|
{ |
|
"best_metric": 1.644777774810791, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.10752688172043011, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.002150537634408602, |
|
"grad_norm": 15.986177444458008, |
|
"learning_rate": 5e-06, |
|
"loss": 8.5433, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.002150537634408602, |
|
"eval_loss": 2.4243364334106445, |
|
"eval_runtime": 116.5757, |
|
"eval_samples_per_second": 6.725, |
|
"eval_steps_per_second": 0.841, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.004301075268817204, |
|
"grad_norm": 717.1296997070312, |
|
"learning_rate": 1e-05, |
|
"loss": 8.2612, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0064516129032258064, |
|
"grad_norm": 5363.35546875, |
|
"learning_rate": 1.5e-05, |
|
"loss": 8.3129, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.008602150537634409, |
|
"grad_norm": 10.108478546142578, |
|
"learning_rate": 2e-05, |
|
"loss": 10.0528, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.010752688172043012, |
|
"grad_norm": 21.097169876098633, |
|
"learning_rate": 2.5e-05, |
|
"loss": 10.6582, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.012903225806451613, |
|
"grad_norm": 11.138842582702637, |
|
"learning_rate": 3e-05, |
|
"loss": 9.9272, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.015053763440860216, |
|
"grad_norm": 14.46927261352539, |
|
"learning_rate": 3.5e-05, |
|
"loss": 9.3086, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.017204301075268817, |
|
"grad_norm": 4.204796314239502, |
|
"learning_rate": 4e-05, |
|
"loss": 8.5735, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.01935483870967742, |
|
"grad_norm": 4.104348182678223, |
|
"learning_rate": 4.5e-05, |
|
"loss": 8.9812, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.021505376344086023, |
|
"grad_norm": 7.411334037780762, |
|
"learning_rate": 5e-05, |
|
"loss": 11.3629, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.023655913978494623, |
|
"grad_norm": 8.226151466369629, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 9.496, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.025806451612903226, |
|
"grad_norm": 121.1121826171875, |
|
"learning_rate": 6e-05, |
|
"loss": 7.9266, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.02795698924731183, |
|
"grad_norm": 13.033742904663086, |
|
"learning_rate": 6.500000000000001e-05, |
|
"loss": 8.7298, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.030107526881720432, |
|
"grad_norm": 5.372778415679932, |
|
"learning_rate": 7e-05, |
|
"loss": 8.8813, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.03225806451612903, |
|
"grad_norm": 13.778736114501953, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 7.8643, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.034408602150537634, |
|
"grad_norm": 5.646563529968262, |
|
"learning_rate": 8e-05, |
|
"loss": 7.7038, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.03655913978494624, |
|
"grad_norm": 14.398736000061035, |
|
"learning_rate": 8.5e-05, |
|
"loss": 8.3796, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.03870967741935484, |
|
"grad_norm": 7.327658653259277, |
|
"learning_rate": 9e-05, |
|
"loss": 8.1228, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.04086021505376344, |
|
"grad_norm": 4.2828168869018555, |
|
"learning_rate": 9.5e-05, |
|
"loss": 7.1571, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.043010752688172046, |
|
"grad_norm": 532.1356201171875, |
|
"learning_rate": 0.0001, |
|
"loss": 7.9117, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.04516129032258064, |
|
"grad_norm": 4.106211185455322, |
|
"learning_rate": 9.972609476841367e-05, |
|
"loss": 7.2517, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.047311827956989246, |
|
"grad_norm": 3.981506109237671, |
|
"learning_rate": 9.890738003669029e-05, |
|
"loss": 7.5363, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.04946236559139785, |
|
"grad_norm": 2.6978485584259033, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 7.0731, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.05161290322580645, |
|
"grad_norm": 16.74765968322754, |
|
"learning_rate": 9.567727288213005e-05, |
|
"loss": 5.8038, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.053763440860215055, |
|
"grad_norm": 32.079010009765625, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 7.5026, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.053763440860215055, |
|
"eval_loss": 1.7179549932479858, |
|
"eval_runtime": 117.5747, |
|
"eval_samples_per_second": 6.668, |
|
"eval_steps_per_second": 0.834, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05591397849462366, |
|
"grad_norm": 2.289424180984497, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 6.4329, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.05806451612903226, |
|
"grad_norm": 2.517298460006714, |
|
"learning_rate": 8.715724127386972e-05, |
|
"loss": 6.0302, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.060215053763440864, |
|
"grad_norm": 3.4784586429595947, |
|
"learning_rate": 8.345653031794292e-05, |
|
"loss": 6.5625, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.06236559139784946, |
|
"grad_norm": 3.08809494972229, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 7.3558, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.06451612903225806, |
|
"grad_norm": 2.907604455947876, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 6.9755, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.06666666666666667, |
|
"grad_norm": 2.4555325508117676, |
|
"learning_rate": 7.033683215379002e-05, |
|
"loss": 7.0884, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.06881720430107527, |
|
"grad_norm": 3.109780788421631, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 5.9083, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.07096774193548387, |
|
"grad_norm": 5.803027629852295, |
|
"learning_rate": 6.0395584540887963e-05, |
|
"loss": 6.5149, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.07311827956989247, |
|
"grad_norm": 3.701385259628296, |
|
"learning_rate": 5.522642316338268e-05, |
|
"loss": 6.6396, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.07526881720430108, |
|
"grad_norm": 2.906161069869995, |
|
"learning_rate": 5e-05, |
|
"loss": 6.7558, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.07741935483870968, |
|
"grad_norm": 3.355015993118286, |
|
"learning_rate": 4.477357683661734e-05, |
|
"loss": 6.6618, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.07956989247311828, |
|
"grad_norm": 2.019418716430664, |
|
"learning_rate": 3.960441545911204e-05, |
|
"loss": 7.2221, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.08172043010752689, |
|
"grad_norm": 2.2855887413024902, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 5.8867, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.08387096774193549, |
|
"grad_norm": 5.668225288391113, |
|
"learning_rate": 2.9663167846209998e-05, |
|
"loss": 7.0586, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.08602150537634409, |
|
"grad_norm": 49.42198181152344, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 6.7356, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.08817204301075268, |
|
"grad_norm": 3.67435359954834, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 6.6045, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.09032258064516129, |
|
"grad_norm": 3.468963146209717, |
|
"learning_rate": 1.6543469682057106e-05, |
|
"loss": 6.9789, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.09247311827956989, |
|
"grad_norm": 1.8968158960342407, |
|
"learning_rate": 1.2842758726130283e-05, |
|
"loss": 5.5492, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.09462365591397849, |
|
"grad_norm": 46.57176208496094, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 6.3358, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.0967741935483871, |
|
"grad_norm": 2.8659753799438477, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 5.6891, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.0989247311827957, |
|
"grad_norm": 6.436995983123779, |
|
"learning_rate": 4.322727117869951e-06, |
|
"loss": 6.5427, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.1010752688172043, |
|
"grad_norm": 2.667637825012207, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 5.9998, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.1032258064516129, |
|
"grad_norm": 4.361298084259033, |
|
"learning_rate": 1.0926199633097157e-06, |
|
"loss": 6.8748, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.1053763440860215, |
|
"grad_norm": 4.055363655090332, |
|
"learning_rate": 2.7390523158633554e-07, |
|
"loss": 6.2738, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.10752688172043011, |
|
"grad_norm": 3.4398603439331055, |
|
"learning_rate": 0.0, |
|
"loss": 6.8857, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.10752688172043011, |
|
"eval_loss": 1.644777774810791, |
|
"eval_runtime": 117.505, |
|
"eval_samples_per_second": 6.672, |
|
"eval_steps_per_second": 0.834, |
|
"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": 1.3781132378112e+17, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|