| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013967699694456569, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002793539938891314, | |
| "grad_norm": 6.970461368560791, | |
| "learning_rate": 1e-05, | |
| "loss": 20.2109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002793539938891314, | |
| "eval_loss": 1.442408561706543, | |
| "eval_runtime": 1007.3212, | |
| "eval_samples_per_second": 5.985, | |
| "eval_steps_per_second": 2.993, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005587079877782628, | |
| "grad_norm": 8.621979713439941, | |
| "learning_rate": 2e-05, | |
| "loss": 19.3008, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008380619816673942, | |
| "grad_norm": 25.636756896972656, | |
| "learning_rate": 3e-05, | |
| "loss": 23.4492, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011174159755565256, | |
| "grad_norm": 28.452890396118164, | |
| "learning_rate": 4e-05, | |
| "loss": 24.0312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001396769969445657, | |
| "grad_norm": 25.22979164123535, | |
| "learning_rate": 5e-05, | |
| "loss": 23.2031, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016761239633347883, | |
| "grad_norm": 11.268664360046387, | |
| "learning_rate": 6e-05, | |
| "loss": 21.0352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019554779572239197, | |
| "grad_norm": 7.0515360832214355, | |
| "learning_rate": 7e-05, | |
| "loss": 18.0703, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022348319511130512, | |
| "grad_norm": 14.672618865966797, | |
| "learning_rate": 8e-05, | |
| "loss": 20.1523, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025141859450021824, | |
| "grad_norm": 36.66195297241211, | |
| "learning_rate": 9e-05, | |
| "loss": 26.6875, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002793539938891314, | |
| "grad_norm": 19.24175262451172, | |
| "learning_rate": 0.0001, | |
| "loss": 23.5977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003072893932780445, | |
| "grad_norm": 9.555656433105469, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 19.2812, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033522479266695766, | |
| "grad_norm": 12.923059463500977, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 21.9219, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003631601920558708, | |
| "grad_norm": 7.538259506225586, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 18.7695, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003631601920558708, | |
| "eval_loss": 1.2370249032974243, | |
| "eval_runtime": 888.687, | |
| "eval_samples_per_second": 6.784, | |
| "eval_steps_per_second": 3.393, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003910955914447839, | |
| "grad_norm": 8.404040336608887, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 18.8438, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0041903099083369704, | |
| "grad_norm": 23.96065902709961, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 21.5391, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0044696639022261024, | |
| "grad_norm": 8.518821716308594, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 17.5547, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004749017896115234, | |
| "grad_norm": 9.683491706848145, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 18.3867, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005028371890004365, | |
| "grad_norm": 12.909642219543457, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 20.334, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005307725883893497, | |
| "grad_norm": 6.089707851409912, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 18.9375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005587079877782628, | |
| "grad_norm": 8.212544441223145, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 19.8164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005866433871671759, | |
| "grad_norm": 8.69490909576416, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 19.0977, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00614578786556089, | |
| "grad_norm": 6.588229179382324, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 18.7383, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006425141859450022, | |
| "grad_norm": 6.510587215423584, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 19.0391, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006704495853339153, | |
| "grad_norm": 10.146479606628418, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 20.457, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006983849847228284, | |
| "grad_norm": 6.790075302124023, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 19.5586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007263203841117416, | |
| "grad_norm": 6.229572296142578, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 19.375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007263203841117416, | |
| "eval_loss": 1.168168306350708, | |
| "eval_runtime": 888.7918, | |
| "eval_samples_per_second": 6.783, | |
| "eval_steps_per_second": 3.392, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0075425578350065475, | |
| "grad_norm": 7.612943649291992, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 19.8984, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007821911828895679, | |
| "grad_norm": 7.850345134735107, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 18.8711, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00810126582278481, | |
| "grad_norm": 8.194131851196289, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 18.4531, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008380619816673941, | |
| "grad_norm": 8.798739433288574, | |
| "learning_rate": 5e-05, | |
| "loss": 20.082, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008659973810563073, | |
| "grad_norm": 4.806086540222168, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 18.3242, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008939327804452205, | |
| "grad_norm": 6.420837879180908, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 17.5234, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009218681798341335, | |
| "grad_norm": 5.769430637359619, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 19.3711, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009498035792230467, | |
| "grad_norm": 6.312093734741211, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 17.0234, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0097773897861196, | |
| "grad_norm": 10.681304931640625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 19.4766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01005674378000873, | |
| "grad_norm": 8.919983863830566, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 16.9336, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010336097773897861, | |
| "grad_norm": 7.540457725524902, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 17.8359, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010615451767786993, | |
| "grad_norm": 6.8388752937316895, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 19.4062, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010894805761676124, | |
| "grad_norm": 5.113622188568115, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 17.5781, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010894805761676124, | |
| "eval_loss": 1.1385672092437744, | |
| "eval_runtime": 888.7356, | |
| "eval_samples_per_second": 6.784, | |
| "eval_steps_per_second": 3.392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011174159755565256, | |
| "grad_norm": 5.941615581512451, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 18.2148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011453513749454386, | |
| "grad_norm": 6.788694858551025, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 18.3477, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011732867743343518, | |
| "grad_norm": 6.989747524261475, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 19.8516, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01201222173723265, | |
| "grad_norm": 9.784863471984863, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 16.9668, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01229157573112178, | |
| "grad_norm": 7.244667053222656, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 18.1797, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012570929725010912, | |
| "grad_norm": 7.783876419067383, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 18.0039, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012850283718900044, | |
| "grad_norm": 12.166605949401855, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 18.4736, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013129637712789174, | |
| "grad_norm": 7.943640232086182, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 17.7656, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013408991706678306, | |
| "grad_norm": 7.052063941955566, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 17.332, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013688345700567438, | |
| "grad_norm": 7.097042560577393, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 17.2266, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013967699694456569, | |
| "grad_norm": 9.13848876953125, | |
| "learning_rate": 0.0, | |
| "loss": 18.5176, | |
| "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": 5.072003618832384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |