| { | |
| "best_metric": 0.6928964853286743, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.007357674974707992, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036788374873539964, | |
| "grad_norm": 8.641034126281738, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036788374873539964, | |
| "eval_loss": 3.5604350566864014, | |
| "eval_runtime": 162.037, | |
| "eval_samples_per_second": 7.066, | |
| "eval_steps_per_second": 3.536, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007357674974707993, | |
| "grad_norm": 6.875428676605225, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3059, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011036512462061989, | |
| "grad_norm": 7.295816898345947, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014715349949415985, | |
| "grad_norm": 6.719980716705322, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6083, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001839418743676998, | |
| "grad_norm": 6.446127891540527, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9195, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001839418743676998, | |
| "eval_loss": 2.9542577266693115, | |
| "eval_runtime": 160.8239, | |
| "eval_samples_per_second": 7.12, | |
| "eval_steps_per_second": 3.563, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022073024924123977, | |
| "grad_norm": 6.19967794418335, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6303, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002575186241147797, | |
| "grad_norm": 5.094878196716309, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002943069989883197, | |
| "grad_norm": 4.440817356109619, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0104, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033109537386185966, | |
| "grad_norm": 5.241264820098877, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003678837487353996, | |
| "grad_norm": 4.398327827453613, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4926, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003678837487353996, | |
| "eval_loss": 1.2735178470611572, | |
| "eval_runtime": 156.5936, | |
| "eval_samples_per_second": 7.312, | |
| "eval_steps_per_second": 3.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004046721236089396, | |
| "grad_norm": 4.377835750579834, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.2754, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004414604984824795, | |
| "grad_norm": 3.609360933303833, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.9183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004782488733560195, | |
| "grad_norm": 3.6163525581359863, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.9236, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005150372482295594, | |
| "grad_norm": 3.1708669662475586, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.8382, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005518256231030994, | |
| "grad_norm": 2.7939131259918213, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6538, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005518256231030994, | |
| "eval_loss": 0.7443342804908752, | |
| "eval_runtime": 153.8448, | |
| "eval_samples_per_second": 7.443, | |
| "eval_steps_per_second": 3.725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005886139979766394, | |
| "grad_norm": 4.013178825378418, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8417, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006254023728501794, | |
| "grad_norm": 3.8191921710968018, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.8894, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006621907477237193, | |
| "grad_norm": 3.4114315509796143, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.7048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006989791225972593, | |
| "grad_norm": 2.447831153869629, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.4686, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007357674974707992, | |
| "grad_norm": 4.075280666351318, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007357674974707992, | |
| "eval_loss": 0.6928964853286743, | |
| "eval_runtime": 154.6256, | |
| "eval_samples_per_second": 7.405, | |
| "eval_steps_per_second": 3.706, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1000194661416960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |