| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12053638692180202, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024107277384360403, | |
| "grad_norm": 0.18300533294677734, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7954, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024107277384360403, | |
| "eval_loss": 11.799297332763672, | |
| "eval_runtime": 14.7876, | |
| "eval_samples_per_second": 47.269, | |
| "eval_steps_per_second": 23.668, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0048214554768720806, | |
| "grad_norm": 0.1799505054950714, | |
| "learning_rate": 2e-05, | |
| "loss": 11.788, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007232183215308121, | |
| "grad_norm": 0.16323117911815643, | |
| "learning_rate": 3e-05, | |
| "loss": 11.8032, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009642910953744161, | |
| "grad_norm": 0.14314371347427368, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7996, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012053638692180202, | |
| "grad_norm": 0.14851737022399902, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7834, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014464366430616242, | |
| "grad_norm": 0.15303704142570496, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7991, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016875094169052283, | |
| "grad_norm": 0.18720045685768127, | |
| "learning_rate": 7e-05, | |
| "loss": 11.8015, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019285821907488322, | |
| "grad_norm": 0.20559322834014893, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7867, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021696549645924365, | |
| "grad_norm": 0.16245993971824646, | |
| "learning_rate": 9e-05, | |
| "loss": 11.7981, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024107277384360404, | |
| "grad_norm": 0.15587429702281952, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026518005122796444, | |
| "grad_norm": 0.15051642060279846, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 11.7957, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028928732861232483, | |
| "grad_norm": 0.1579117774963379, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.7856, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03133946059966852, | |
| "grad_norm": 0.15979625284671783, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 11.7926, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03133946059966852, | |
| "eval_loss": 11.796106338500977, | |
| "eval_runtime": 0.9529, | |
| "eval_samples_per_second": 733.577, | |
| "eval_steps_per_second": 367.313, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.033750188338104566, | |
| "grad_norm": 0.18402183055877686, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.7933, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03616091607654061, | |
| "grad_norm": 0.15201744437217712, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.7894, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.038571643814976644, | |
| "grad_norm": 0.178207665681839, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 11.7895, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04098237155341269, | |
| "grad_norm": 0.17396970093250275, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 11.7901, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04339309929184873, | |
| "grad_norm": 0.18107326328754425, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.7946, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045803827030284766, | |
| "grad_norm": 0.1765798181295395, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 11.8012, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04821455476872081, | |
| "grad_norm": 0.23805269598960876, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.7868, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.050625282507156845, | |
| "grad_norm": 0.2204178422689438, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 11.7883, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05303601024559289, | |
| "grad_norm": 0.21025092899799347, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.7956, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05544673798402893, | |
| "grad_norm": 0.18470381200313568, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 11.7915, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05785746572246497, | |
| "grad_norm": 0.1800222247838974, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.7856, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06026819346090101, | |
| "grad_norm": 0.22917437553405762, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.7965, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06267892119933705, | |
| "grad_norm": 0.2602176070213318, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.7896, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06267892119933705, | |
| "eval_loss": 11.790661811828613, | |
| "eval_runtime": 0.9583, | |
| "eval_samples_per_second": 729.402, | |
| "eval_steps_per_second": 365.223, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0650896489377731, | |
| "grad_norm": 0.2239828109741211, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 11.7856, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06750037667620913, | |
| "grad_norm": 0.24870462715625763, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 11.7983, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06991110441464517, | |
| "grad_norm": 0.22321942448616028, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 11.779, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07232183215308122, | |
| "grad_norm": 0.21131961047649384, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7853, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07473255989151725, | |
| "grad_norm": 0.18241849541664124, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 11.7763, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07714328762995329, | |
| "grad_norm": 0.19740787148475647, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 11.7796, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07955401536838934, | |
| "grad_norm": 0.21648883819580078, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 11.7823, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08196474310682537, | |
| "grad_norm": 0.17037546634674072, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.7975, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08437547084526141, | |
| "grad_norm": 0.21887211501598358, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.7907, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08678619858369746, | |
| "grad_norm": 0.23544444143772125, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 11.7838, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0891969263221335, | |
| "grad_norm": 0.22000566124916077, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 11.7847, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09160765406056953, | |
| "grad_norm": 0.28442928194999695, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 11.7825, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09401838179900557, | |
| "grad_norm": 0.25764262676239014, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 11.7722, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09401838179900557, | |
| "eval_loss": 11.787515640258789, | |
| "eval_runtime": 0.9775, | |
| "eval_samples_per_second": 715.095, | |
| "eval_steps_per_second": 358.059, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09642910953744162, | |
| "grad_norm": 0.23126229643821716, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.7885, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09883983727587765, | |
| "grad_norm": 0.21654988825321198, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 11.7704, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10125056501431369, | |
| "grad_norm": 0.2214740812778473, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.7851, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10366129275274974, | |
| "grad_norm": 0.24273362755775452, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 11.7811, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10607202049118578, | |
| "grad_norm": 0.2188863307237625, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 11.7789, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10848274822962181, | |
| "grad_norm": 0.20905157923698425, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.7927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11089347596805786, | |
| "grad_norm": 0.2186051905155182, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 11.7862, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1133042037064939, | |
| "grad_norm": 0.2207147777080536, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 11.7808, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11571493144492993, | |
| "grad_norm": 0.260870099067688, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 11.7878, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11812565918336598, | |
| "grad_norm": 0.1919865906238556, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 11.7874, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12053638692180202, | |
| "grad_norm": 0.2674182653427124, | |
| "learning_rate": 0.0, | |
| "loss": 11.7881, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 10295707336704.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |