| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.7527114967462039, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03470715835140998, | |
| "grad_norm": 1.0270408391952515, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03470715835140998, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.6098, | |
| "eval_samples_per_second": 13.851, | |
| "eval_steps_per_second": 3.601, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06941431670281996, | |
| "grad_norm": 0.9911738634109497, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10412147505422993, | |
| "grad_norm": 1.0123313665390015, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.9004, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13882863340563992, | |
| "grad_norm": 1.1171038150787354, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.0405, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1735357917570499, | |
| "grad_norm": 1.0495178699493408, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.9618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20824295010845986, | |
| "grad_norm": 1.032975196838379, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.9063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24295010845986983, | |
| "grad_norm": 1.3030965328216553, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.8093, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27765726681127983, | |
| "grad_norm": 1.113315224647522, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.9621, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3123644251626898, | |
| "grad_norm": 1.320401668548584, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.8794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3470715835140998, | |
| "grad_norm": 1.2780348062515259, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.1614, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38177874186550975, | |
| "grad_norm": 1.2609745264053345, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.2007, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4164859002169197, | |
| "grad_norm": 1.1756610870361328, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.2247, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4511930585683297, | |
| "grad_norm": 1.2289035320281982, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.2601, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.48590021691973967, | |
| "grad_norm": 1.4233766794204712, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.9673, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5206073752711496, | |
| "grad_norm": 1.0535727739334106, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.5299, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5553145336225597, | |
| "grad_norm": 1.213702917098999, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.7016, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5900216919739696, | |
| "grad_norm": 1.3188772201538086, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.7211, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6247288503253796, | |
| "grad_norm": 1.353604793548584, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.7997, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6594360086767896, | |
| "grad_norm": 1.3442471027374268, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.7069, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6941431670281996, | |
| "grad_norm": 1.2742968797683716, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.7996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7288503253796096, | |
| "grad_norm": 1.404556155204773, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.7581, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7635574837310195, | |
| "grad_norm": 0.9362565875053406, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.3051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7982646420824295, | |
| "grad_norm": 1.0469181537628174, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.2941, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8329718004338394, | |
| "grad_norm": 1.0510656833648682, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.3864, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "grad_norm": 1.2001053094863892, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.4031, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2517, | |
| "eval_samples_per_second": 15.376, | |
| "eval_steps_per_second": 3.998, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9023861171366594, | |
| "grad_norm": 1.270917534828186, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.3487, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9370932754880694, | |
| "grad_norm": 1.400947093963623, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.1771, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9718004338394793, | |
| "grad_norm": 1.8828790187835693, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.5593, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0238611713665944, | |
| "grad_norm": 1.7455302476882935, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 7.0855, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0585683297180044, | |
| "grad_norm": 1.0067161321640015, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.1927, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0932754880694142, | |
| "grad_norm": 0.9785596132278442, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.8184, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1279826464208242, | |
| "grad_norm": 1.14651358127594, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.2095, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1626898047722343, | |
| "grad_norm": 1.0360416173934937, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.0984, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1973969631236443, | |
| "grad_norm": 1.2359875440597534, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.1898, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2321041214750543, | |
| "grad_norm": 1.3868677616119385, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.7502, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2668112798264641, | |
| "grad_norm": 1.1134669780731201, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.8309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3015184381778742, | |
| "grad_norm": 0.9911520481109619, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.8265, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3362255965292842, | |
| "grad_norm": 0.9708497524261475, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.5501, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3709327548806942, | |
| "grad_norm": 1.183776617050171, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.2784, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.405639913232104, | |
| "grad_norm": 1.1506365537643433, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.6222, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.440347071583514, | |
| "grad_norm": 1.267316222190857, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.9714, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.475054229934924, | |
| "grad_norm": 1.6185253858566284, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.3338, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.509761388286334, | |
| "grad_norm": 1.0542787313461304, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.8664, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5444685466377441, | |
| "grad_norm": 0.9902780055999756, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.4753, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.579175704989154, | |
| "grad_norm": 1.081815481185913, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.0674, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.613882863340564, | |
| "grad_norm": 1.1183944940567017, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.8616, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.648590021691974, | |
| "grad_norm": 1.1336209774017334, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.8991, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6832971800433838, | |
| "grad_norm": 1.3395631313323975, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.0566, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.718004338394794, | |
| "grad_norm": 1.4792617559432983, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.8368, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7527114967462039, | |
| "grad_norm": 1.0658278465270996, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7527114967462039, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.2427, | |
| "eval_samples_per_second": 15.419, | |
| "eval_steps_per_second": 4.009, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |