| { | |
| "best_metric": 1.445395827293396, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004064049418840933, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 0.42466479539871216, | |
| "learning_rate": 2e-05, | |
| "loss": 6.5745, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 1.7880605459213257, | |
| "eval_runtime": 541.8403, | |
| "eval_samples_per_second": 4.782, | |
| "eval_steps_per_second": 2.392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 0.4982253313064575, | |
| "learning_rate": 4e-05, | |
| "loss": 7.4698, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.4963212311267853, | |
| "learning_rate": 6e-05, | |
| "loss": 7.1837, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 0.6705942153930664, | |
| "learning_rate": 8e-05, | |
| "loss": 7.6109, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 0.5894594788551331, | |
| "learning_rate": 0.0001, | |
| "loss": 7.338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "eval_loss": 1.7698947191238403, | |
| "eval_runtime": 539.5874, | |
| "eval_samples_per_second": 4.802, | |
| "eval_steps_per_second": 2.402, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 0.7001488208770752, | |
| "learning_rate": 0.00012, | |
| "loss": 6.6551, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 0.676232099533081, | |
| "learning_rate": 0.00014, | |
| "loss": 5.805, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 1.1085022687911987, | |
| "learning_rate": 0.00016, | |
| "loss": 7.0894, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 1.3170788288116455, | |
| "learning_rate": 0.00018, | |
| "loss": 7.0139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 2.0295796394348145, | |
| "learning_rate": 0.0002, | |
| "loss": 7.8076, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 1.6063923835754395, | |
| "eval_runtime": 541.2996, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 2.394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017881817442900105, | |
| "grad_norm": 1.4203264713287354, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.0159, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 1.2493367195129395, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 7.1809, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "grad_norm": 2.142144203186035, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.2994, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 2.612400770187378, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.3049, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 2.3758747577667236, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.4849, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "eval_loss": 1.531221866607666, | |
| "eval_runtime": 540.1619, | |
| "eval_samples_per_second": 4.797, | |
| "eval_steps_per_second": 2.399, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 2.8996591567993164, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.7643, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027635536048118345, | |
| "grad_norm": 3.941735029220581, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 6.3934, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 2.863781690597534, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 6.2186, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003088677558319109, | |
| "grad_norm": 3.3763999938964844, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 5.9787, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 2.3317129611968994, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 5.9861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 1.4639239311218262, | |
| "eval_runtime": 543.415, | |
| "eval_samples_per_second": 4.768, | |
| "eval_steps_per_second": 2.385, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 2.345309019088745, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 5.7032, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 2.150189161300659, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.6857, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037389254653336585, | |
| "grad_norm": 2.1052958965301514, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.8889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 2.2360198497772217, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.5735, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 3.2359986305236816, | |
| "learning_rate": 0.0, | |
| "loss": 5.897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "eval_loss": 1.445395827293396, | |
| "eval_runtime": 540.7082, | |
| "eval_samples_per_second": 4.792, | |
| "eval_steps_per_second": 2.397, | |
| "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": 1.278459991031808e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |