| { | |
| "best_metric": 0.8936432003974915, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7094017094017095, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.3629566431045532, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "eval_loss": 1.2048848867416382, | |
| "eval_runtime": 3.8285, | |
| "eval_samples_per_second": 13.06, | |
| "eval_steps_per_second": 3.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.41237789392471313, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0399, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 0.4242379665374756, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.0646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.3851858377456665, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.0962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.6028817296028137, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2293, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.7408937811851501, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1312, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 1.0603728294372559, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1818, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.8225412368774414, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9262, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.8064265251159668, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.5837405920028687, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.9599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 0.43087607622146606, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9624, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.6023728251457214, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0984, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.7657191753387451, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.2308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.6526044607162476, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.0051, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.26829999685287476, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.26890355348587036, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8369, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 0.33930063247680664, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.8634, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3213464021682739, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9046, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 0.30203214287757874, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9754, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.39848047494888306, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.4964998960494995, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.29781854152679443, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.7722, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.27328628301620483, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8204, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.2900655269622803, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.8712, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.29044869542121887, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8574, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": 0.9397671222686768, | |
| "eval_runtime": 3.4925, | |
| "eval_samples_per_second": 14.316, | |
| "eval_steps_per_second": 3.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3003530502319336, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9396, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.38296979665756226, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.0315, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.4535260498523712, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.9811, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 0.6909157037734985, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.9657, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 0.5730057954788208, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.4471, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0598290598290598, | |
| "grad_norm": 0.23904989659786224, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7712, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0940170940170941, | |
| "grad_norm": 0.2702152729034424, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.803, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1282051282051282, | |
| "grad_norm": 0.2781081795692444, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8369, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1623931623931625, | |
| "grad_norm": 0.2826618254184723, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9031, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1965811965811965, | |
| "grad_norm": 0.4115469455718994, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0045, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.5486916303634644, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.264957264957265, | |
| "grad_norm": 0.27575865387916565, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2991452991452992, | |
| "grad_norm": 0.23719096183776855, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.7849, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.23659953474998474, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.7611, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3675213675213675, | |
| "grad_norm": 0.24429921805858612, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.8367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4017094017094016, | |
| "grad_norm": 0.3248053193092346, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.9198, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": 0.4573812782764435, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.006, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4700854700854702, | |
| "grad_norm": 0.4747590720653534, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7927, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5042735042735043, | |
| "grad_norm": 0.2991985082626343, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5808, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.26089948415756226, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.863, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5726495726495726, | |
| "grad_norm": 0.23467212915420532, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7654, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.606837606837607, | |
| "grad_norm": 0.2614939212799072, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7831, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.3077352046966553, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8956, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6752136752136753, | |
| "grad_norm": 0.3929722011089325, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9792, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "grad_norm": 0.4925636053085327, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "eval_loss": 0.8936432003974915, | |
| "eval_runtime": 3.4896, | |
| "eval_samples_per_second": 14.328, | |
| "eval_steps_per_second": 3.725, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |