| { | |
| "best_metric": 3.4069063663482666, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07886435331230283, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015772870662460567, | |
| "grad_norm": 14.288801193237305, | |
| "learning_rate": 1e-06, | |
| "loss": 4.1392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015772870662460567, | |
| "eval_loss": 5.495478630065918, | |
| "eval_runtime": 32.9516, | |
| "eval_samples_per_second": 8.103, | |
| "eval_steps_per_second": 2.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031545741324921135, | |
| "grad_norm": 15.715526580810547, | |
| "learning_rate": 2e-06, | |
| "loss": 5.0502, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00473186119873817, | |
| "grad_norm": 15.536548614501953, | |
| "learning_rate": 3e-06, | |
| "loss": 5.1276, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006309148264984227, | |
| "grad_norm": 17.026763916015625, | |
| "learning_rate": 4e-06, | |
| "loss": 5.374, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007886435331230283, | |
| "grad_norm": 15.741572380065918, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 5.5136, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00946372239747634, | |
| "grad_norm": 15.484997749328613, | |
| "learning_rate": 6e-06, | |
| "loss": 5.2435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011041009463722398, | |
| "grad_norm": 15.373290061950684, | |
| "learning_rate": 7e-06, | |
| "loss": 4.9099, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012618296529968454, | |
| "grad_norm": 12.652005195617676, | |
| "learning_rate": 8e-06, | |
| "loss": 4.9459, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014195583596214511, | |
| "grad_norm": 12.026541709899902, | |
| "learning_rate": 9e-06, | |
| "loss": 4.9864, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015772870662460567, | |
| "grad_norm": 10.106391906738281, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 4.5523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017350157728706624, | |
| "grad_norm": 8.480169296264648, | |
| "learning_rate": 1.1e-05, | |
| "loss": 4.231, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01892744479495268, | |
| "grad_norm": 6.781610012054443, | |
| "learning_rate": 1.2e-05, | |
| "loss": 4.1676, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02050473186119874, | |
| "grad_norm": 6.3951416015625, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 4.1037, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022082018927444796, | |
| "grad_norm": 5.828855514526367, | |
| "learning_rate": 1.4e-05, | |
| "loss": 4.0932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02365930599369085, | |
| "grad_norm": 5.394031047821045, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.9269, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025236593059936908, | |
| "grad_norm": 5.391214847564697, | |
| "learning_rate": 1.6e-05, | |
| "loss": 3.9033, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026813880126182965, | |
| "grad_norm": 5.0820088386535645, | |
| "learning_rate": 1.7e-05, | |
| "loss": 3.9008, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028391167192429023, | |
| "grad_norm": 4.5527448654174805, | |
| "learning_rate": 1.8e-05, | |
| "loss": 3.7433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02996845425867508, | |
| "grad_norm": 4.142192840576172, | |
| "learning_rate": 1.9e-05, | |
| "loss": 3.8041, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031545741324921134, | |
| "grad_norm": 4.488745212554932, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 3.6456, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033123028391167195, | |
| "grad_norm": 5.890789031982422, | |
| "learning_rate": 2.1e-05, | |
| "loss": 3.7687, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03470031545741325, | |
| "grad_norm": 4.825263977050781, | |
| "learning_rate": 2.2e-05, | |
| "loss": 3.6791, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03627760252365931, | |
| "grad_norm": 5.447760105133057, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 3.5713, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03785488958990536, | |
| "grad_norm": 5.412661075592041, | |
| "learning_rate": 2.4e-05, | |
| "loss": 3.6008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03943217665615142, | |
| "grad_norm": 5.67608118057251, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.557, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04100946372239748, | |
| "grad_norm": 5.01165771484375, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 3.5387, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04258675078864353, | |
| "grad_norm": 5.461337566375732, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 3.4848, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04416403785488959, | |
| "grad_norm": 5.771214485168457, | |
| "learning_rate": 2.8e-05, | |
| "loss": 3.6061, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04574132492113565, | |
| "grad_norm": 5.130762577056885, | |
| "learning_rate": 2.9e-05, | |
| "loss": 3.4529, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0473186119873817, | |
| "grad_norm": 5.74155330657959, | |
| "learning_rate": 3e-05, | |
| "loss": 3.6219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04889589905362776, | |
| "grad_norm": 5.010629653930664, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 3.4359, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.050473186119873815, | |
| "grad_norm": 5.268033981323242, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 3.5354, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.052050473186119876, | |
| "grad_norm": 4.732529163360596, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 3.3508, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05362776025236593, | |
| "grad_norm": 4.656714916229248, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 3.1475, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.055205047318611984, | |
| "grad_norm": 5.401196002960205, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 3.543, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.056782334384858045, | |
| "grad_norm": 4.2879109382629395, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 2.6872, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0583596214511041, | |
| "grad_norm": 4.594905853271484, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 3.223, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05993690851735016, | |
| "grad_norm": 4.826547145843506, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 3.2465, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.061514195583596214, | |
| "grad_norm": 6.053707599639893, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 3.3025, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06309148264984227, | |
| "grad_norm": 4.34194803237915, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 3.169, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06466876971608833, | |
| "grad_norm": 4.723700046539307, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 3.2656, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06624605678233439, | |
| "grad_norm": 4.55301570892334, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 3.21, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06782334384858044, | |
| "grad_norm": 4.821488380432129, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 3.1943, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0694006309148265, | |
| "grad_norm": 5.458112716674805, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 3.1723, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07097791798107256, | |
| "grad_norm": 4.9624128341674805, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 3.2817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07255520504731862, | |
| "grad_norm": 5.255752086639404, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 3.251, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07413249211356467, | |
| "grad_norm": 5.183978080749512, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 3.3239, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07570977917981073, | |
| "grad_norm": 5.015427112579346, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 3.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07728706624605679, | |
| "grad_norm": 4.870700359344482, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 3.2715, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07886435331230283, | |
| "grad_norm": 6.772426128387451, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 3.3329, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07886435331230283, | |
| "eval_loss": 3.4069063663482666, | |
| "eval_runtime": 33.6247, | |
| "eval_samples_per_second": 7.941, | |
| "eval_steps_per_second": 1.993, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 2.520792649904947e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |