| { | |
| "best_metric": 0.12372367829084396, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05829204313611192, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011658408627222385, | |
| "grad_norm": 16.38446617126465, | |
| "learning_rate": 5e-05, | |
| "loss": 12.1759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011658408627222385, | |
| "eval_loss": 12.8995943069458, | |
| "eval_runtime": 384.5861, | |
| "eval_samples_per_second": 15.027, | |
| "eval_steps_per_second": 1.88, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002331681725444477, | |
| "grad_norm": 16.659414291381836, | |
| "learning_rate": 0.0001, | |
| "loss": 12.3466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034975225881667153, | |
| "grad_norm": 17.676015853881836, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.6318, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004663363450888954, | |
| "grad_norm": 15.860479354858398, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.5545, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005829204313611192, | |
| "grad_norm": 17.837818145751953, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.7707, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006995045176333431, | |
| "grad_norm": 15.243780136108398, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.11, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00816088603905567, | |
| "grad_norm": 9.980854034423828, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.467, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009326726901777908, | |
| "grad_norm": 6.602626800537109, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010492567764500145, | |
| "grad_norm": 6.178258419036865, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5236, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011658408627222384, | |
| "grad_norm": 10.202402114868164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012824249489944622, | |
| "grad_norm": 7.428191661834717, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013990090352666861, | |
| "grad_norm": 4.225120544433594, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.293, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0151559312153891, | |
| "grad_norm": 4.913784027099609, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3645, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01632177207811134, | |
| "grad_norm": 4.96398401260376, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2782, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017487612940833577, | |
| "grad_norm": 0.8653579950332642, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1909, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018653453803555816, | |
| "grad_norm": 3.7116739749908447, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2241, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019819294666278055, | |
| "grad_norm": 0.8005671501159668, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1851, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02098513552900029, | |
| "grad_norm": 1.426818609237671, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1733, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02215097639172253, | |
| "grad_norm": 0.8837517499923706, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1377, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023316817254444767, | |
| "grad_norm": 0.6280977725982666, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024482658117167006, | |
| "grad_norm": 1.3945311307907104, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1228, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025648498979889245, | |
| "grad_norm": 2.828673839569092, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1648, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026814339842611484, | |
| "grad_norm": 2.7186119556427, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1356, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027980180705333722, | |
| "grad_norm": 2.902658700942993, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1207, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02914602156805596, | |
| "grad_norm": 1.6081689596176147, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02914602156805596, | |
| "eval_loss": 0.14292261004447937, | |
| "eval_runtime": 385.0382, | |
| "eval_samples_per_second": 15.009, | |
| "eval_steps_per_second": 1.878, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0303118624307782, | |
| "grad_norm": 1.704371690750122, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.031477703293500435, | |
| "grad_norm": 1.3473323583602905, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1554, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03264354415622268, | |
| "grad_norm": 2.562687635421753, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1205, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03380938501894491, | |
| "grad_norm": 1.177115559577942, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.034975225881667155, | |
| "grad_norm": 2.527552843093872, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1418, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03614106674438939, | |
| "grad_norm": 2.0997745990753174, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1238, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03730690760711163, | |
| "grad_norm": 1.3611961603164673, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1154, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03847274846983387, | |
| "grad_norm": 0.8035974502563477, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1221, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03963858933255611, | |
| "grad_norm": 1.2102768421173096, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1148, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.040804430195278345, | |
| "grad_norm": 1.1181646585464478, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1183, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04197027105800058, | |
| "grad_norm": 1.1671463251113892, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1271, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04313611192072282, | |
| "grad_norm": 2.192769765853882, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1297, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04430195278344506, | |
| "grad_norm": 1.4882858991622925, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1307, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0454677936461673, | |
| "grad_norm": 0.477984219789505, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1209, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.046633634508889535, | |
| "grad_norm": 0.4987645447254181, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04779947537161178, | |
| "grad_norm": 0.6753437519073486, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1193, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04896531623433401, | |
| "grad_norm": 0.557161808013916, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1209, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.050131157097056255, | |
| "grad_norm": 0.49947306513786316, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1271, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05129699795977849, | |
| "grad_norm": 0.6148838996887207, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1238, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05246283882250073, | |
| "grad_norm": 0.9675053358078003, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1403, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05362867968522297, | |
| "grad_norm": 0.7859569787979126, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1004, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 0.6264702081680298, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1157, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.055960361410667445, | |
| "grad_norm": 1.377821922302246, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1094, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05712620227338968, | |
| "grad_norm": 1.2376253604888916, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1575, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05829204313611192, | |
| "grad_norm": 0.8887091875076294, | |
| "learning_rate": 0.0, | |
| "loss": 0.1337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05829204313611192, | |
| "eval_loss": 0.12372367829084396, | |
| "eval_runtime": 386.06, | |
| "eval_samples_per_second": 14.969, | |
| "eval_steps_per_second": 1.873, | |
| "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 | |
| } | |