| { | |
| "best_metric": 10.859091758728027, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06400512040963277, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012801024081926554, | |
| "grad_norm": 7.932831287384033, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012801024081926554, | |
| "eval_loss": 11.107329368591309, | |
| "eval_runtime": 5.9013, | |
| "eval_samples_per_second": 891.844, | |
| "eval_steps_per_second": 111.502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002560204816385311, | |
| "grad_norm": 8.110054969787598, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1132, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038403072245779663, | |
| "grad_norm": 8.086522102355957, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.1008, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005120409632770622, | |
| "grad_norm": 8.630813598632812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.0995, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006400512040963277, | |
| "grad_norm": 8.999592781066895, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.0904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007680614449155933, | |
| "grad_norm": 8.825994491577148, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.075, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008960716857348588, | |
| "grad_norm": 9.3751859664917, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.0743, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010240819265541243, | |
| "grad_norm": 10.451610565185547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.0581, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011520921673733898, | |
| "grad_norm": 9.829924583435059, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.0484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012801024081926553, | |
| "grad_norm": 9.564868927001953, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.0434, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01408112649011921, | |
| "grad_norm": 10.038867950439453, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.0311, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015361228898311865, | |
| "grad_norm": 9.876754760742188, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.0287, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016641331306504522, | |
| "grad_norm": 9.104659080505371, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.0245, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017921433714697177, | |
| "grad_norm": 8.249415397644043, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0235, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019201536122889832, | |
| "grad_norm": 9.441581726074219, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.0043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020481638531082487, | |
| "grad_norm": 9.700508117675781, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.9933, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021761740939275142, | |
| "grad_norm": 9.133739471435547, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.9886, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023041843347467797, | |
| "grad_norm": 9.890276908874512, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.9686, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024321945755660452, | |
| "grad_norm": 10.736612319946289, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.951, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025602048163853107, | |
| "grad_norm": 10.405147552490234, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.9462, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026882150572045762, | |
| "grad_norm": 10.21131706237793, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.9428, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02816225298023842, | |
| "grad_norm": 10.646858215332031, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.9252, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029442355388431075, | |
| "grad_norm": 9.915033340454102, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.9348, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03072245779662373, | |
| "grad_norm": 9.764278411865234, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.9332, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032002560204816385, | |
| "grad_norm": 10.946702003479004, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.9174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032002560204816385, | |
| "eval_loss": 10.915375709533691, | |
| "eval_runtime": 5.8801, | |
| "eval_samples_per_second": 895.049, | |
| "eval_steps_per_second": 111.902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033282662613009044, | |
| "grad_norm": 9.160806655883789, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9391, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.034562765021201695, | |
| "grad_norm": 8.870255470275879, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.9376, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.035842867429394354, | |
| "grad_norm": 9.3232421875, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.9196, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.037122969837587005, | |
| "grad_norm": 9.68075942993164, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.8989, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.038403072245779664, | |
| "grad_norm": 9.822731018066406, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.8904, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.039683174653972315, | |
| "grad_norm": 10.109760284423828, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.8711, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.040963277062164974, | |
| "grad_norm": 10.420609474182129, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.8687, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042243379470357625, | |
| "grad_norm": 10.236992835998535, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.8692, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.043523481878550284, | |
| "grad_norm": 10.572797775268555, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.8552, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04480358428674294, | |
| "grad_norm": 10.187577247619629, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.8572, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.046083686694935594, | |
| "grad_norm": 10.250493049621582, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.8482, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04736378910312825, | |
| "grad_norm": 9.556073188781738, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.8744, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.048643891511320904, | |
| "grad_norm": 9.524937629699707, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.8739, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04992399391951356, | |
| "grad_norm": 8.893146514892578, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.8919, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.051204096327706214, | |
| "grad_norm": 9.009846687316895, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.8814, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05248419873589887, | |
| "grad_norm": 8.93393611907959, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.8815, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.053764301144091524, | |
| "grad_norm": 9.061225891113281, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.8766, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05504440355228418, | |
| "grad_norm": 9.76646614074707, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.8549, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05632450596047684, | |
| "grad_norm": 10.304689407348633, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.8355, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05760460836866949, | |
| "grad_norm": 9.984641075134277, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.8481, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05888471077686215, | |
| "grad_norm": 9.914651870727539, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.8374, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0601648131850548, | |
| "grad_norm": 9.991412162780762, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.8372, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06144491559324746, | |
| "grad_norm": 10.301223754882812, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.837, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06272501800144012, | |
| "grad_norm": 9.447504043579102, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.8695, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06400512040963277, | |
| "grad_norm": 10.3909273147583, | |
| "learning_rate": 0.0, | |
| "loss": 10.8582, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06400512040963277, | |
| "eval_loss": 10.859091758728027, | |
| "eval_runtime": 5.8597, | |
| "eval_samples_per_second": 898.169, | |
| "eval_steps_per_second": 112.292, | |
| "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": 38111123865600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |