| { | |
| "best_metric": 0.6951894164085388, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22785531187695812, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004557106237539163, | |
| "grad_norm": 8.820571899414062, | |
| "learning_rate": 5e-05, | |
| "loss": 15.3345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004557106237539163, | |
| "eval_loss": 1.4357178211212158, | |
| "eval_runtime": 2.0774, | |
| "eval_samples_per_second": 24.068, | |
| "eval_steps_per_second": 6.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009114212475078326, | |
| "grad_norm": 10.310887336730957, | |
| "learning_rate": 0.0001, | |
| "loss": 17.2755, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013671318712617488, | |
| "grad_norm": 10.644173622131348, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 17.7059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01822842495015665, | |
| "grad_norm": 8.655240058898926, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 17.3498, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02278553118769581, | |
| "grad_norm": 6.201514720916748, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 15.5536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027342637425234975, | |
| "grad_norm": 5.440313339233398, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 14.9356, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031899743662774135, | |
| "grad_norm": 5.338633060455322, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 15.0853, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0364568499003133, | |
| "grad_norm": 5.429011821746826, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 14.4636, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04101395613785246, | |
| "grad_norm": 5.006093502044678, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 13.8889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04557106237539162, | |
| "grad_norm": 4.839547634124756, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 13.4465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05012816861293079, | |
| "grad_norm": 5.606185436248779, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 14.1412, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05468527485046995, | |
| "grad_norm": 10.54796028137207, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 12.2674, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05924238108800912, | |
| "grad_norm": 5.457554340362549, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.8642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06379948732554827, | |
| "grad_norm": 3.5658295154571533, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 12.3164, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06835659356308744, | |
| "grad_norm": 3.49507737159729, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 12.7239, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0729136998006266, | |
| "grad_norm": 2.7759528160095215, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 12.058, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07747080603816577, | |
| "grad_norm": 2.6823928356170654, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 12.1357, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08202791227570493, | |
| "grad_norm": 2.345581293106079, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.505, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08658501851324409, | |
| "grad_norm": 2.521139621734619, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.1799, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09114212475078325, | |
| "grad_norm": 2.5136117935180664, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.831, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09569923098832242, | |
| "grad_norm": 2.724536895751953, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.2209, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10025633722586158, | |
| "grad_norm": 3.3481075763702393, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3393, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10481344346340074, | |
| "grad_norm": 4.651725769042969, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 12.2298, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1093705497009399, | |
| "grad_norm": 7.655670642852783, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11392765593847906, | |
| "grad_norm": 9.879958152770996, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 7.8513, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11392765593847906, | |
| "eval_loss": 0.726329505443573, | |
| "eval_runtime": 2.1222, | |
| "eval_samples_per_second": 23.56, | |
| "eval_steps_per_second": 6.126, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11848476217601824, | |
| "grad_norm": 2.477088689804077, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.1875, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1230418684135574, | |
| "grad_norm": 2.374391555786133, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7398, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12759897465109654, | |
| "grad_norm": 2.537091016769409, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7191, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13215608088863573, | |
| "grad_norm": 2.4189252853393555, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7205, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1367131871261749, | |
| "grad_norm": 2.188260793685913, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.0926, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14127029336371405, | |
| "grad_norm": 2.1279513835906982, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.709, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1458273996012532, | |
| "grad_norm": 2.162879705429077, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.5126, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15038450583879237, | |
| "grad_norm": 4.307819843292236, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.5518, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15494161207633153, | |
| "grad_norm": 2.7188963890075684, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.9315, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1594987183138707, | |
| "grad_norm": 3.0349268913269043, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.0043, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16405582455140985, | |
| "grad_norm": 4.643979072570801, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 12.3598, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.168612930788949, | |
| "grad_norm": 6.440622329711914, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.8752, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17317003702648817, | |
| "grad_norm": 4.075384616851807, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 9.3186, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17772714326402733, | |
| "grad_norm": 1.565960168838501, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.3988, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1822842495015665, | |
| "grad_norm": 1.775325059890747, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.5951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18684135573910568, | |
| "grad_norm": 1.5518596172332764, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.3133, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19139846197664484, | |
| "grad_norm": 1.7390590906143188, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.4181, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.195955568214184, | |
| "grad_norm": 1.728224277496338, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.6342, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20051267445172316, | |
| "grad_norm": 1.828178882598877, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.1649, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20506978068926232, | |
| "grad_norm": 1.769647240638733, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3964, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20962688692680148, | |
| "grad_norm": 2.0480496883392334, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.366, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21418399316434064, | |
| "grad_norm": 2.396080732345581, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.6168, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2187410994018798, | |
| "grad_norm": 2.990973711013794, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.1925, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22329820563941896, | |
| "grad_norm": 5.037263870239258, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.9783, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22785531187695812, | |
| "grad_norm": 6.590723991394043, | |
| "learning_rate": 1e-05, | |
| "loss": 7.5131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22785531187695812, | |
| "eval_loss": 0.6951894164085388, | |
| "eval_runtime": 2.1209, | |
| "eval_samples_per_second": 23.575, | |
| "eval_steps_per_second": 6.13, | |
| "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": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |