| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.029720184136957283, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1658, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.03486771939014158, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1586, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.030499845616562056, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1606, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.029842600492727876, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.03193828275511967, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1566, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.03898766683257652, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.25925925925925924, | |
| "grad_norm": 0.0305356771066798, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 0.1566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.03785110896854066, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.1483, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.03523928938060042, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 0.1341, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.030989997872209137, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.1307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4074074074074074, | |
| "grad_norm": 0.0307587332869342, | |
| "learning_rate": 4.867325323737765e-05, | |
| "loss": 0.1164, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.032855708559603986, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.1198, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.48148148148148145, | |
| "grad_norm": 0.03684797833781682, | |
| "learning_rate": 4.742181853831721e-05, | |
| "loss": 0.1154, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 0.03092462089881499, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.12, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.034522828309207276, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 0.11, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.03883602343311024, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.107, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6296296296296297, | |
| "grad_norm": 0.03754767111769993, | |
| "learning_rate": 4.379599518697444e-05, | |
| "loss": 0.101, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.03232556146652115, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0962, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7037037037037037, | |
| "grad_norm": 0.024099202404702792, | |
| "learning_rate": 4.148364537750172e-05, | |
| "loss": 0.0874, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.022567984069900678, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0829, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.026437060221120093, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 0.0881, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.02162774540839224, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0729, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8518518518518519, | |
| "grad_norm": 0.02468371578673811, | |
| "learning_rate": 3.6057217255475034e-05, | |
| "loss": 0.081, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.025095468985489207, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0759, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "grad_norm": 0.023835922892399036, | |
| "learning_rate": 3.303598663257904e-05, | |
| "loss": 0.0691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "grad_norm": 0.024135725380681573, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.02143818466707733, | |
| "learning_rate": 2.9877258050403212e-05, | |
| "loss": 0.0649, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.037037037037037, | |
| "grad_norm": 0.021975353543597143, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 0.020460645688750702, | |
| "learning_rate": 2.663507823075358e-05, | |
| "loss": 0.0588, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.02005719122153396, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1481481481481481, | |
| "grad_norm": 0.02205770556604261, | |
| "learning_rate": 2.3364921769246423e-05, | |
| "loss": 0.0585, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.021622497917847996, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0554, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 0.02266356600613073, | |
| "learning_rate": 2.0122741949596797e-05, | |
| "loss": 0.0516, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2592592592592593, | |
| "grad_norm": 0.018411302507836163, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0529, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2962962962962963, | |
| "grad_norm": 0.018169530470609537, | |
| "learning_rate": 1.6964013367420966e-05, | |
| "loss": 0.0542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.01799959996854442, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0506, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 0.02346499484844407, | |
| "learning_rate": 1.3942782744524973e-05, | |
| "loss": 0.0491, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4074074074074074, | |
| "grad_norm": 0.021788519977543077, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.051, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.020394104745529888, | |
| "learning_rate": 1.1110744174509952e-05, | |
| "loss": 0.0506, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 0.019274638389913223, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0511, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 0.02128599734418728, | |
| "learning_rate": 8.51635462249828e-06, | |
| "loss": 0.0503, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 0.01968221746508841, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0498, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5925925925925926, | |
| "grad_norm": 0.01921152342107632, | |
| "learning_rate": 6.204004813025568e-06, | |
| "loss": 0.0536, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6296296296296298, | |
| "grad_norm": 0.020638559778193205, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0499, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.02209529960346837, | |
| "learning_rate": 4.213259692436367e-06, | |
| "loss": 0.0429, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7037037037037037, | |
| "grad_norm": 0.02060638418553541, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0425, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7407407407407407, | |
| "grad_norm": 0.021415059976167307, | |
| "learning_rate": 2.578181461682794e-06, | |
| "loss": 0.0483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.020972877285230354, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0462, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8148148148148149, | |
| "grad_norm": 0.01871295899620719, | |
| "learning_rate": 1.3267467626223606e-06, | |
| "loss": 0.0461, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 0.02234470762585676, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0413, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.01992557714039091, | |
| "learning_rate": 4.803679899192392e-07, | |
| "loss": 0.046, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "grad_norm": 0.018381170337810084, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.05, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9629629629629628, | |
| "grad_norm": 0.021746331584797423, | |
| "learning_rate": 5.352691903491303e-08, | |
| "loss": 0.0429, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.019701565733805382, | |
| "learning_rate": 0.0, | |
| "loss": 0.0467, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 54, | |
| "total_flos": 364812512526336.0, | |
| "train_loss": 0.08273856348737522, | |
| "train_runtime": 819.6955, | |
| "train_samples_per_second": 0.515, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 54, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 364812512526336.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |