| { | |
| "best_metric": 1.4391453266143799, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02960331557134399, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "grad_norm": 1.1244513988494873, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "eval_loss": 1.6248306035995483, | |
| "eval_runtime": 83.4696, | |
| "eval_samples_per_second": 4.265, | |
| "eval_steps_per_second": 2.133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002368265245707519, | |
| "grad_norm": 0.7392627000808716, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7623, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003552397868561279, | |
| "grad_norm": 0.8358471393585205, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6948, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004736530491415038, | |
| "grad_norm": 1.1530704498291016, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7117, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005920663114268798, | |
| "grad_norm": 0.7539251446723938, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005920663114268798, | |
| "eval_loss": 1.614780068397522, | |
| "eval_runtime": 85.7408, | |
| "eval_samples_per_second": 4.152, | |
| "eval_steps_per_second": 2.076, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007104795737122558, | |
| "grad_norm": 1.0595225095748901, | |
| "learning_rate": 0.00012, | |
| "loss": 1.151, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008288928359976317, | |
| "grad_norm": 0.8684213161468506, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009473060982830076, | |
| "grad_norm": 0.8159509301185608, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8195, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010657193605683837, | |
| "grad_norm": 0.8147774338722229, | |
| "learning_rate": 0.00018, | |
| "loss": 1.802, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011841326228537596, | |
| "grad_norm": 1.0804157257080078, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0283, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011841326228537596, | |
| "eval_loss": 1.555640697479248, | |
| "eval_runtime": 81.9567, | |
| "eval_samples_per_second": 4.344, | |
| "eval_steps_per_second": 2.172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013025458851391355, | |
| "grad_norm": 0.9944465160369873, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.9366, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014209591474245116, | |
| "grad_norm": 1.5967128276824951, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.2509, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015393724097098875, | |
| "grad_norm": 0.6631534099578857, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.1633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016577856719952634, | |
| "grad_norm": 0.5836420655250549, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.0428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.8438186645507812, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6668, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "eval_loss": 1.4639616012573242, | |
| "eval_runtime": 87.2922, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 2.039, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018946121965660152, | |
| "grad_norm": 1.0537880659103394, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.756, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020130254588513915, | |
| "grad_norm": 1.179638147354126, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.8299, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021314387211367674, | |
| "grad_norm": 0.7309013605117798, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.1362, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022498519834221433, | |
| "grad_norm": 0.7479605674743652, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023682652457075192, | |
| "grad_norm": 0.629127025604248, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9961, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023682652457075192, | |
| "eval_loss": 1.4427205324172974, | |
| "eval_runtime": 82.6509, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 2.154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02486678507992895, | |
| "grad_norm": 0.8581761121749878, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5749, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02605091770278271, | |
| "grad_norm": 0.8760268688201904, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6816, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027235050325636473, | |
| "grad_norm": 0.6158702969551086, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6894, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028419182948490232, | |
| "grad_norm": 1.123356580734253, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8956, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02960331557134399, | |
| "grad_norm": 1.8370057344436646, | |
| "learning_rate": 0.0, | |
| "loss": 1.9829, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02960331557134399, | |
| "eval_loss": 1.4391453266143799, | |
| "eval_runtime": 85.2663, | |
| "eval_samples_per_second": 4.175, | |
| "eval_steps_per_second": 2.088, | |
| "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": 347248838836224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |