| { | |
| "best_metric": 0.15093161165714264, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1816838995568686, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023633677991137372, | |
| "grad_norm": 36.13075637817383, | |
| "learning_rate": 5e-05, | |
| "loss": 14.8253, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023633677991137372, | |
| "eval_loss": 15.885754585266113, | |
| "eval_runtime": 12.6282, | |
| "eval_samples_per_second": 22.648, | |
| "eval_steps_per_second": 2.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.047267355982274745, | |
| "grad_norm": 40.872886657714844, | |
| "learning_rate": 0.0001, | |
| "loss": 15.5628, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07090103397341212, | |
| "grad_norm": 35.460655212402344, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.9899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09453471196454949, | |
| "grad_norm": 33.51130294799805, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.1501, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11816838995568685, | |
| "grad_norm": 23.153060913085938, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.9594, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14180206794682423, | |
| "grad_norm": 8.426461219787598, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2076, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1654357459379616, | |
| "grad_norm": 9.334433555603027, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0174, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18906942392909898, | |
| "grad_norm": 7.1330180168151855, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21270310192023634, | |
| "grad_norm": 25.25038719177246, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0518, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2363367799113737, | |
| "grad_norm": 19.066661834716797, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25997045790251105, | |
| "grad_norm": 2.192826747894287, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.302, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28360413589364847, | |
| "grad_norm": 0.9697281718254089, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.2422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3072378138847858, | |
| "grad_norm": 2.184361219406128, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3308714918759232, | |
| "grad_norm": 5.644247531890869, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3174, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.35450516986706054, | |
| "grad_norm": 1.0984175205230713, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2351, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.37813884785819796, | |
| "grad_norm": 4.182483196258545, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2719, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4017725258493353, | |
| "grad_norm": 5.4484758377075195, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2953, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4254062038404727, | |
| "grad_norm": 1.4386926889419556, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2363, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.44903988183161003, | |
| "grad_norm": 2.446730136871338, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2525, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4726735598227474, | |
| "grad_norm": 0.9701130986213684, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2355, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4963072378138848, | |
| "grad_norm": 2.5759549140930176, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.243, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5199409158050221, | |
| "grad_norm": 0.998708963394165, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1983, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5435745937961596, | |
| "grad_norm": 3.6955859661102295, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2304, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5672082717872969, | |
| "grad_norm": 3.4236507415771484, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2594, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "grad_norm": 0.705708920955658, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1947, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5908419497784343, | |
| "eval_loss": 0.24974502623081207, | |
| "eval_runtime": 5.761, | |
| "eval_samples_per_second": 49.644, | |
| "eval_steps_per_second": 6.249, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6144756277695717, | |
| "grad_norm": 4.591713905334473, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2397, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.638109305760709, | |
| "grad_norm": 4.146514415740967, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2351, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6617429837518464, | |
| "grad_norm": 2.406968355178833, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2146, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6853766617429837, | |
| "grad_norm": 0.6187187433242798, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2175, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7090103397341211, | |
| "grad_norm": 2.0070714950561523, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.212, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7326440177252584, | |
| "grad_norm": 2.084167718887329, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1694, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7562776957163959, | |
| "grad_norm": 1.9323058128356934, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1806, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7799113737075333, | |
| "grad_norm": 2.303253412246704, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1458, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8035450516986706, | |
| "grad_norm": 1.032419204711914, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1421, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.827178729689808, | |
| "grad_norm": 0.9199665188789368, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1829, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8508124076809453, | |
| "grad_norm": 1.3219627141952515, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2118, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8744460856720827, | |
| "grad_norm": 1.3310699462890625, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1886, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8980797636632201, | |
| "grad_norm": 1.1247669458389282, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1896, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9217134416543574, | |
| "grad_norm": 1.5984141826629639, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9453471196454948, | |
| "grad_norm": 1.794048547744751, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1466, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9689807976366323, | |
| "grad_norm": 1.0123627185821533, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1883, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9926144756277696, | |
| "grad_norm": 0.8090836405754089, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1501, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.016248153618907, | |
| "grad_norm": 4.631110668182373, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2396, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0398818316100442, | |
| "grad_norm": 1.457216739654541, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1558, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0635155096011817, | |
| "grad_norm": 3.9395034313201904, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1582, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0871491875923192, | |
| "grad_norm": 1.5542545318603516, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1492, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1107828655834564, | |
| "grad_norm": 3.0677404403686523, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1387, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1344165435745939, | |
| "grad_norm": 1.127978801727295, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1864, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1580502215657311, | |
| "grad_norm": 2.2917068004608154, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1743, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1816838995568686, | |
| "grad_norm": 2.9250011444091797, | |
| "learning_rate": 0.0, | |
| "loss": 0.1453, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1816838995568686, | |
| "eval_loss": 0.15093161165714264, | |
| "eval_runtime": 5.7417, | |
| "eval_samples_per_second": 49.811, | |
| "eval_steps_per_second": 6.27, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |