| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9157088122605364, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.038314176245210725, | |
| "grad_norm": 0.3217230917151008, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 2.4318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07662835249042145, | |
| "grad_norm": 0.40615181133127565, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 2.4277, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11494252873563218, | |
| "grad_norm": 0.6561447102516671, | |
| "learning_rate": 5.660377358490566e-05, | |
| "loss": 2.433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1532567049808429, | |
| "grad_norm": 0.47475244248065424, | |
| "learning_rate": 7.547169811320755e-05, | |
| "loss": 2.4355, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19157088122605365, | |
| "grad_norm": 0.7543768354889395, | |
| "learning_rate": 9.433962264150944e-05, | |
| "loss": 2.4467, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22988505747126436, | |
| "grad_norm": 0.45899820520400003, | |
| "learning_rate": 9.994504457428558e-05, | |
| "loss": 2.4393, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2681992337164751, | |
| "grad_norm": 0.4823946996990999, | |
| "learning_rate": 9.967616591677905e-05, | |
| "loss": 2.4541, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3065134099616858, | |
| "grad_norm": 0.3393294030578001, | |
| "learning_rate": 9.918447466584544e-05, | |
| "loss": 2.4523, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.5651147369232912, | |
| "learning_rate": 9.847217620510815e-05, | |
| "loss": 2.4576, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3831417624521073, | |
| "grad_norm": 0.34879332121566425, | |
| "learning_rate": 9.754246540809257e-05, | |
| "loss": 2.4504, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.421455938697318, | |
| "grad_norm": 0.5594959779731135, | |
| "learning_rate": 9.639951230825433e-05, | |
| "loss": 2.466, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45977011494252873, | |
| "grad_norm": 0.274770129693475, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 2.4469, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49808429118773945, | |
| "grad_norm": 0.30708437591742765, | |
| "learning_rate": 9.349531862043952e-05, | |
| "loss": 2.4521, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5363984674329502, | |
| "grad_norm": 0.28940091280377206, | |
| "learning_rate": 9.174710421746444e-05, | |
| "loss": 2.4596, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 0.33901258469233675, | |
| "learning_rate": 8.981164145529944e-05, | |
| "loss": 2.4572, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6130268199233716, | |
| "grad_norm": 0.29452774712566837, | |
| "learning_rate": 8.769761146843949e-05, | |
| "loss": 2.4545, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6513409961685823, | |
| "grad_norm": 0.28040855801882, | |
| "learning_rate": 8.541449631926325e-05, | |
| "loss": 2.4562, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.26567815293624064, | |
| "learning_rate": 8.297253646812213e-05, | |
| "loss": 2.4482, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7279693486590039, | |
| "grad_norm": 0.6149158857790219, | |
| "learning_rate": 8.038268484178565e-05, | |
| "loss": 2.4553, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7662835249042146, | |
| "grad_norm": 0.27934075531158126, | |
| "learning_rate": 7.765655770625997e-05, | |
| "loss": 2.4463, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8045977011494253, | |
| "grad_norm": 0.26860998367945094, | |
| "learning_rate": 7.480638256432977e-05, | |
| "loss": 2.4514, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.842911877394636, | |
| "grad_norm": 0.34035821167200137, | |
| "learning_rate": 7.184494331151866e-05, | |
| "loss": 2.449, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8812260536398467, | |
| "grad_norm": 0.262160342617283, | |
| "learning_rate": 6.878552289646041e-05, | |
| "loss": 2.4381, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9195402298850575, | |
| "grad_norm": 0.29975838142553335, | |
| "learning_rate": 6.564184374286636e-05, | |
| "loss": 2.4477, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9578544061302682, | |
| "grad_norm": 0.3038130770045491, | |
| "learning_rate": 6.242800620031434e-05, | |
| "loss": 2.4393, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9961685823754789, | |
| "grad_norm": 0.23643504791544426, | |
| "learning_rate": 5.915842529992631e-05, | |
| "loss": 2.4285, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 0.4638398552745887, | |
| "learning_rate": 5.584776609860414e-05, | |
| "loss": 2.1607, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0727969348659003, | |
| "grad_norm": 0.3369549986726721, | |
| "learning_rate": 5.2510877901824286e-05, | |
| "loss": 2.1133, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.2891769614162093, | |
| "learning_rate": 4.916272766002227e-05, | |
| "loss": 2.1084, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 0.25599077000320447, | |
| "learning_rate": 4.5818332837303665e-05, | |
| "loss": 2.1109, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1877394636015326, | |
| "grad_norm": 0.25505449141811376, | |
| "learning_rate": 4.249269405358634e-05, | |
| "loss": 2.1141, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2260536398467432, | |
| "grad_norm": 0.24717989839985094, | |
| "learning_rate": 3.920072780229378e-05, | |
| "loss": 2.1141, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.264367816091954, | |
| "grad_norm": 0.24533136645961962, | |
| "learning_rate": 3.595719954538122e-05, | |
| "loss": 2.1111, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3026819923371646, | |
| "grad_norm": 0.2405802075099404, | |
| "learning_rate": 3.277665748578336e-05, | |
| "loss": 2.1086, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3409961685823755, | |
| "grad_norm": 0.24564169644979666, | |
| "learning_rate": 2.9673367314334532e-05, | |
| "loss": 2.1076, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.23899109047951717, | |
| "learning_rate": 2.6661248223840707e-05, | |
| "loss": 2.1092, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.417624521072797, | |
| "grad_norm": 0.24093321299505463, | |
| "learning_rate": 2.37538104772998e-05, | |
| "loss": 2.1092, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4559386973180077, | |
| "grad_norm": 0.2353684891980503, | |
| "learning_rate": 2.0964094810295558e-05, | |
| "loss": 2.1158, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.4942528735632183, | |
| "grad_norm": 0.2338179136134976, | |
| "learning_rate": 1.830461393936353e-05, | |
| "loss": 2.1139, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5325670498084292, | |
| "grad_norm": 0.2338961312820727, | |
| "learning_rate": 1.578729643868181e-05, | |
| "loss": 2.1143, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5708812260536398, | |
| "grad_norm": 0.2296079266331823, | |
| "learning_rate": 1.3423433236816563e-05, | |
| "loss": 2.1117, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6091954022988506, | |
| "grad_norm": 0.2318348232005023, | |
| "learning_rate": 1.1223626973500396e-05, | |
| "loss": 2.1109, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6475095785440614, | |
| "grad_norm": 0.22777895966815453, | |
| "learning_rate": 9.197744443594003e-06, | |
| "loss": 2.1023, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.685823754789272, | |
| "grad_norm": 0.2294544601103437, | |
| "learning_rate": 7.3548723415340196e-06, | |
| "loss": 2.1046, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.22902930560321783, | |
| "learning_rate": 5.7032765047665136e-06, | |
| "loss": 2.1181, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7624521072796935, | |
| "grad_norm": 0.2266817684502059, | |
| "learning_rate": 4.250364838972065e-06, | |
| "loss": 2.1089, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8007662835249043, | |
| "grad_norm": 0.2258576905472298, | |
| "learning_rate": 3.0026540913734522e-06, | |
| "loss": 2.1077, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.839080459770115, | |
| "grad_norm": 0.2254304711001865, | |
| "learning_rate": 1.9657406211579966e-06, | |
| "loss": 2.1057, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.8773946360153255, | |
| "grad_norm": 0.21992296869073144, | |
| "learning_rate": 1.1442752981179527e-06, | |
| "loss": 2.1031, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9157088122605364, | |
| "grad_norm": 0.21929533112603253, | |
| "learning_rate": 5.41942642096177e-07, | |
| "loss": 2.1109, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9157088122605364, | |
| "eval_loss": 2.403846263885498, | |
| "eval_runtime": 0.7812, | |
| "eval_samples_per_second": 16.641, | |
| "eval_steps_per_second": 1.28, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 522, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1944814878720000.0, | |
| "train_batch_size": 120, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |