| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10614772224679346, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017691287041132243, | |
| "grad_norm": 1.9742480441813004, | |
| "learning_rate": 2e-08, | |
| "loss": 3.2598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035382574082264487, | |
| "grad_norm": 2.038016027037428, | |
| "learning_rate": 4e-08, | |
| "loss": 3.4531, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005307386112339673, | |
| "grad_norm": 2.225136431627388, | |
| "learning_rate": 6e-08, | |
| "loss": 3.4746, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007076514816452897, | |
| "grad_norm": 2.0178713550531033, | |
| "learning_rate": 8e-08, | |
| "loss": 3.293, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008845643520566122, | |
| "grad_norm": 2.042908378033956, | |
| "learning_rate": 1e-07, | |
| "loss": 3.2383, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010614772224679346, | |
| "grad_norm": 2.1329682870055464, | |
| "learning_rate": 1.2e-07, | |
| "loss": 3.2441, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 2.1377356269998873, | |
| "learning_rate": 1.4e-07, | |
| "loss": 3.293, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014153029632905795, | |
| "grad_norm": 2.0514676704041146, | |
| "learning_rate": 1.6e-07, | |
| "loss": 3.4004, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01592215833701902, | |
| "grad_norm": 1.94775665931649, | |
| "learning_rate": 1.8e-07, | |
| "loss": 3.4355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017691287041132243, | |
| "grad_norm": 2.0977166835164653, | |
| "learning_rate": 2e-07, | |
| "loss": 3.3711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019460415745245468, | |
| "grad_norm": 2.192564032711453, | |
| "learning_rate": 2.1999999999999998e-07, | |
| "loss": 3.3398, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021229544449358692, | |
| "grad_norm": 2.1498795965856914, | |
| "learning_rate": 2.4e-07, | |
| "loss": 3.1562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022998673153471916, | |
| "grad_norm": 2.109291509736264, | |
| "learning_rate": 2.6e-07, | |
| "loss": 3.3652, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 2.044792800372603, | |
| "learning_rate": 2.8e-07, | |
| "loss": 3.2461, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.026536930561698365, | |
| "grad_norm": 2.167283994785129, | |
| "learning_rate": 3e-07, | |
| "loss": 3.3301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02830605926581159, | |
| "grad_norm": 1.995664320722997, | |
| "learning_rate": 3.2e-07, | |
| "loss": 3.3867, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 2.00843521276344, | |
| "learning_rate": 3.4000000000000003e-07, | |
| "loss": 3.2363, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03184431667403804, | |
| "grad_norm": 2.107294400286055, | |
| "learning_rate": 3.6e-07, | |
| "loss": 3.3809, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03361344537815126, | |
| "grad_norm": 1.9965688324131208, | |
| "learning_rate": 3.7999999999999996e-07, | |
| "loss": 3.2637, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03538257408226449, | |
| "grad_norm": 2.1690567393421936, | |
| "learning_rate": 4e-07, | |
| "loss": 3.2461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03715170278637771, | |
| "grad_norm": 1.9509465820725813, | |
| "learning_rate": 4.1999999999999995e-07, | |
| "loss": 3.3359, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.038920831490490936, | |
| "grad_norm": 2.180359699431997, | |
| "learning_rate": 4.3999999999999997e-07, | |
| "loss": 3.498, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.040689960194604156, | |
| "grad_norm": 1.9303585281557267, | |
| "learning_rate": 4.6e-07, | |
| "loss": 3.4453, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.042459088898717384, | |
| "grad_norm": 2.105287899781242, | |
| "learning_rate": 4.8e-07, | |
| "loss": 3.4531, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.044228217602830605, | |
| "grad_norm": 1.996519659869237, | |
| "learning_rate": 5e-07, | |
| "loss": 3.3633, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04599734630694383, | |
| "grad_norm": 2.0672497293218903, | |
| "learning_rate": 5.2e-07, | |
| "loss": 3.4746, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.047766475011057054, | |
| "grad_norm": 2.0187116926490165, | |
| "learning_rate": 5.4e-07, | |
| "loss": 3.3105, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 2.185446736666104, | |
| "learning_rate": 5.6e-07, | |
| "loss": 3.1953, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0513047324192835, | |
| "grad_norm": 1.9785091042817515, | |
| "learning_rate": 5.8e-07, | |
| "loss": 3.2207, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05307386112339673, | |
| "grad_norm": 1.983411961208081, | |
| "learning_rate": 6e-07, | |
| "loss": 3.1953, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05484298982750995, | |
| "grad_norm": 1.8887794910668352, | |
| "learning_rate": 6.2e-07, | |
| "loss": 3.127, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05661211853162318, | |
| "grad_norm": 2.024592500623624, | |
| "learning_rate": 6.4e-07, | |
| "loss": 3.3652, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0583812472357364, | |
| "grad_norm": 2.033056092327317, | |
| "learning_rate": 6.6e-07, | |
| "loss": 3.4629, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 2.1137985890313646, | |
| "learning_rate": 6.800000000000001e-07, | |
| "loss": 3.4277, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06191950464396285, | |
| "grad_norm": 2.135970317417631, | |
| "learning_rate": 7e-07, | |
| "loss": 3.5664, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06368863334807608, | |
| "grad_norm": 1.9525141602052385, | |
| "learning_rate": 7.2e-07, | |
| "loss": 3.3164, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0654577620521893, | |
| "grad_norm": 1.9679140574444143, | |
| "learning_rate": 7.4e-07, | |
| "loss": 3.1348, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06722689075630252, | |
| "grad_norm": 2.0697308820659295, | |
| "learning_rate": 7.599999999999999e-07, | |
| "loss": 3.3574, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06899601946041574, | |
| "grad_norm": 2.0879787228782463, | |
| "learning_rate": 7.799999999999999e-07, | |
| "loss": 3.3477, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07076514816452897, | |
| "grad_norm": 2.0051097367804234, | |
| "learning_rate": 8e-07, | |
| "loss": 3.3477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0725342768686422, | |
| "grad_norm": 2.039846964044792, | |
| "learning_rate": 8.199999999999999e-07, | |
| "loss": 3.2109, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "grad_norm": 2.13344976323939, | |
| "learning_rate": 8.399999999999999e-07, | |
| "loss": 3.3848, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07607253427686864, | |
| "grad_norm": 2.2830511277961585, | |
| "learning_rate": 8.599999999999999e-07, | |
| "loss": 3.1602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07784166298098187, | |
| "grad_norm": 1.9427108734819927, | |
| "learning_rate": 8.799999999999999e-07, | |
| "loss": 3.1914, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07961079168509509, | |
| "grad_norm": 1.9926391710215448, | |
| "learning_rate": 9e-07, | |
| "loss": 3.3711, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08137992038920831, | |
| "grad_norm": 2.2237278323731107, | |
| "learning_rate": 9.2e-07, | |
| "loss": 3.4746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08314904909332153, | |
| "grad_norm": 2.123759872019136, | |
| "learning_rate": 9.399999999999999e-07, | |
| "loss": 3.3926, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08491817779743477, | |
| "grad_norm": 2.138037893897646, | |
| "learning_rate": 9.6e-07, | |
| "loss": 3.377, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08668730650154799, | |
| "grad_norm": 2.074234748374453, | |
| "learning_rate": 9.8e-07, | |
| "loss": 3.3457, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08845643520566121, | |
| "grad_norm": 2.162562414477262, | |
| "learning_rate": 1e-06, | |
| "loss": 3.2148, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 2.091661753228539, | |
| "learning_rate": 1.02e-06, | |
| "loss": 3.3613, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.09199469261388767, | |
| "grad_norm": 2.1815638012188963, | |
| "learning_rate": 1.04e-06, | |
| "loss": 3.2949, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09376382131800089, | |
| "grad_norm": 2.127146363547092, | |
| "learning_rate": 1.06e-06, | |
| "loss": 3.4297, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.09553295002211411, | |
| "grad_norm": 2.201243987413546, | |
| "learning_rate": 1.08e-06, | |
| "loss": 3.1445, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09730207872622733, | |
| "grad_norm": 2.1006629919292075, | |
| "learning_rate": 1.1e-06, | |
| "loss": 3.4238, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "grad_norm": 2.2056247586234115, | |
| "learning_rate": 1.12e-06, | |
| "loss": 3.3516, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.10084033613445378, | |
| "grad_norm": 2.300409874538962, | |
| "learning_rate": 1.1399999999999999e-06, | |
| "loss": 3.4766, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.102609464838567, | |
| "grad_norm": 2.10637739408632, | |
| "learning_rate": 1.16e-06, | |
| "loss": 3.3477, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.10437859354268023, | |
| "grad_norm": 2.047319466977983, | |
| "learning_rate": 1.18e-06, | |
| "loss": 3.3965, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10614772224679346, | |
| "grad_norm": 2.0670306109309102, | |
| "learning_rate": 1.2e-06, | |
| "loss": 3.2266, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 565, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 15477887729664.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |