| { |
| "best_metric": 11.931747436523438, |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", |
| "epoch": 0.1423487544483986, |
| "eval_steps": 5, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004744958481613286, |
| "eval_loss": 11.932116508483887, |
| "eval_runtime": 0.8506, |
| "eval_samples_per_second": 209.264, |
| "eval_steps_per_second": 52.904, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.014234875444839857, |
| "grad_norm": 0.02677612006664276, |
| "learning_rate": 0.00012, |
| "loss": 11.9319, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.02372479240806643, |
| "eval_loss": 11.932097434997559, |
| "eval_runtime": 0.8543, |
| "eval_samples_per_second": 208.355, |
| "eval_steps_per_second": 52.674, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.028469750889679714, |
| "grad_norm": 0.03796449303627014, |
| "learning_rate": 0.0001992114701314478, |
| "loss": 11.9311, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.042704626334519574, |
| "grad_norm": 0.03717769309878349, |
| "learning_rate": 0.00018763066800438636, |
| "loss": 11.9322, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.04744958481613286, |
| "eval_loss": 11.93195915222168, |
| "eval_runtime": 0.9139, |
| "eval_samples_per_second": 194.77, |
| "eval_steps_per_second": 49.24, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05693950177935943, |
| "grad_norm": 0.037996333092451096, |
| "learning_rate": 0.000163742398974869, |
| "loss": 11.9331, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0711743772241993, |
| "grad_norm": 0.040662698447704315, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 11.9289, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0711743772241993, |
| "eval_loss": 11.931912422180176, |
| "eval_runtime": 0.8673, |
| "eval_samples_per_second": 205.239, |
| "eval_steps_per_second": 51.886, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.08540925266903915, |
| "grad_norm": 0.04711554944515228, |
| "learning_rate": 9.372094804706867e-05, |
| "loss": 11.9324, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.09489916963226572, |
| "eval_loss": 11.931827545166016, |
| "eval_runtime": 0.8984, |
| "eval_samples_per_second": 198.131, |
| "eval_steps_per_second": 50.089, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.099644128113879, |
| "grad_norm": 0.042521167546510696, |
| "learning_rate": 5.7422070843492734e-05, |
| "loss": 11.9327, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.11387900355871886, |
| "grad_norm": 0.04662325605750084, |
| "learning_rate": 2.7103137257858868e-05, |
| "loss": 11.9348, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.11862396204033215, |
| "eval_loss": 11.931800842285156, |
| "eval_runtime": 0.8704, |
| "eval_samples_per_second": 204.515, |
| "eval_steps_per_second": 51.703, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12811387900355872, |
| "grad_norm": 0.05982173606753349, |
| "learning_rate": 7.022351411174866e-06, |
| "loss": 11.9331, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.1423487544483986, |
| "grad_norm": 0.03850724920630455, |
| "learning_rate": 0.0, |
| "loss": 11.9307, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1423487544483986, |
| "eval_loss": 11.931747436523438, |
| "eval_runtime": 0.8532, |
| "eval_samples_per_second": 208.63, |
| "eval_steps_per_second": 52.744, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "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": 22484090880.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
