857391, | |
| "learning_rate": 3.134991119005329e-05, | |
| "loss": 0.0933, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.464, | |
| "grad_norm": 0.09188514947891235, | |
| "learning_rate": 2.690941385435169e-05, | |
| "loss": 0.0969, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.552888888888889, | |
| "grad_norm": 0.08308542519807816, | |
| "learning_rate": 2.246891651865009e-05, | |
| "loss": 0.1067, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.6417777777777776, | |
| "grad_norm": 0.10817820578813553, | |
| "learning_rate": 1.8028419182948492e-05, | |
| "loss": 0.0931, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.7306666666666666, | |
| "grad_norm": 0.06676340103149414, | |
| "learning_rate": 1.3587921847246892e-05, | |
| "loss": 0.0984, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.8195555555555556, | |
| "grad_norm": 0.0792100727558136, | |
| "learning_rate": 9.147424511545293e-06, | |
| "loss": 0.1007, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.9084444444444446, | |
| "grad_norm": 0.06362316757440567, | |
| "learning_rate": 4.706927175843695e-06, | |
| "loss": 0.0935, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.997333333333333, | |
| "grad_norm": 0.08906163275241852, | |
| "learning_rate": 2.6642984014209596e-07, | |
| "loss": 0.0958, | |
| "step": 2250 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2252, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.468874889363456e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |