| { |
| "best_metric": 0.1569606214761734, |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", |
| "epoch": 0.12053638692180202, |
| "eval_steps": 100, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006026819346090101, |
| "eval_loss": 2.890679121017456, |
| "eval_runtime": 19.5541, |
| "eval_samples_per_second": 35.747, |
| "eval_steps_per_second": 17.899, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.006026819346090101, |
| "grad_norm": 16.7128963470459, |
| "learning_rate": 2.5e-06, |
| "loss": 2.8187, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.012053638692180202, |
| "grad_norm": 5.472095966339111, |
| "learning_rate": 5e-06, |
| "loss": 2.6526, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.018080458038270304, |
| "grad_norm": 6.024045944213867, |
| "learning_rate": 7.5e-06, |
| "loss": 2.1175, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.024107277384360404, |
| "grad_norm": 7.031100749969482, |
| "learning_rate": 1e-05, |
| "loss": 1.6338, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.030134096730450505, |
| "grad_norm": 4.758700847625732, |
| "learning_rate": 1.25e-05, |
| "loss": 0.9916, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03616091607654061, |
| "grad_norm": 2.474622964859009, |
| "learning_rate": 1.5e-05, |
| "loss": 0.3518, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.042187735422630705, |
| "grad_norm": 2.6985368728637695, |
| "learning_rate": 1.75e-05, |
| "loss": 0.417, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.04821455476872081, |
| "grad_norm": 1.3015024662017822, |
| "learning_rate": 2e-05, |
| "loss": 0.2501, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.054241374114810906, |
| "grad_norm": 1.4973636865615845, |
| "learning_rate": 2.25e-05, |
| "loss": 0.1989, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.06026819346090101, |
| "grad_norm": 0.7235045433044434, |
| "learning_rate": 2.5e-05, |
| "loss": 0.3077, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06026819346090101, |
| "eval_loss": 0.17322567105293274, |
| "eval_runtime": 19.4751, |
| "eval_samples_per_second": 35.892, |
| "eval_steps_per_second": 17.972, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06629501280699111, |
| "grad_norm": 2.4882545471191406, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.5264, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.07232183215308122, |
| "grad_norm": 0.6996169686317444, |
| "learning_rate": 3e-05, |
| "loss": 0.2292, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0783486514991713, |
| "grad_norm": 0.5811498165130615, |
| "learning_rate": 3.2500000000000004e-05, |
| "loss": 0.3182, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.08437547084526141, |
| "grad_norm": 0.24197261035442352, |
| "learning_rate": 3.5e-05, |
| "loss": 0.2114, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.09040229019135151, |
| "grad_norm": 0.4716508090496063, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.1169, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09642910953744162, |
| "grad_norm": 0.48725882172584534, |
| "learning_rate": 4e-05, |
| "loss": 0.1013, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10245592888353172, |
| "grad_norm": 0.35950130224227905, |
| "learning_rate": 4.25e-05, |
| "loss": 0.2313, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.10848274822962181, |
| "grad_norm": 0.43237921595573425, |
| "learning_rate": 4.5e-05, |
| "loss": 0.2109, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.11450956757571192, |
| "grad_norm": 1.0144596099853516, |
| "learning_rate": 4.75e-05, |
| "loss": 0.3166, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.12053638692180202, |
| "grad_norm": 0.6670956015586853, |
| "learning_rate": 5e-05, |
| "loss": 0.328, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12053638692180202, |
| "eval_loss": 0.1569606214761734, |
| "eval_runtime": 19.5861, |
| "eval_samples_per_second": 35.688, |
| "eval_steps_per_second": 17.87, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": 7747803637874688.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
