| { | |
| "best_metric": 1.5941076278686523, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.043440486533449174, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017376194613379669, | |
| "grad_norm": 0.9666237235069275, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4111, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017376194613379669, | |
| "eval_loss": 2.35498046875, | |
| "eval_runtime": 48.5637, | |
| "eval_samples_per_second": 5.004, | |
| "eval_steps_per_second": 2.512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034752389226759338, | |
| "grad_norm": 0.8123922348022461, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005212858384013901, | |
| "grad_norm": 0.7388425469398499, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2589, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0069504778453518675, | |
| "grad_norm": 0.688607931137085, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9124, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008688097306689836, | |
| "grad_norm": 0.9173185229301453, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3572, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008688097306689836, | |
| "eval_loss": 2.288583278656006, | |
| "eval_runtime": 46.5472, | |
| "eval_samples_per_second": 5.221, | |
| "eval_steps_per_second": 2.621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010425716768027803, | |
| "grad_norm": 1.004861831665039, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2209, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01216333622936577, | |
| "grad_norm": 1.193684697151184, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013900955690703735, | |
| "grad_norm": 1.0951910018920898, | |
| "learning_rate": 0.00016, | |
| "loss": 2.144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015638575152041704, | |
| "grad_norm": 0.7744985818862915, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9588, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01737619461337967, | |
| "grad_norm": 0.5166142582893372, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01737619461337967, | |
| "eval_loss": 1.8561629056930542, | |
| "eval_runtime": 46.4923, | |
| "eval_samples_per_second": 5.227, | |
| "eval_steps_per_second": 2.624, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019113814074717638, | |
| "grad_norm": 0.5831554532051086, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.7998, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020851433536055605, | |
| "grad_norm": 1.058409333229065, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.9262, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022589052997393572, | |
| "grad_norm": 0.8140910863876343, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7846, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02432667245873154, | |
| "grad_norm": 0.8120012879371643, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.8817, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.026064291920069503, | |
| "grad_norm": 0.7701101899147034, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.5197, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026064291920069503, | |
| "eval_loss": 1.6632987260818481, | |
| "eval_runtime": 47.2723, | |
| "eval_samples_per_second": 5.14, | |
| "eval_steps_per_second": 2.581, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02780191138140747, | |
| "grad_norm": 0.653910756111145, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5716, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029539530842745437, | |
| "grad_norm": 0.7035102248191833, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.6999, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03127715030408341, | |
| "grad_norm": 0.5811207294464111, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.687, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03301476976542137, | |
| "grad_norm": 1.1224349737167358, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.5975, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03475238922675934, | |
| "grad_norm": 0.6417143940925598, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.3906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03475238922675934, | |
| "eval_loss": 1.6070237159729004, | |
| "eval_runtime": 47.2061, | |
| "eval_samples_per_second": 5.148, | |
| "eval_steps_per_second": 2.584, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.036490008688097306, | |
| "grad_norm": 0.5803474187850952, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.7383, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.038227628149435276, | |
| "grad_norm": 0.7997701168060303, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.7855, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03996524761077324, | |
| "grad_norm": 0.5163703560829163, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.5399, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04170286707211121, | |
| "grad_norm": 0.6158132553100586, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.6514, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.043440486533449174, | |
| "grad_norm": 0.7691506147384644, | |
| "learning_rate": 0.0, | |
| "loss": 1.638, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043440486533449174, | |
| "eval_loss": 1.5941076278686523, | |
| "eval_runtime": 47.3248, | |
| "eval_samples_per_second": 5.135, | |
| "eval_steps_per_second": 2.578, | |
| "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": 4861077623930880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |