| { | |
| "best_metric": 1.2455435991287231, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.03395585738539898, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016977928692699492, | |
| "eval_loss": 1.4329637289047241, | |
| "eval_runtime": 234.9554, | |
| "eval_samples_per_second": 5.278, | |
| "eval_steps_per_second": 1.319, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001697792869269949, | |
| "grad_norm": 1.341242790222168, | |
| "learning_rate": 4.12e-05, | |
| "loss": 1.4209, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003395585738539898, | |
| "grad_norm": 0.7306675910949707, | |
| "learning_rate": 8.24e-05, | |
| "loss": 1.338, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0050933786078098476, | |
| "grad_norm": 0.7428624629974365, | |
| "learning_rate": 0.0001236, | |
| "loss": 1.2576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006791171477079796, | |
| "grad_norm": 0.7021359205245972, | |
| "learning_rate": 0.0001648, | |
| "loss": 1.2015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008488964346349746, | |
| "grad_norm": 0.8103872537612915, | |
| "learning_rate": 0.000206, | |
| "loss": 1.2281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008488964346349746, | |
| "eval_loss": 1.2455830574035645, | |
| "eval_runtime": 237.2217, | |
| "eval_samples_per_second": 5.227, | |
| "eval_steps_per_second": 1.307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010186757215619695, | |
| "grad_norm": 0.7842703461647034, | |
| "learning_rate": 0.0002057490971767619, | |
| "loss": 1.2212, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011884550084889643, | |
| "grad_norm": 0.8670001029968262, | |
| "learning_rate": 0.00020499761108038175, | |
| "loss": 1.2051, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.013582342954159592, | |
| "grad_norm": 0.8176340460777283, | |
| "learning_rate": 0.00020374920287558198, | |
| "loss": 1.209, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.015280135823429542, | |
| "grad_norm": 1.0117417573928833, | |
| "learning_rate": 0.00020200995468164684, | |
| "loss": 1.2546, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01697792869269949, | |
| "grad_norm": 1.4239269495010376, | |
| "learning_rate": 0.00019978833994094855, | |
| "loss": 1.3016, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01697792869269949, | |
| "eval_loss": 1.3394960165023804, | |
| "eval_runtime": 236.5162, | |
| "eval_samples_per_second": 5.243, | |
| "eval_steps_per_second": 1.311, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01867572156196944, | |
| "grad_norm": 0.6853418350219727, | |
| "learning_rate": 0.00019709518213718787, | |
| "loss": 1.3013, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02037351443123939, | |
| "grad_norm": 0.7583730816841125, | |
| "learning_rate": 0.00019394360206446948, | |
| "loss": 1.1855, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.022071307300509338, | |
| "grad_norm": 0.8353321552276611, | |
| "learning_rate": 0.00019034895390411186, | |
| "loss": 1.2214, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.023769100169779286, | |
| "grad_norm": 0.8519904613494873, | |
| "learning_rate": 0.0001863287504206196, | |
| "loss": 1.2907, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.025466893039049237, | |
| "grad_norm": 0.7282483577728271, | |
| "learning_rate": 0.00018190257764125471, | |
| "loss": 1.1985, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.025466893039049237, | |
| "eval_loss": 1.2455435991287231, | |
| "eval_runtime": 237.1965, | |
| "eval_samples_per_second": 5.228, | |
| "eval_steps_per_second": 1.307, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.027164685908319185, | |
| "grad_norm": 0.8496482968330383, | |
| "learning_rate": 0.00017709199943488106, | |
| "loss": 1.1761, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.028862478777589132, | |
| "grad_norm": 0.7892032861709595, | |
| "learning_rate": 0.00017192045245496238, | |
| "loss": 1.2281, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.030560271646859084, | |
| "grad_norm": 0.8588133454322815, | |
| "learning_rate": 0.00016641313195854277, | |
| "loss": 1.205, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 0.9884034991264343, | |
| "learning_rate": 0.0001605968690574869, | |
| "loss": 1.2602, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03395585738539898, | |
| "grad_norm": 1.295212745666504, | |
| "learning_rate": 0.0001545, | |
| "loss": 1.2808, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03395585738539898, | |
| "eval_loss": 1.3785539865493774, | |
| "eval_runtime": 236.0337, | |
| "eval_samples_per_second": 5.253, | |
| "eval_steps_per_second": 1.313, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.387406029088358e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |