| { | |
| "best_metric": 3.831801176071167, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004202033784351626, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016808135137406504, | |
| "grad_norm": 0.6703398823738098, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016808135137406504, | |
| "eval_loss": 4.348113536834717, | |
| "eval_runtime": 216.1675, | |
| "eval_samples_per_second": 11.588, | |
| "eval_steps_per_second": 5.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033616270274813007, | |
| "grad_norm": 0.69629967212677, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4925, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005042440541221952, | |
| "grad_norm": 0.7081684470176697, | |
| "learning_rate": 6e-05, | |
| "loss": 4.2426, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006723254054962601, | |
| "grad_norm": 0.7529476284980774, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008404067568703252, | |
| "grad_norm": 0.7710140347480774, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2267, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008404067568703252, | |
| "eval_loss": 4.336910724639893, | |
| "eval_runtime": 211.9166, | |
| "eval_samples_per_second": 11.821, | |
| "eval_steps_per_second": 5.913, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010084881082443903, | |
| "grad_norm": 1.1266764402389526, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7829, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011765694596184554, | |
| "grad_norm": 0.8971369862556458, | |
| "learning_rate": 0.00014, | |
| "loss": 5.3763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013446508109925203, | |
| "grad_norm": 0.8245266675949097, | |
| "learning_rate": 0.00016, | |
| "loss": 4.3786, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015127321623665854, | |
| "grad_norm": 0.9381071925163269, | |
| "learning_rate": 0.00018, | |
| "loss": 4.9129, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016808135137406505, | |
| "grad_norm": 1.246238350868225, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016808135137406505, | |
| "eval_loss": 4.148122310638428, | |
| "eval_runtime": 211.8, | |
| "eval_samples_per_second": 11.827, | |
| "eval_steps_per_second": 5.916, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018488948651147156, | |
| "grad_norm": 0.9299777150154114, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.4881, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020169762164887806, | |
| "grad_norm": 1.18503999710083, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.0163, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021850575678628455, | |
| "grad_norm": 1.2439167499542236, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.0226, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002353138919236911, | |
| "grad_norm": 0.9216750264167786, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.3341, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025212202706109757, | |
| "grad_norm": 0.8185566663742065, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.4702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025212202706109757, | |
| "eval_loss": 3.90740704536438, | |
| "eval_runtime": 211.8663, | |
| "eval_samples_per_second": 11.823, | |
| "eval_steps_per_second": 5.914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026893016219850406, | |
| "grad_norm": 0.7571693658828735, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.0438, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002857382973359106, | |
| "grad_norm": 1.0295147895812988, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.6677, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030254643247331708, | |
| "grad_norm": 0.9374280571937561, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.2293, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003193545676107236, | |
| "grad_norm": 0.9331271648406982, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.5881, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003361627027481301, | |
| "grad_norm": 0.8545352816581726, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003361627027481301, | |
| "eval_loss": 3.8484609127044678, | |
| "eval_runtime": 209.7391, | |
| "eval_samples_per_second": 11.943, | |
| "eval_steps_per_second": 5.974, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003529708378855366, | |
| "grad_norm": 0.9038202166557312, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.2658, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003697789730229431, | |
| "grad_norm": 0.7761992812156677, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.4303, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.003865871081603496, | |
| "grad_norm": 0.9693357348442078, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.1018, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004033952432977561, | |
| "grad_norm": 0.9627821445465088, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 3.7486, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004202033784351626, | |
| "grad_norm": 1.1465263366699219, | |
| "learning_rate": 0.0, | |
| "loss": 4.3581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004202033784351626, | |
| "eval_loss": 3.831801176071167, | |
| "eval_runtime": 211.2104, | |
| "eval_samples_per_second": 11.86, | |
| "eval_steps_per_second": 5.932, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 645874745081856.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |