| { | |
| "best_metric": 0.9468892216682434, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.002733454060887689, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013667270304438446, | |
| "grad_norm": 0.50577712059021, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013667270304438446, | |
| "eval_loss": 1.2357397079467773, | |
| "eval_runtime": 652.1609, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 2.363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027334540608876893, | |
| "grad_norm": 0.3678644299507141, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041001810913315336, | |
| "grad_norm": 0.49455997347831726, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0898, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005466908121775379, | |
| "grad_norm": 0.4921368658542633, | |
| "learning_rate": 4e-05, | |
| "loss": 1.069, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006833635152219223, | |
| "grad_norm": 0.43720000982284546, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1512, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006833635152219223, | |
| "eval_loss": 1.2310501337051392, | |
| "eval_runtime": 649.2905, | |
| "eval_samples_per_second": 4.745, | |
| "eval_steps_per_second": 2.373, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008200362182663067, | |
| "grad_norm": 0.5448674559593201, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0919, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009567089213106913, | |
| "grad_norm": 0.24378623068332672, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7775, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010933816243550757, | |
| "grad_norm": 0.347241073846817, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012300543273994601, | |
| "grad_norm": 0.4972077012062073, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0055, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013667270304438446, | |
| "grad_norm": 0.6088771224021912, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1217, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013667270304438446, | |
| "eval_loss": 1.1784987449645996, | |
| "eval_runtime": 649.9639, | |
| "eval_samples_per_second": 4.74, | |
| "eval_steps_per_second": 2.371, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001503399733488229, | |
| "grad_norm": 0.6936522126197815, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.0377, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016400724365326135, | |
| "grad_norm": 0.6066957116127014, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.1414, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001776745139576998, | |
| "grad_norm": 1.024498701095581, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9257, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019134178426213825, | |
| "grad_norm": 0.39579325914382935, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.7189, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002050090545665767, | |
| "grad_norm": 0.5156039595603943, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002050090545665767, | |
| "eval_loss": 1.0189374685287476, | |
| "eval_runtime": 651.4577, | |
| "eval_samples_per_second": 4.729, | |
| "eval_steps_per_second": 2.365, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021867632487101514, | |
| "grad_norm": 0.4737545847892761, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.9375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002323435951754536, | |
| "grad_norm": 0.37397414445877075, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.794, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0024601086547989203, | |
| "grad_norm": 2.7903082370758057, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.8632, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0025967813578433047, | |
| "grad_norm": 0.5934101343154907, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.7099, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002733454060887689, | |
| "grad_norm": 0.43005478382110596, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002733454060887689, | |
| "eval_loss": 0.9468892216682434, | |
| "eval_runtime": 652.2901, | |
| "eval_samples_per_second": 4.723, | |
| "eval_steps_per_second": 2.362, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 6138140389539840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |