| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 546, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.27392202615737915, | |
| "learning_rate": 4.908424908424908e-05, | |
| "loss": 0.6974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 1.1879206895828247, | |
| "learning_rate": 4.816849816849817e-05, | |
| "loss": 0.707, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "grad_norm": 0.04194138944149017, | |
| "learning_rate": 4.7252747252747257e-05, | |
| "loss": 0.6944, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 0.4733542203903198, | |
| "learning_rate": 4.6336996336996343e-05, | |
| "loss": 0.6962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27472527472527475, | |
| "grad_norm": 0.5218614339828491, | |
| "learning_rate": 4.5421245421245424e-05, | |
| "loss": 0.6971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 0.6687294244766235, | |
| "learning_rate": 4.4505494505494504e-05, | |
| "loss": 0.6912, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.8817914128303528, | |
| "learning_rate": 4.358974358974359e-05, | |
| "loss": 0.7019, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.0032853269949555397, | |
| "learning_rate": 4.267399267399267e-05, | |
| "loss": 0.6987, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "grad_norm": 0.41789019107818604, | |
| "learning_rate": 4.1758241758241765e-05, | |
| "loss": 0.7004, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "grad_norm": 0.36019155383110046, | |
| "learning_rate": 4.0842490842490845e-05, | |
| "loss": 0.697, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6043956043956044, | |
| "grad_norm": 0.10219324380159378, | |
| "learning_rate": 3.992673992673993e-05, | |
| "loss": 0.6915, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.5682424902915955, | |
| "learning_rate": 3.901098901098901e-05, | |
| "loss": 0.6871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.32208287715911865, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.6929, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.6399782299995422, | |
| "learning_rate": 3.717948717948718e-05, | |
| "loss": 0.6935, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "grad_norm": 0.6218127012252808, | |
| "learning_rate": 3.6263736263736266e-05, | |
| "loss": 0.689, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.15324005484580994, | |
| "learning_rate": 3.534798534798535e-05, | |
| "loss": 0.6934, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9340659340659341, | |
| "grad_norm": 0.6022002100944519, | |
| "learning_rate": 3.443223443223443e-05, | |
| "loss": 0.6959, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "grad_norm": 0.5421551465988159, | |
| "learning_rate": 3.3516483516483513e-05, | |
| "loss": 0.6943, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6939666867256165, | |
| "eval_runtime": 189.5452, | |
| "eval_samples_per_second": 3.83, | |
| "eval_steps_per_second": 0.243, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.043956043956044, | |
| "grad_norm": 0.029725607484579086, | |
| "learning_rate": 3.26007326007326e-05, | |
| "loss": 0.6941, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.098901098901099, | |
| "grad_norm": 0.2241191416978836, | |
| "learning_rate": 3.168498168498169e-05, | |
| "loss": 0.6947, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 0.3774152100086212, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.6942, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2087912087912087, | |
| "grad_norm": 0.20546726882457733, | |
| "learning_rate": 2.9853479853479855e-05, | |
| "loss": 0.6969, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2637362637362637, | |
| "grad_norm": 0.13492144644260406, | |
| "learning_rate": 2.893772893772894e-05, | |
| "loss": 0.6902, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 0.8513393402099609, | |
| "learning_rate": 2.8021978021978025e-05, | |
| "loss": 0.6876, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3736263736263736, | |
| "grad_norm": 0.6317694783210754, | |
| "learning_rate": 2.7106227106227105e-05, | |
| "loss": 0.6997, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.5553500056266785, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.6957, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4835164835164836, | |
| "grad_norm": 0.6473520994186401, | |
| "learning_rate": 2.5274725274725276e-05, | |
| "loss": 0.6845, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.4740413427352905, | |
| "learning_rate": 2.435897435897436e-05, | |
| "loss": 0.6901, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.5934065934065935, | |
| "grad_norm": 0.30147257447242737, | |
| "learning_rate": 2.3443223443223443e-05, | |
| "loss": 0.6938, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.6483516483516483, | |
| "grad_norm": 0.8619340658187866, | |
| "learning_rate": 2.252747252747253e-05, | |
| "loss": 0.702, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.7032967032967035, | |
| "grad_norm": 0.7783694863319397, | |
| "learning_rate": 2.1611721611721613e-05, | |
| "loss": 0.6931, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 1.2516826391220093, | |
| "learning_rate": 2.0695970695970697e-05, | |
| "loss": 0.6936, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.8131868131868132, | |
| "grad_norm": 0.9541371464729309, | |
| "learning_rate": 1.978021978021978e-05, | |
| "loss": 0.6923, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.8681318681318682, | |
| "grad_norm": 0.26722267270088196, | |
| "learning_rate": 1.8864468864468864e-05, | |
| "loss": 0.6944, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 0.26405128836631775, | |
| "learning_rate": 1.794871794871795e-05, | |
| "loss": 0.6936, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.978021978021978, | |
| "grad_norm": 0.6899142861366272, | |
| "learning_rate": 1.7032967032967035e-05, | |
| "loss": 0.691, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6916947960853577, | |
| "eval_runtime": 240.4419, | |
| "eval_samples_per_second": 3.019, | |
| "eval_steps_per_second": 0.191, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.032967032967033, | |
| "grad_norm": 0.15929658710956573, | |
| "learning_rate": 1.6117216117216118e-05, | |
| "loss": 0.6928, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.087912087912088, | |
| "grad_norm": 0.15032555162906647, | |
| "learning_rate": 1.52014652014652e-05, | |
| "loss": 0.6908, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.12846487760543823, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.6912, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "grad_norm": 0.1073530912399292, | |
| "learning_rate": 1.336996336996337e-05, | |
| "loss": 0.6958, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.2527472527472527, | |
| "grad_norm": 0.3209209144115448, | |
| "learning_rate": 1.2454212454212454e-05, | |
| "loss": 0.695, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.19632519781589508, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.6951, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.3626373626373627, | |
| "grad_norm": 1.1780059337615967, | |
| "learning_rate": 1.0622710622710623e-05, | |
| "loss": 0.6906, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.4175824175824174, | |
| "grad_norm": 0.2050175666809082, | |
| "learning_rate": 9.706959706959708e-06, | |
| "loss": 0.6941, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.4725274725274726, | |
| "grad_norm": 0.6877321004867554, | |
| "learning_rate": 8.791208791208792e-06, | |
| "loss": 0.6908, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.5274725274725274, | |
| "grad_norm": 0.41336432099342346, | |
| "learning_rate": 7.875457875457876e-06, | |
| "loss": 0.6903, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.5824175824175826, | |
| "grad_norm": 0.339912474155426, | |
| "learning_rate": 6.95970695970696e-06, | |
| "loss": 0.6932, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "grad_norm": 0.3437363803386688, | |
| "learning_rate": 6.043956043956044e-06, | |
| "loss": 0.692, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 0.10014953464269638, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 0.6907, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.7472527472527473, | |
| "grad_norm": 0.10608287155628204, | |
| "learning_rate": 4.212454212454213e-06, | |
| "loss": 0.6899, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.802197802197802, | |
| "grad_norm": 0.13735678791999817, | |
| "learning_rate": 3.2967032967032968e-06, | |
| "loss": 0.694, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.5880533456802368, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.7005, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.912087912087912, | |
| "grad_norm": 0.3347012996673584, | |
| "learning_rate": 1.4652014652014652e-06, | |
| "loss": 0.692, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.967032967032967, | |
| "grad_norm": 0.39770108461380005, | |
| "learning_rate": 5.494505494505495e-07, | |
| "loss": 0.6867, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6915315389633179, | |
| "eval_runtime": 192.9872, | |
| "eval_samples_per_second": 3.762, | |
| "eval_steps_per_second": 0.238, | |
| "step": 546 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 546, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.751102135223255e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |