| { | |
| "best_metric": 1.3211456537246704, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.061312078479460456, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002452483139178418, | |
| "grad_norm": 1.1990253925323486, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002452483139178418, | |
| "eval_loss": 1.8322724103927612, | |
| "eval_runtime": 37.6173, | |
| "eval_samples_per_second": 4.572, | |
| "eval_steps_per_second": 2.286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004904966278356836, | |
| "grad_norm": 1.1349740028381348, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0293, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007357449417535254, | |
| "grad_norm": 1.104918360710144, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9023, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009809932556713672, | |
| "grad_norm": 0.9111782312393188, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9264, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012262415695892091, | |
| "grad_norm": 1.0062782764434814, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6187, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012262415695892091, | |
| "eval_loss": 1.8154027462005615, | |
| "eval_runtime": 36.0268, | |
| "eval_samples_per_second": 4.774, | |
| "eval_steps_per_second": 2.387, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014714898835070508, | |
| "grad_norm": 1.078047275543213, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5573, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017167381974248927, | |
| "grad_norm": 1.1716063022613525, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019619865113427344, | |
| "grad_norm": 1.2709145545959473, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9394, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022072348252605765, | |
| "grad_norm": 1.5057402849197388, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8044, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024524831391784182, | |
| "grad_norm": 1.3489257097244263, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024524831391784182, | |
| "eval_loss": 1.598532795906067, | |
| "eval_runtime": 36.0453, | |
| "eval_samples_per_second": 4.772, | |
| "eval_steps_per_second": 2.386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0269773145309626, | |
| "grad_norm": 1.1657987833023071, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.6275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029429797670141016, | |
| "grad_norm": 1.2491055727005005, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.4108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03188228080931944, | |
| "grad_norm": 1.3122302293777466, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5438, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034334763948497854, | |
| "grad_norm": 1.375346064567566, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.3879, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03678724708767627, | |
| "grad_norm": 1.3388978242874146, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03678724708767627, | |
| "eval_loss": 1.3976945877075195, | |
| "eval_runtime": 36.051, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.386, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03923973022685469, | |
| "grad_norm": 1.8990790843963623, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4382, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.041692213366033105, | |
| "grad_norm": 1.6522033214569092, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.351, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04414469650521153, | |
| "grad_norm": 1.8031131029129028, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.4272, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04659717964438995, | |
| "grad_norm": 1.5843220949172974, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.0583, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.049049662783568364, | |
| "grad_norm": 1.3835418224334717, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.049049662783568364, | |
| "eval_loss": 1.3281397819519043, | |
| "eval_runtime": 36.7286, | |
| "eval_samples_per_second": 4.683, | |
| "eval_steps_per_second": 2.341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05150214592274678, | |
| "grad_norm": 1.299329161643982, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.9771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0539546290619252, | |
| "grad_norm": 1.4647064208984375, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.0974, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.056407112201103615, | |
| "grad_norm": 1.6498510837554932, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.2246, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05885959534028203, | |
| "grad_norm": 1.297864317893982, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0874, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061312078479460456, | |
| "grad_norm": 1.972848892211914, | |
| "learning_rate": 0.0, | |
| "loss": 1.5734, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.061312078479460456, | |
| "eval_loss": 1.3211456537246704, | |
| "eval_runtime": 36.4113, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 2.362, | |
| "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": 7858637380780032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |