| { | |
| "best_metric": 2.1368038654327393, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02450379808870375, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00098015192354815, | |
| "grad_norm": 1.0274126529693604, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00098015192354815, | |
| "eval_loss": 2.4249114990234375, | |
| "eval_runtime": 31.1693, | |
| "eval_samples_per_second": 13.796, | |
| "eval_steps_per_second": 6.898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019603038470963, | |
| "grad_norm": 0.48389723896980286, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00294045577064445, | |
| "grad_norm": 0.6074631214141846, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1782, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0039206076941926, | |
| "grad_norm": 0.5143649578094482, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0112, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "grad_norm": 0.6112140417098999, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5237, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "eval_loss": 2.4187209606170654, | |
| "eval_runtime": 30.1848, | |
| "eval_samples_per_second": 14.246, | |
| "eval_steps_per_second": 7.123, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0058809115412889, | |
| "grad_norm": 0.5209685564041138, | |
| "learning_rate": 0.00012, | |
| "loss": 2.518, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00686106346483705, | |
| "grad_norm": 0.611119270324707, | |
| "learning_rate": 0.00014, | |
| "loss": 2.2351, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0078412153883852, | |
| "grad_norm": 0.5997849106788635, | |
| "learning_rate": 0.00016, | |
| "loss": 2.332, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008821367311933349, | |
| "grad_norm": 0.6130127310752869, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4948, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "grad_norm": 0.6186327934265137, | |
| "learning_rate": 0.0002, | |
| "loss": 2.127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "eval_loss": 2.348543882369995, | |
| "eval_runtime": 30.1892, | |
| "eval_samples_per_second": 14.243, | |
| "eval_steps_per_second": 7.122, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01078167115902965, | |
| "grad_norm": 0.7577857971191406, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.277, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0117618230825778, | |
| "grad_norm": 0.5409818291664124, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1708, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01274197500612595, | |
| "grad_norm": 0.4970989227294922, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.0626, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0137221269296741, | |
| "grad_norm": 0.7126469612121582, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.5659, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014702278853222249, | |
| "grad_norm": 0.5474905371665955, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.0383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014702278853222249, | |
| "eval_loss": 2.2148451805114746, | |
| "eval_runtime": 30.227, | |
| "eval_samples_per_second": 14.226, | |
| "eval_steps_per_second": 7.113, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0156824307767704, | |
| "grad_norm": 0.6352144479751587, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2655, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01666258270031855, | |
| "grad_norm": 0.6581323742866516, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.1256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017642734623866698, | |
| "grad_norm": 0.705475389957428, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.0248, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018622886547414848, | |
| "grad_norm": 0.8269036412239075, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.3213, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "grad_norm": 0.6235066056251526, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.038, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "eval_loss": 2.1507134437561035, | |
| "eval_runtime": 30.2493, | |
| "eval_samples_per_second": 14.215, | |
| "eval_steps_per_second": 7.108, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02058319039451115, | |
| "grad_norm": 0.7433381676673889, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.1337, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0215633423180593, | |
| "grad_norm": 0.7238690853118896, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.1446, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02254349424160745, | |
| "grad_norm": 0.54570472240448, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.9859, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0235236461651556, | |
| "grad_norm": 0.628850519657135, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 2.2154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02450379808870375, | |
| "grad_norm": 0.9672688245773315, | |
| "learning_rate": 0.0, | |
| "loss": 2.0251, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02450379808870375, | |
| "eval_loss": 2.1368038654327393, | |
| "eval_runtime": 30.5546, | |
| "eval_samples_per_second": 14.073, | |
| "eval_steps_per_second": 7.037, | |
| "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": 85731626188800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |