| { | |
| "best_metric": 0.8007434606552124, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.011981428785382657, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005990714392691329, | |
| "grad_norm": 0.3232486844062805, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0991, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005990714392691329, | |
| "eval_loss": 1.0628771781921387, | |
| "eval_runtime": 131.644, | |
| "eval_samples_per_second": 5.34, | |
| "eval_steps_per_second": 2.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011981428785382657, | |
| "grad_norm": 0.23657472431659698, | |
| "learning_rate": 4e-05, | |
| "loss": 1.067, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017972143178073986, | |
| "grad_norm": 0.28239014744758606, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023962857570765314, | |
| "grad_norm": 0.2843663990497589, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029953571963456643, | |
| "grad_norm": 0.2925613224506378, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029953571963456643, | |
| "eval_loss": 1.048013687133789, | |
| "eval_runtime": 130.2253, | |
| "eval_samples_per_second": 5.398, | |
| "eval_steps_per_second": 2.703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003594428635614797, | |
| "grad_norm": 0.34553882479667664, | |
| "learning_rate": 0.00012, | |
| "loss": 0.9914, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00419350007488393, | |
| "grad_norm": 0.33732372522354126, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0054, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004792571514153063, | |
| "grad_norm": 0.41986826062202454, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9714, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005391642953422196, | |
| "grad_norm": 0.28040024638175964, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0071, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0059907143926913285, | |
| "grad_norm": 0.3935498297214508, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9173, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0059907143926913285, | |
| "eval_loss": 0.9063844680786133, | |
| "eval_runtime": 129.7311, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 2.713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006589785831960461, | |
| "grad_norm": 0.31022465229034424, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.8604, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007188857271229594, | |
| "grad_norm": 0.4046589732170105, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.9009, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007787928710498727, | |
| "grad_norm": 0.5031927824020386, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.876, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00838700014976786, | |
| "grad_norm": 0.4806121289730072, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.9419, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008986071589036993, | |
| "grad_norm": 0.35671281814575195, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.8153, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008986071589036993, | |
| "eval_loss": 0.8290239572525024, | |
| "eval_runtime": 130.5907, | |
| "eval_samples_per_second": 5.383, | |
| "eval_steps_per_second": 2.695, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009585143028306126, | |
| "grad_norm": 0.3003746569156647, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8158, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010184214467575258, | |
| "grad_norm": 0.2912845015525818, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.804, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010783285906844391, | |
| "grad_norm": 0.31682682037353516, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.8039, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011382357346113524, | |
| "grad_norm": 0.3057119846343994, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.8771, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011981428785382657, | |
| "grad_norm": 0.28653478622436523, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.8927, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011981428785382657, | |
| "eval_loss": 0.8007434606552124, | |
| "eval_runtime": 135.9653, | |
| "eval_samples_per_second": 5.17, | |
| "eval_steps_per_second": 2.589, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 6591291693465600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |