| { | |
| "best_metric": 1.639454960823059, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09715812484819043, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048579062424095217, | |
| "eval_loss": 2.5925121307373047, | |
| "eval_runtime": 51.7124, | |
| "eval_samples_per_second": 16.766, | |
| "eval_steps_per_second": 4.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004857906242409522, | |
| "grad_norm": 14.00100326538086, | |
| "learning_rate": 4.2600000000000005e-05, | |
| "loss": 3.0736, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009715812484819043, | |
| "grad_norm": 12.023590087890625, | |
| "learning_rate": 8.520000000000001e-05, | |
| "loss": 2.3164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014573718727228565, | |
| "grad_norm": 25.465974807739258, | |
| "learning_rate": 0.0001278, | |
| "loss": 2.5703, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019431624969638087, | |
| "grad_norm": 14.983630180358887, | |
| "learning_rate": 0.00017040000000000002, | |
| "loss": 2.9312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024289531212047608, | |
| "grad_norm": 18.844684600830078, | |
| "learning_rate": 0.000213, | |
| "loss": 3.0475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.024289531212047608, | |
| "eval_loss": 1.639454960823059, | |
| "eval_runtime": 51.7386, | |
| "eval_samples_per_second": 16.757, | |
| "eval_steps_per_second": 4.194, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02914743745445713, | |
| "grad_norm": 9.967033386230469, | |
| "learning_rate": 0.00021274057135267128, | |
| "loss": 2.881, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03400534369686665, | |
| "grad_norm": 13.58944320678711, | |
| "learning_rate": 0.00021196354932097723, | |
| "loss": 2.4333, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03886324993927617, | |
| "grad_norm": 24.828699111938477, | |
| "learning_rate": 0.0002106727194781503, | |
| "loss": 3.1402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04372115618168569, | |
| "grad_norm": 51.00019454956055, | |
| "learning_rate": 0.00020887437061743096, | |
| "loss": 3.3349, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.048579062424095217, | |
| "grad_norm": 26.764297485351562, | |
| "learning_rate": 0.00020657726411369925, | |
| "loss": 3.5652, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.048579062424095217, | |
| "eval_loss": 2.1433684825897217, | |
| "eval_runtime": 51.7778, | |
| "eval_samples_per_second": 16.745, | |
| "eval_steps_per_second": 4.191, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.053436968666504735, | |
| "grad_norm": 20.774890899658203, | |
| "learning_rate": 0.000203792591238937, | |
| "loss": 3.2651, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05829487490891426, | |
| "grad_norm": 13.955368041992188, | |
| "learning_rate": 0.0002005339186394757, | |
| "loss": 2.3564, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06315278115132378, | |
| "grad_norm": 20.711078643798828, | |
| "learning_rate": 0.00019681712224065936, | |
| "loss": 3.2759, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0680106873937333, | |
| "grad_norm": 20.040428161621094, | |
| "learning_rate": 0.0001926603099009319, | |
| "loss": 3.2425, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07286859363614283, | |
| "grad_norm": 50.84387969970703, | |
| "learning_rate": 0.00018808373319217114, | |
| "loss": 3.6393, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07286859363614283, | |
| "eval_loss": 1.8135055303573608, | |
| "eval_runtime": 51.7534, | |
| "eval_samples_per_second": 16.753, | |
| "eval_steps_per_second": 4.193, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07772649987855235, | |
| "grad_norm": 15.678354263305664, | |
| "learning_rate": 0.00018310968873606635, | |
| "loss": 3.1187, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08258440612096186, | |
| "grad_norm": 27.940187454223633, | |
| "learning_rate": 0.0001777624095772184, | |
| "loss": 2.4375, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08744231236337138, | |
| "grad_norm": 22.329130172729492, | |
| "learning_rate": 0.0001720679471221826, | |
| "loss": 3.5057, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09230021860578091, | |
| "grad_norm": 21.67806053161621, | |
| "learning_rate": 0.00016605404421963453, | |
| "loss": 3.6538, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09715812484819043, | |
| "grad_norm": 19.599658966064453, | |
| "learning_rate": 0.00015975, | |
| "loss": 3.1059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09715812484819043, | |
| "eval_loss": 1.7558817863464355, | |
| "eval_runtime": 51.7429, | |
| "eval_samples_per_second": 16.756, | |
| "eval_steps_per_second": 4.194, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.57749502246912e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |