| { | |
| "best_metric": 5.243720531463623, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07414272474513438, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014828544949026877, | |
| "grad_norm": 1.7221952676773071, | |
| "learning_rate": 5e-05, | |
| "loss": 5.445, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014828544949026877, | |
| "eval_loss": 5.937737941741943, | |
| "eval_runtime": 3.8314, | |
| "eval_samples_per_second": 13.05, | |
| "eval_steps_per_second": 3.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029657089898053753, | |
| "grad_norm": 1.6534409523010254, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5437, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004448563484708063, | |
| "grad_norm": 0.8762360215187073, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.481, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005931417979610751, | |
| "grad_norm": 1.3805123567581177, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.432, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0074142724745134385, | |
| "grad_norm": 0.9976455569267273, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.4148, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008897126969416125, | |
| "grad_norm": 0.5944635272026062, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.4136, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010379981464318814, | |
| "grad_norm": 0.7650989890098572, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.4493, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011862835959221501, | |
| "grad_norm": 0.8748031854629517, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.4168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013345690454124188, | |
| "grad_norm": 1.683163046836853, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.4665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014828544949026877, | |
| "grad_norm": 1.16215980052948, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.4773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016311399443929564, | |
| "grad_norm": 1.4530987739562988, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.4526, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01779425393883225, | |
| "grad_norm": 5.790648460388184, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.5559, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01927710843373494, | |
| "grad_norm": 8.996513366699219, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.7334, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02075996292863763, | |
| "grad_norm": 3.0871427059173584, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.3363, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022242817423540315, | |
| "grad_norm": 1.2835654020309448, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 5.3605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023725671918443002, | |
| "grad_norm": 1.3427907228469849, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 5.3633, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02520852641334569, | |
| "grad_norm": 0.7967485189437866, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 5.3219, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.026691380908248376, | |
| "grad_norm": 0.7298111915588379, | |
| "learning_rate": 7.75e-05, | |
| "loss": 5.3514, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028174235403151067, | |
| "grad_norm": 0.8981371521949768, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 5.3028, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029657089898053754, | |
| "grad_norm": 0.8268678784370422, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 5.3285, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03113994439295644, | |
| "grad_norm": 0.9234107732772827, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 5.2139, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03262279888785913, | |
| "grad_norm": 1.1020126342773438, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 5.2947, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.034105653382761815, | |
| "grad_norm": 1.1854844093322754, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 5.3084, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0355885078776645, | |
| "grad_norm": 0.978499174118042, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 5.2116, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03707136237256719, | |
| "grad_norm": 1.2116599082946777, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.2337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03707136237256719, | |
| "eval_loss": 5.733458042144775, | |
| "eval_runtime": 3.4725, | |
| "eval_samples_per_second": 14.399, | |
| "eval_steps_per_second": 3.744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03855421686746988, | |
| "grad_norm": 14.637948989868164, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 5.8067, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04003707136237257, | |
| "grad_norm": 13.025384902954102, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 5.6793, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04151992585727526, | |
| "grad_norm": 7.037714004516602, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 5.5536, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.043002780352177944, | |
| "grad_norm": 2.708852529525757, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 5.4214, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04448563484708063, | |
| "grad_norm": 1.5370925664901733, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 5.3473, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04596848934198332, | |
| "grad_norm": 1.4543185234069824, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 5.3576, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.047451343836886005, | |
| "grad_norm": 1.3065513372421265, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 5.3533, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04893419833178869, | |
| "grad_norm": 1.3391211032867432, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 5.3029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05041705282669138, | |
| "grad_norm": 1.0643391609191895, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 5.301, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.051899907321594066, | |
| "grad_norm": 1.066335916519165, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 5.3114, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05338276181649675, | |
| "grad_norm": 1.191772222518921, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 5.2993, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05486561631139945, | |
| "grad_norm": 1.4020297527313232, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 5.3416, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.056348470806302134, | |
| "grad_norm": 0.9556575417518616, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 5.2409, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05783132530120482, | |
| "grad_norm": 1.0040682554244995, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 5.2272, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05931417979610751, | |
| "grad_norm": 0.9176912903785706, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 5.1909, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.060797034291010195, | |
| "grad_norm": 0.7513061165809631, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 5.2537, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06227988878591288, | |
| "grad_norm": 0.6128130555152893, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 5.252, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06376274328081558, | |
| "grad_norm": 0.566775381565094, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 5.2356, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06524559777571826, | |
| "grad_norm": 0.49181070923805237, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 5.2679, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06672845227062095, | |
| "grad_norm": 0.5992257595062256, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 5.227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06821130676552363, | |
| "grad_norm": 1.2758322954177856, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 5.2075, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06969416126042632, | |
| "grad_norm": 0.846122145652771, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 5.286, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.071177015755329, | |
| "grad_norm": 1.0701982975006104, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 5.2788, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0726598702502317, | |
| "grad_norm": 1.3257886171340942, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 5.2388, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07414272474513438, | |
| "grad_norm": 2.1276042461395264, | |
| "learning_rate": 1e-05, | |
| "loss": 5.3273, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07414272474513438, | |
| "eval_loss": 5.243720531463623, | |
| "eval_runtime": 3.4628, | |
| "eval_samples_per_second": 14.439, | |
| "eval_steps_per_second": 3.754, | |
| "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": 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 | |
| } | |