| { | |
| "best_metric": 3.6852939128875732, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0017573148229505316, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.029259291802126e-05, | |
| "grad_norm": 9.411466598510742, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.029259291802126e-05, | |
| "eval_loss": 7.7762651443481445, | |
| "eval_runtime": 4432.0766, | |
| "eval_samples_per_second": 1.352, | |
| "eval_steps_per_second": 0.676, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014058518583604253, | |
| "grad_norm": 9.495089530944824, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2361, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021087777875406378, | |
| "grad_norm": 8.74798583984375, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.1303, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00028117037167208506, | |
| "grad_norm": 4.712350845336914, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.4543, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00035146296459010633, | |
| "grad_norm": 4.159116744995117, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.0895, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042175555750812756, | |
| "grad_norm": 3.948648691177368, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.9215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004920481504261489, | |
| "grad_norm": 4.281744003295898, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.1163, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005623407433441701, | |
| "grad_norm": 4.81821346282959, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.53, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006326333362621913, | |
| "grad_norm": 4.640680313110352, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.731, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007029259291802127, | |
| "grad_norm": 4.920532703399658, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.3617, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007732185220982339, | |
| "grad_norm": 4.455087661743164, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.7523, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008435111150162551, | |
| "grad_norm": 3.681004285812378, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.9495, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009138037079342764, | |
| "grad_norm": 3.6873984336853027, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.2534, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009840963008522978, | |
| "grad_norm": 4.170083522796631, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.6071, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001054388893770319, | |
| "grad_norm": 3.7524523735046387, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.2183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011246814866883402, | |
| "grad_norm": 3.95082426071167, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.6198, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011949740796063616, | |
| "grad_norm": 4.456296920776367, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 3.3993, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012652666725243827, | |
| "grad_norm": 4.209654808044434, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.1265, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001335559265442404, | |
| "grad_norm": 4.037990093231201, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 3.7803, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014058518583604253, | |
| "grad_norm": 4.132318496704102, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.8329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014761444512784464, | |
| "grad_norm": 4.986948490142822, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 4.0136, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015464370441964678, | |
| "grad_norm": 3.795536518096924, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.6991, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016167296371144891, | |
| "grad_norm": 4.052053451538086, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.9433, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0016870222300325102, | |
| "grad_norm": 3.4409587383270264, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.2573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017573148229505316, | |
| "grad_norm": 4.064533710479736, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.4339, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017573148229505316, | |
| "eval_loss": 3.6852939128875732, | |
| "eval_runtime": 4443.7138, | |
| "eval_samples_per_second": 1.348, | |
| "eval_steps_per_second": 0.674, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.11806271012864e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |