| { | |
| "best_metric": 1.9884905815124512, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.028540849090260435, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014270424545130217, | |
| "eval_loss": 2.0832698345184326, | |
| "eval_runtime": 65.5341, | |
| "eval_samples_per_second": 9.003, | |
| "eval_steps_per_second": 2.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004281127363539065, | |
| "grad_norm": 0.7657609581947327, | |
| "learning_rate": 0.00012, | |
| "loss": 8.1135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007135212272565109, | |
| "eval_loss": 2.0654828548431396, | |
| "eval_runtime": 65.9922, | |
| "eval_samples_per_second": 8.94, | |
| "eval_steps_per_second": 2.243, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00856225472707813, | |
| "grad_norm": 0.6937746405601501, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 7.9043, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012843382090617196, | |
| "grad_norm": 0.9151648283004761, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.0914, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014270424545130217, | |
| "eval_loss": 2.0186924934387207, | |
| "eval_runtime": 65.97, | |
| "eval_samples_per_second": 8.943, | |
| "eval_steps_per_second": 2.243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01712450945415626, | |
| "grad_norm": 0.6517742276191711, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 8.3796, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021405636817695327, | |
| "grad_norm": 0.6615819931030273, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.1922, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021405636817695327, | |
| "eval_loss": 1.9932925701141357, | |
| "eval_runtime": 66.361, | |
| "eval_samples_per_second": 8.891, | |
| "eval_steps_per_second": 2.23, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025686764181234393, | |
| "grad_norm": 0.4475820064544678, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 8.1842, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028540849090260435, | |
| "eval_loss": 1.9884905815124512, | |
| "eval_runtime": 66.3425, | |
| "eval_samples_per_second": 8.893, | |
| "eval_steps_per_second": 2.231, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.613858577416192e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |