| { | |
| "best_metric": 1.7015981674194336, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.00975371860521824, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "eval_loss": 6.374954700469971, | |
| "eval_runtime": 159.0694, | |
| "eval_samples_per_second": 16.288, | |
| "eval_steps_per_second": 4.074, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 3.529289484024048, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4985, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 4.591853618621826, | |
| "eval_runtime": 159.244, | |
| "eval_samples_per_second": 16.271, | |
| "eval_steps_per_second": 4.069, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 3.607182502746582, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 3.0397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 6.760822772979736, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.5328, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 2.051936388015747, | |
| "eval_runtime": 159.2955, | |
| "eval_samples_per_second": 16.265, | |
| "eval_steps_per_second": 4.068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 2.0285325050354004, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.7677, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 1.3885489702224731, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "eval_loss": 1.8683792352676392, | |
| "eval_runtime": 159.3475, | |
| "eval_samples_per_second": 16.26, | |
| "eval_steps_per_second": 4.067, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005852231163130944, | |
| "grad_norm": 1.2759499549865723, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.6451, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006502479070145493, | |
| "eval_loss": 1.7570436000823975, | |
| "eval_runtime": 159.2372, | |
| "eval_samples_per_second": 16.271, | |
| "eval_steps_per_second": 4.069, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006827603023652768, | |
| "grad_norm": 1.436516523361206, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.6213, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007802974884174592, | |
| "grad_norm": 1.3249201774597168, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.5169, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "eval_loss": 1.7124468088150024, | |
| "eval_runtime": 159.3102, | |
| "eval_samples_per_second": 16.264, | |
| "eval_steps_per_second": 4.068, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008778346744696415, | |
| "grad_norm": 1.4247421026229858, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.5687, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00975371860521824, | |
| "grad_norm": 1.7823768854141235, | |
| "learning_rate": 0.0, | |
| "loss": 1.6421, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00975371860521824, | |
| "eval_loss": 1.7015981674194336, | |
| "eval_runtime": 159.1864, | |
| "eval_samples_per_second": 16.277, | |
| "eval_steps_per_second": 4.071, | |
| "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": 2.3198554436665344e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |