| { | |
| "best_metric": 2.9981603622436523, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.04675081813931744, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018700327255726976, | |
| "grad_norm": 1.8426740169525146, | |
| "learning_rate": 2e-05, | |
| "loss": 3.8067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018700327255726976, | |
| "eval_loss": 4.4178900718688965, | |
| "eval_runtime": 69.2448, | |
| "eval_samples_per_second": 3.264, | |
| "eval_steps_per_second": 1.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037400654511453952, | |
| "grad_norm": 2.6008360385894775, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7382, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005610098176718092, | |
| "grad_norm": 4.860208988189697, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1965, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0074801309022907905, | |
| "grad_norm": 1.7851980924606323, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8876, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009350163627863487, | |
| "grad_norm": 2.326505661010742, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8646, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009350163627863487, | |
| "eval_loss": 4.300511837005615, | |
| "eval_runtime": 68.437, | |
| "eval_samples_per_second": 3.302, | |
| "eval_steps_per_second": 1.651, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011220196353436185, | |
| "grad_norm": 3.141526699066162, | |
| "learning_rate": 0.00012, | |
| "loss": 4.1651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013090229079008883, | |
| "grad_norm": 1.9473650455474854, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014960261804581581, | |
| "grad_norm": 3.0919103622436523, | |
| "learning_rate": 0.00016, | |
| "loss": 3.9862, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016830294530154277, | |
| "grad_norm": 2.943354606628418, | |
| "learning_rate": 0.00018, | |
| "loss": 4.252, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018700327255726974, | |
| "grad_norm": 2.4729549884796143, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018700327255726974, | |
| "eval_loss": 3.4390909671783447, | |
| "eval_runtime": 68.6948, | |
| "eval_samples_per_second": 3.29, | |
| "eval_steps_per_second": 1.645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020570359981299673, | |
| "grad_norm": 2.57906436920166, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.0176, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02244039270687237, | |
| "grad_norm": 2.799055576324463, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.1078, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02431042543244507, | |
| "grad_norm": 4.204552173614502, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.1832, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026180458158017766, | |
| "grad_norm": 2.5168063640594482, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.1536, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028050490883590462, | |
| "grad_norm": 2.580556869506836, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.4018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028050490883590462, | |
| "eval_loss": 3.1383156776428223, | |
| "eval_runtime": 68.8924, | |
| "eval_samples_per_second": 3.28, | |
| "eval_steps_per_second": 1.64, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029920523609163162, | |
| "grad_norm": 2.216768264770508, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.9221, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031790556334735855, | |
| "grad_norm": 2.0270326137542725, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.4759, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.033660589060308554, | |
| "grad_norm": 2.583855390548706, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.007, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035530621785881254, | |
| "grad_norm": 2.130866527557373, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.8303, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03740065451145395, | |
| "grad_norm": 2.2856619358062744, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.6275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03740065451145395, | |
| "eval_loss": 3.0200448036193848, | |
| "eval_runtime": 68.769, | |
| "eval_samples_per_second": 3.286, | |
| "eval_steps_per_second": 1.643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03927068723702665, | |
| "grad_norm": 2.3286995887756348, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04114071996259935, | |
| "grad_norm": 3.739103078842163, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 1.9473609924316406, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.9033, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04488078541374474, | |
| "grad_norm": 1.9453413486480713, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04675081813931744, | |
| "grad_norm": 3.785376787185669, | |
| "learning_rate": 0.0, | |
| "loss": 3.4354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04675081813931744, | |
| "eval_loss": 2.9981603622436523, | |
| "eval_runtime": 68.574, | |
| "eval_samples_per_second": 3.296, | |
| "eval_steps_per_second": 1.648, | |
| "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": 5280456769536000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |