| { | |
| "best_metric": 0.27144113183021545, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.076510067114094, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021476510067114093, | |
| "grad_norm": 260.48162841796875, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021476510067114093, | |
| "eval_loss": 7.360443115234375, | |
| "eval_runtime": 15.4126, | |
| "eval_samples_per_second": 20.373, | |
| "eval_steps_per_second": 2.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042953020134228186, | |
| "grad_norm": 297.0155334472656, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0084, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06442953020134229, | |
| "grad_norm": 275.2556457519531, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.6849, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08590604026845637, | |
| "grad_norm": 352.376708984375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7447, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 91.99493408203125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.502, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12885906040268458, | |
| "grad_norm": 46.79368591308594, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1112, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15033557046979865, | |
| "grad_norm": 24.683958053588867, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17181208053691274, | |
| "grad_norm": 29.150592803955078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.947, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19328859060402684, | |
| "grad_norm": 47.48466491699219, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1741, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21476510067114093, | |
| "grad_norm": 216.91615295410156, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23624161073825503, | |
| "grad_norm": 94.46873474121094, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25771812080536916, | |
| "grad_norm": 29.807615280151367, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1499, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2791946308724832, | |
| "grad_norm": 17.8881778717041, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6092, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3006711409395973, | |
| "grad_norm": 17.096132278442383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3221476510067114, | |
| "grad_norm": 16.282032012939453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5441, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3436241610738255, | |
| "grad_norm": 17.785125732421875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4419, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3651006711409396, | |
| "grad_norm": 15.897377967834473, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3437, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3865771812080537, | |
| "grad_norm": 12.955235481262207, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4080536912751678, | |
| "grad_norm": 14.379870414733887, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2507, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.42953020134228187, | |
| "grad_norm": 24.634723663330078, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45100671140939597, | |
| "grad_norm": 24.113536834716797, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.343, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.47248322147651006, | |
| "grad_norm": 21.331897735595703, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3353, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.49395973154362416, | |
| "grad_norm": 30.45175552368164, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4716, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5154362416107383, | |
| "grad_norm": 57.83376693725586, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5369127516778524, | |
| "grad_norm": 33.72331237792969, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5804, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5369127516778524, | |
| "eval_loss": 0.3158932328224182, | |
| "eval_runtime": 15.3909, | |
| "eval_samples_per_second": 20.402, | |
| "eval_steps_per_second": 2.599, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5583892617449664, | |
| "grad_norm": 28.777877807617188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4573, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5798657718120805, | |
| "grad_norm": 17.136690139770508, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.287, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6013422818791946, | |
| "grad_norm": 14.741988182067871, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2617, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6228187919463087, | |
| "grad_norm": 10.193075180053711, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1994, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6442953020134228, | |
| "grad_norm": 7.09152364730835, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1473, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6657718120805369, | |
| "grad_norm": 10.199577331542969, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2079, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.687248322147651, | |
| "grad_norm": 9.366825103759766, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2648, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7087248322147651, | |
| "grad_norm": 10.735113143920898, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3117, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7302013422818792, | |
| "grad_norm": 7.8755316734313965, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3043, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7516778523489933, | |
| "grad_norm": 19.299285888671875, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7202, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7731543624161074, | |
| "grad_norm": 16.11593246459961, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4716, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7946308724832215, | |
| "grad_norm": 10.856176376342773, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3398, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8161073825503355, | |
| "grad_norm": 13.369665145874023, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4083, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8375838926174497, | |
| "grad_norm": 13.565021514892578, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3234, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8590604026845637, | |
| "grad_norm": 9.394250869750977, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2066, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8805369127516779, | |
| "grad_norm": 7.041374683380127, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1839, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9020134228187919, | |
| "grad_norm": 13.638995170593262, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1963, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9234899328859061, | |
| "grad_norm": 8.915301322937012, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1899, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9449664429530201, | |
| "grad_norm": 7.626116752624512, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2316, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9664429530201343, | |
| "grad_norm": 9.224981307983398, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2937, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9879194630872483, | |
| "grad_norm": 9.10223388671875, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2994, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0120805369127517, | |
| "grad_norm": 25.860401153564453, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7044, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0335570469798658, | |
| "grad_norm": 22.862300872802734, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4963, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0550335570469798, | |
| "grad_norm": 15.496158599853516, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3009, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.076510067114094, | |
| "grad_norm": 15.115484237670898, | |
| "learning_rate": 0.0, | |
| "loss": 0.3819, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.076510067114094, | |
| "eval_loss": 0.27144113183021545, | |
| "eval_runtime": 15.3658, | |
| "eval_samples_per_second": 20.435, | |
| "eval_steps_per_second": 2.603, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.990361686604513e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |