| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2058672156459084, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004117344312918168, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004117344312918168, | |
| "eval_loss": NaN, | |
| "eval_runtime": 204.7152, | |
| "eval_samples_per_second": 2.003, | |
| "eval_steps_per_second": 1.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008234688625836336, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012352032938754504, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016469377251672673, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020586721564590838, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024704065877509007, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028821410190427176, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032938754503345345, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03705609881626351, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.041173443129181676, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04529078744209985, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.049408131755018014, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05352547606793618, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05352547606793618, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.8507, | |
| "eval_samples_per_second": 9.797, | |
| "eval_steps_per_second": 4.898, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05764282038085435, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06176016469377252, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06587750900669069, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06999485331960885, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07411219763252702, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0782295419454452, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08234688625836335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08646423057128153, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0905815748841997, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09469891919711786, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09881626351003603, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1029336078229542, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10705095213587236, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10705095213587236, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.8281, | |
| "eval_samples_per_second": 9.802, | |
| "eval_steps_per_second": 4.901, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11116829644879053, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1248.2094, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1152856407617087, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12352032938754504, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1276376737004632, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13175501801338138, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13587236232629954, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1399897066392177, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14410705095213588, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14822439526505404, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1523417395779722, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1564590838908904, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16057642820380855, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16057642820380855, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.9216, | |
| "eval_samples_per_second": 9.78, | |
| "eval_steps_per_second": 4.89, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1646937725167267, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1688111168296449, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17292846114256305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1770458054554812, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1811631497683994, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18528049408131755, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1893978383942357, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1935151827071539, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19763252702007206, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20174987133299022, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2058672156459084, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 1.1069915059244237e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |