| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 163, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019979171608653924, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019852201067560606, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001961129783872301, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.000192592477719385, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018800122039735358, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018239230057575542, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017583058084785625, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016839194216246108, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016016240632249224, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001512371412128424, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014171936026123168, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00013171912885891063, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00012135209154397962, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011073813466641632, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.92618653335837e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.864790845602039e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.09839651807560063, | |
| "learning_rate": 6.82808711410894e-05, | |
| "loss": 0.9838, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.10800711797719255, | |
| "learning_rate": 5.828063973876834e-05, | |
| "loss": 0.9641, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.10290376530473021, | |
| "learning_rate": 4.876285878715764e-05, | |
| "loss": 0.9273, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.10186139886850558, | |
| "learning_rate": 3.9837593677507726e-05, | |
| "loss": 0.9404, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.10144888390670637, | |
| "learning_rate": 3.160805783753897e-05, | |
| "loss": 0.9338, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08752798479645085, | |
| "learning_rate": 2.4169419152143768e-05, | |
| "loss": 0.9566, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.09946507647649253, | |
| "learning_rate": 1.7607699424244585e-05, | |
| "loss": 0.9439, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.09362373509551941, | |
| "learning_rate": 1.1998779602646437e-05, | |
| "loss": 0.93, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.09941944273675073, | |
| "learning_rate": 7.40752228061502e-06, | |
| "loss": 0.9089, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.10732869076286236, | |
| "learning_rate": 3.887021612769936e-06, | |
| "loss": 0.9399, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.09376518103530347, | |
| "learning_rate": 1.4779893243939359e-06, | |
| "loss": 0.8965, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.09129164224191258, | |
| "learning_rate": 2.082839134607828e-07, | |
| "loss": 0.936, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1432331800460815, | |
| "eval_runtime": 200.5256, | |
| "eval_samples_per_second": 11.52, | |
| "eval_steps_per_second": 0.723, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 163, | |
| "total_flos": 2037837427900416.0, | |
| "train_loss": 0.36281629574079455, | |
| "train_runtime": 1284.7614, | |
| "train_samples_per_second": 16.222, | |
| "train_steps_per_second": 0.127 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 163, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 2037837427900416.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |