| { | |
| "best_metric": 1.6961973905563354, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010486577181208054, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020973154362416107, | |
| "grad_norm": 3.0111474990844727, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9126, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020973154362416107, | |
| "eval_loss": 2.36071515083313, | |
| "eval_runtime": 437.7926, | |
| "eval_samples_per_second": 18.342, | |
| "eval_steps_per_second": 2.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041946308724832214, | |
| "grad_norm": 4.440647602081299, | |
| "learning_rate": 4e-05, | |
| "loss": 7.4566, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006291946308724832, | |
| "grad_norm": 3.8682024478912354, | |
| "learning_rate": 6e-05, | |
| "loss": 7.6517, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008389261744966443, | |
| "grad_norm": 3.737701892852783, | |
| "learning_rate": 8e-05, | |
| "loss": 7.1519, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010486577181208054, | |
| "grad_norm": 3.7156572341918945, | |
| "learning_rate": 0.0001, | |
| "loss": 6.398, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012583892617449664, | |
| "grad_norm": 3.359435558319092, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 6.8605, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014681208053691276, | |
| "grad_norm": 3.383056163787842, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 6.7665, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016778523489932886, | |
| "grad_norm": 4.306021690368652, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 7.0671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018875838926174498, | |
| "grad_norm": 2.699436664581299, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 6.9682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020973154362416107, | |
| "grad_norm": 3.3397040367126465, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 6.9951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002307046979865772, | |
| "grad_norm": 2.384814739227295, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 6.6337, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0025167785234899327, | |
| "grad_norm": 3.4232239723205566, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 6.7536, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002726510067114094, | |
| "grad_norm": 3.253732919692993, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 6.4512, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002936241610738255, | |
| "grad_norm": 2.7404983043670654, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.4563, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003145973154362416, | |
| "grad_norm": 3.736191749572754, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 6.4015, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003355704697986577, | |
| "grad_norm": 3.08125376701355, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 6.6318, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0035654362416107383, | |
| "grad_norm": 3.8511247634887695, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 6.6143, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0037751677852348995, | |
| "grad_norm": 3.2807059288024902, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 6.6775, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003984899328859061, | |
| "grad_norm": 3.06815242767334, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 6.4738, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0041946308724832215, | |
| "grad_norm": 2.903425931930542, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.7428, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004404362416107382, | |
| "grad_norm": 3.557361125946045, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 6.2812, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004614093959731544, | |
| "grad_norm": 2.8678152561187744, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 6.3831, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004823825503355705, | |
| "grad_norm": 2.9509992599487305, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.39, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0050335570469798654, | |
| "grad_norm": 2.8665361404418945, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 6.1318, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005243288590604027, | |
| "grad_norm": 2.8915178775787354, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.3825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005243288590604027, | |
| "eval_loss": 1.6961973905563354, | |
| "eval_runtime": 440.3076, | |
| "eval_samples_per_second": 18.237, | |
| "eval_steps_per_second": 2.28, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005453020134228188, | |
| "grad_norm": 3.5189576148986816, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 7.1497, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005662751677852349, | |
| "grad_norm": 3.4907236099243164, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 6.8121, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00587248322147651, | |
| "grad_norm": 3.352301597595215, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 6.9369, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006082214765100671, | |
| "grad_norm": 3.8302619457244873, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 6.9222, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006291946308724832, | |
| "grad_norm": 3.51759672164917, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 6.6552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0065016778523489934, | |
| "grad_norm": 3.75423526763916, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 6.5789, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "grad_norm": 4.301468372344971, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 6.8843, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006921140939597316, | |
| "grad_norm": 4.287465572357178, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 6.3121, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007130872483221477, | |
| "grad_norm": 4.683781147003174, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 6.3466, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007340604026845637, | |
| "grad_norm": 4.297049045562744, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.5177, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007550335570469799, | |
| "grad_norm": 5.890731334686279, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 6.3405, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00776006711409396, | |
| "grad_norm": 5.064823627471924, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 5.9357, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007969798657718121, | |
| "grad_norm": 4.774162292480469, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 5.8669, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008179530201342282, | |
| "grad_norm": 4.649093151092529, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 5.9236, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008389261744966443, | |
| "grad_norm": 5.287595272064209, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 6.5715, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008598993288590604, | |
| "grad_norm": 5.230982780456543, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 5.8544, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.008808724832214765, | |
| "grad_norm": 5.401068210601807, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 5.6195, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009018456375838927, | |
| "grad_norm": 5.703489303588867, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 6.1054, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009228187919463088, | |
| "grad_norm": 6.4749274253845215, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 5.2847, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009437919463087249, | |
| "grad_norm": 8.451642036437988, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 5.1672, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00964765100671141, | |
| "grad_norm": 6.819253444671631, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 4.9192, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00985738255033557, | |
| "grad_norm": 6.859738349914551, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 5.0944, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010067114093959731, | |
| "grad_norm": 8.738635063171387, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 5.6795, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010276845637583893, | |
| "grad_norm": 19.29412841796875, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 4.5156, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010486577181208054, | |
| "grad_norm": 61.366493225097656, | |
| "learning_rate": 0.0, | |
| "loss": 6.8393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010486577181208054, | |
| "eval_loss": 1.8221542835235596, | |
| "eval_runtime": 440.2648, | |
| "eval_samples_per_second": 18.239, | |
| "eval_steps_per_second": 2.28, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.831286539157504e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |