| { | |
| "best_metric": 10.378952026367188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.0008469013995045627, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.823004665015209e-05, | |
| "eval_loss": 10.381486892700195, | |
| "eval_runtime": 81.3515, | |
| "eval_samples_per_second": 183.34, | |
| "eval_steps_per_second": 91.676, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.469013995045627e-05, | |
| "grad_norm": 0.027628980576992035, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3813, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014115023325076044, | |
| "eval_loss": 10.381342887878418, | |
| "eval_runtime": 80.9499, | |
| "eval_samples_per_second": 184.25, | |
| "eval_steps_per_second": 92.131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016938027990091254, | |
| "grad_norm": 0.0297038946300745, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3821, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002540704198513688, | |
| "grad_norm": 0.028719373047351837, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3796, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002823004665015209, | |
| "eval_loss": 10.380829811096191, | |
| "eval_runtime": 81.3269, | |
| "eval_samples_per_second": 183.396, | |
| "eval_steps_per_second": 91.704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003387605598018251, | |
| "grad_norm": 0.02849678508937359, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00042345069975228137, | |
| "grad_norm": 0.02935921773314476, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.382, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00042345069975228137, | |
| "eval_loss": 10.380049705505371, | |
| "eval_runtime": 81.6981, | |
| "eval_samples_per_second": 182.562, | |
| "eval_steps_per_second": 91.287, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005081408397027376, | |
| "grad_norm": 0.026194525882601738, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3807, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005646009330030418, | |
| "eval_loss": 10.379389762878418, | |
| "eval_runtime": 81.5372, | |
| "eval_samples_per_second": 182.923, | |
| "eval_steps_per_second": 91.467, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005928309796531939, | |
| "grad_norm": 0.03818906843662262, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3778, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006775211196036502, | |
| "grad_norm": 0.05160631984472275, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.377, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007057511662538022, | |
| "eval_loss": 10.379020690917969, | |
| "eval_runtime": 81.2289, | |
| "eval_samples_per_second": 183.617, | |
| "eval_steps_per_second": 91.815, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007622112595541064, | |
| "grad_norm": 0.02562943659722805, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3788, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0008469013995045627, | |
| "grad_norm": 0.042826201766729355, | |
| "learning_rate": 0.0, | |
| "loss": 10.3782, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008469013995045627, | |
| "eval_loss": 10.378952026367188, | |
| "eval_runtime": 81.8344, | |
| "eval_samples_per_second": 182.258, | |
| "eval_steps_per_second": 91.135, | |
| "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": 784536698880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |