| { | |
| "best_metric": 1.0482399463653564, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1910828025477707, | |
| "eval_steps": 25, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10191082802547771, | |
| "grad_norm": 0.3101247251033783, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10191082802547771, | |
| "eval_loss": 1.4096554517745972, | |
| "eval_runtime": 2.2656, | |
| "eval_samples_per_second": 29.131, | |
| "eval_steps_per_second": 3.972, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.20382165605095542, | |
| "grad_norm": 0.29828256368637085, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3123, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3057324840764331, | |
| "grad_norm": 0.34790894389152527, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 1.4114, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.40764331210191085, | |
| "grad_norm": 0.27280497550964355, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 1.182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5095541401273885, | |
| "grad_norm": 0.3043956756591797, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 1.359, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6114649681528662, | |
| "grad_norm": 0.30795708298683167, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 1.2391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7133757961783439, | |
| "grad_norm": 0.24166040122509003, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 1.2003, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8152866242038217, | |
| "grad_norm": 0.3065624535083771, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 1.1695, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9171974522292994, | |
| "grad_norm": 0.30496659874916077, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.156, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0636942675159236, | |
| "grad_norm": 0.5713984966278076, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 1.7413, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1656050955414012, | |
| "grad_norm": 0.2910941243171692, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.9993, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.267515923566879, | |
| "grad_norm": 0.2529296278953552, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 1.0338, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3694267515923566, | |
| "grad_norm": 0.23656314611434937, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 1.0761, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4713375796178343, | |
| "grad_norm": 0.28531450033187866, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 1.022, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.573248407643312, | |
| "grad_norm": 0.2610785961151123, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 1.1219, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.6751592356687897, | |
| "grad_norm": 0.24870941042900085, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0424, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.7770700636942676, | |
| "grad_norm": 0.25813016295433044, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 1.0083, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.8789808917197452, | |
| "grad_norm": 0.23440974950790405, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.9885, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0254777070063694, | |
| "grad_norm": 0.3416347801685333, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 1.6163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.127388535031847, | |
| "grad_norm": 0.21394824981689453, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.9611, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.229299363057325, | |
| "grad_norm": 0.20293334126472473, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.9253, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.3312101910828025, | |
| "grad_norm": 0.22766590118408203, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 1.0335, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.43312101910828, | |
| "grad_norm": 0.22457292675971985, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9439, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.535031847133758, | |
| "grad_norm": 0.21028192341327667, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.996, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.6369426751592355, | |
| "grad_norm": 0.21007855236530304, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.9546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6369426751592355, | |
| "eval_loss": 1.0482399463653564, | |
| "eval_runtime": 2.2699, | |
| "eval_samples_per_second": 29.076, | |
| "eval_steps_per_second": 3.965, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.738853503184713, | |
| "grad_norm": 0.2180248200893402, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.9552, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.840764331210191, | |
| "grad_norm": 0.19627752900123596, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.9294, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.9426751592356686, | |
| "grad_norm": 0.46095138788223267, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 1.4176, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.089171974522293, | |
| "grad_norm": 0.2987149655818939, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 1.0826, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.1910828025477707, | |
| "grad_norm": 0.2547209560871124, | |
| "learning_rate": 0.0, | |
| "loss": 0.888, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.68704369229824e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |