| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.995433789954339, | |
| "eval_steps": 500, | |
| "global_step": 1204, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 0.4084379971027374, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 0.24725936353206635, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1547, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.1690889149904251, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0644, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.09192364662885666, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0466, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 0.08266641944646835, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0385, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 0.10168185085058212, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0379, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.278538812785388, | |
| "grad_norm": 0.10715723037719727, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0337, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.461187214611872, | |
| "grad_norm": 0.08185174316167831, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0304, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 0.0720980241894722, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0342, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.82648401826484, | |
| "grad_norm": 0.07974616438150406, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0312, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.009132420091324, | |
| "grad_norm": 0.08611268550157547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0315, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 0.06699004024267197, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0267, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.374429223744292, | |
| "grad_norm": 0.1077587902545929, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0246, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.557077625570776, | |
| "grad_norm": 0.10352851450443268, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0267, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 0.08488716930150986, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0297, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.922374429223744, | |
| "grad_norm": 0.08407847583293915, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0269, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.105022831050228, | |
| "grad_norm": 0.0976366400718689, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0251, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.287671232876712, | |
| "grad_norm": 0.08240761607885361, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0229, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.470319634703196, | |
| "grad_norm": 0.0689239650964737, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0232, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.65296803652968, | |
| "grad_norm": 0.0607539638876915, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0231, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.8356164383561646, | |
| "grad_norm": 0.06858925521373749, | |
| "learning_rate": 0.0001, | |
| "loss": 0.023, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.018264840182648, | |
| "grad_norm": 0.04049643874168396, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0231, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.200913242009133, | |
| "grad_norm": 0.08556920289993286, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.383561643835616, | |
| "grad_norm": 0.05961354076862335, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0183, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.566210045662101, | |
| "grad_norm": 0.05691586434841156, | |
| "learning_rate": 0.0001, | |
| "loss": 0.02, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.748858447488584, | |
| "grad_norm": 0.05423538759350777, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0196, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.931506849315069, | |
| "grad_norm": 0.10058747231960297, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0206, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.114155251141552, | |
| "grad_norm": 0.064676932990551, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0177, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.296803652968037, | |
| "grad_norm": 0.08128379285335541, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0157, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.47945205479452, | |
| "grad_norm": 0.10474538058042526, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0169, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.662100456621005, | |
| "grad_norm": 0.09420209378004074, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0207, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.844748858447488, | |
| "grad_norm": 0.07704417407512665, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.027397260273973, | |
| "grad_norm": 0.044411078095436096, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.210045662100456, | |
| "grad_norm": 0.09763959795236588, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0131, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.392694063926941, | |
| "grad_norm": 0.08706251531839371, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0146, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.575342465753424, | |
| "grad_norm": 0.10404196381568909, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0169, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.757990867579909, | |
| "grad_norm": 0.1037658154964447, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0165, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.940639269406392, | |
| "grad_norm": 0.07572110742330551, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.123287671232877, | |
| "grad_norm": 0.06740553677082062, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0139, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.30593607305936, | |
| "grad_norm": 0.08043979108333588, | |
| "learning_rate": 0.0001, | |
| "loss": 0.014, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.488584474885845, | |
| "grad_norm": 0.06607798486948013, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0136, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.671232876712329, | |
| "grad_norm": 0.11705009639263153, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0146, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.853881278538813, | |
| "grad_norm": 0.04560132324695587, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0154, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.036529680365296, | |
| "grad_norm": 0.05037812143564224, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0129, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.219178082191782, | |
| "grad_norm": 0.07135117053985596, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0109, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.401826484018265, | |
| "grad_norm": 0.05977578088641167, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.584474885844749, | |
| "grad_norm": 0.07411223649978638, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0111, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.767123287671232, | |
| "grad_norm": 0.08515261113643646, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.949771689497716, | |
| "grad_norm": 0.07383166998624802, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.132420091324201, | |
| "grad_norm": 0.041954681277275085, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.315068493150685, | |
| "grad_norm": 0.09089387208223343, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.497716894977168, | |
| "grad_norm": 0.08716876059770584, | |
| "learning_rate": 0.0001, | |
| "loss": 0.011, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.680365296803654, | |
| "grad_norm": 0.04927799850702286, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0106, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.863013698630137, | |
| "grad_norm": 0.05259260907769203, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0111, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.045662100456621, | |
| "grad_norm": 0.04412449151277542, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0106, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.228310502283104, | |
| "grad_norm": 0.05673637241125107, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0087, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.41095890410959, | |
| "grad_norm": 0.04577219486236572, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0094, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.593607305936073, | |
| "grad_norm": 0.05691211298108101, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0098, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.776255707762557, | |
| "grad_norm": 0.05354565382003784, | |
| "learning_rate": 0.0001, | |
| "loss": 0.01, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.95890410958904, | |
| "grad_norm": 0.06758158653974533, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0104, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 10900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.136418741180006e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |