| { | |
| "best_metric": 3.7718515396118164, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.01805869074492099, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009029345372460496, | |
| "eval_loss": 4.7750372886657715, | |
| "eval_runtime": 216.269, | |
| "eval_samples_per_second": 2.159, | |
| "eval_steps_per_second": 1.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002708803611738149, | |
| "grad_norm": 0.7688174843788147, | |
| "learning_rate": 3e-05, | |
| "loss": 4.8361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "eval_loss": 4.754970550537109, | |
| "eval_runtime": 213.3266, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 1.097, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005417607223476298, | |
| "grad_norm": 0.8867765665054321, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008126410835214447, | |
| "grad_norm": 0.9143892526626587, | |
| "learning_rate": 9e-05, | |
| "loss": 4.2652, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "eval_loss": 4.398805618286133, | |
| "eval_runtime": 215.101, | |
| "eval_samples_per_second": 2.171, | |
| "eval_steps_per_second": 1.088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010835214446952596, | |
| "grad_norm": 0.947878897190094, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.128, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 1.2918604612350464, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.2702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "eval_loss": 4.007048606872559, | |
| "eval_runtime": 215.49, | |
| "eval_samples_per_second": 2.167, | |
| "eval_steps_per_second": 1.086, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016252821670428894, | |
| "grad_norm": 1.323457956314087, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.1544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "eval_loss": 3.7718515396118164, | |
| "eval_runtime": 214.2875, | |
| "eval_samples_per_second": 2.179, | |
| "eval_steps_per_second": 1.092, | |
| "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": 1.4155533539868672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |