| { | |
| "best_metric": 6.912273406982422, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01188407088848285, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000475362835539314, | |
| "grad_norm": 0.2889825105667114, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9373, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000475362835539314, | |
| "eval_loss": 6.941147327423096, | |
| "eval_runtime": 0.7116, | |
| "eval_samples_per_second": 70.261, | |
| "eval_steps_per_second": 18.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000950725671078628, | |
| "grad_norm": 0.2633208632469177, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9376, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014260885066179419, | |
| "grad_norm": 0.2506893277168274, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001901451342157256, | |
| "grad_norm": 0.24618133902549744, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00237681417769657, | |
| "grad_norm": 0.2463768869638443, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028521770132358838, | |
| "grad_norm": 0.24844573438167572, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003327539848775198, | |
| "grad_norm": 0.23925140500068665, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9312, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003802902684314512, | |
| "grad_norm": 0.22544139623641968, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004278265519853826, | |
| "grad_norm": 0.21495969593524933, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9319, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00475362835539314, | |
| "grad_norm": 0.21318794786930084, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0052289911909324535, | |
| "grad_norm": 0.18213364481925964, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0057043540264717675, | |
| "grad_norm": 0.1623869091272354, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9348, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0061797168620110815, | |
| "grad_norm": 0.34758180379867554, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9202, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006655079697550396, | |
| "grad_norm": 0.3087834119796753, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9181, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00713044253308971, | |
| "grad_norm": 0.2853550612926483, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9149, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007605805368629024, | |
| "grad_norm": 0.2866442799568176, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008081168204168338, | |
| "grad_norm": 0.2917479872703552, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9145, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008556531039707651, | |
| "grad_norm": 0.2843560576438904, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9124, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009031893875246966, | |
| "grad_norm": 0.2888680398464203, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9124, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00950725671078628, | |
| "grad_norm": 0.2755052149295807, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009982619546325594, | |
| "grad_norm": 0.26480522751808167, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9125, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010457982381864907, | |
| "grad_norm": 0.25958582758903503, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9121, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010933345217404222, | |
| "grad_norm": 0.2043898105621338, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.919, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011408708052943535, | |
| "grad_norm": 0.17020662128925323, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9238, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01188407088848285, | |
| "grad_norm": 0.24424903094768524, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01188407088848285, | |
| "eval_loss": 6.912273406982422, | |
| "eval_runtime": 0.1347, | |
| "eval_samples_per_second": 371.293, | |
| "eval_steps_per_second": 96.536, | |
| "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": 3118662336512.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |