| { | |
| "best_metric": 0.2452608197927475, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3722126929674099, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0274442538593482, | |
| "grad_norm": 20.074077606201172, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0274442538593482, | |
| "eval_loss": 10.55981731414795, | |
| "eval_runtime": 7.5303, | |
| "eval_samples_per_second": 32.668, | |
| "eval_steps_per_second": 4.117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0548885077186964, | |
| "grad_norm": 20.803699493408203, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4168, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0823327615780446, | |
| "grad_norm": 23.21198081970215, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.4877, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1097770154373928, | |
| "grad_norm": 14.870956420898438, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.4101, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.137221269296741, | |
| "grad_norm": 27.13115882873535, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1646655231560892, | |
| "grad_norm": 21.948101043701172, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9779, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19210977701543738, | |
| "grad_norm": 11.35668659210205, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5681, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2195540308747856, | |
| "grad_norm": 7.486013412475586, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7649, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2469982847341338, | |
| "grad_norm": 1.9086415767669678, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.3772, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.274442538593482, | |
| "grad_norm": 8.544327735900879, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4924, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 6.786691665649414, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4259, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3293310463121784, | |
| "grad_norm": 7.901662349700928, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4542, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3567753001715266, | |
| "grad_norm": 9.522432327270508, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5027, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.38421955403087477, | |
| "grad_norm": 4.514120578765869, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3589, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.411663807890223, | |
| "grad_norm": 8.0164794921875, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4121, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4391080617495712, | |
| "grad_norm": 10.228675842285156, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4752, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4665523156089194, | |
| "grad_norm": 6.224624156951904, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.373, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4939965694682676, | |
| "grad_norm": 2.6834373474121094, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3268, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5214408233276158, | |
| "grad_norm": 5.358426094055176, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3802, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.548885077186964, | |
| "grad_norm": 3.045642375946045, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5763293310463122, | |
| "grad_norm": 2.567047595977783, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 3.1966068744659424, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3096, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6312178387650086, | |
| "grad_norm": 3.727959156036377, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3256, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6586620926243568, | |
| "grad_norm": 1.0659911632537842, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2684, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "grad_norm": 4.87954044342041, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "eval_loss": 0.30522599816322327, | |
| "eval_runtime": 7.5196, | |
| "eval_samples_per_second": 32.715, | |
| "eval_steps_per_second": 4.123, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7135506003430532, | |
| "grad_norm": 1.8627270460128784, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2793, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7409948542024014, | |
| "grad_norm": 2.5019619464874268, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2595, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7684391080617495, | |
| "grad_norm": 3.339423656463623, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2742, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7958833619210978, | |
| "grad_norm": 4.57916259765625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3306, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.823327615780446, | |
| "grad_norm": 2.4405033588409424, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8507718696397941, | |
| "grad_norm": 2.457447052001953, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2719, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8782161234991424, | |
| "grad_norm": 3.9348955154418945, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2754, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 3.3448519706726074, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2563, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9331046312178388, | |
| "grad_norm": 1.652413010597229, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2726, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9605488850771869, | |
| "grad_norm": 0.9518668055534363, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9879931389365352, | |
| "grad_norm": 1.1170496940612793, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2446, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0154373927958833, | |
| "grad_norm": 4.179270267486572, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3761, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0428816466552315, | |
| "grad_norm": 3.888280153274536, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.248, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0703259005145798, | |
| "grad_norm": 2.5763416290283203, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2139, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.097770154373928, | |
| "grad_norm": 4.430254936218262, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2449, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1252144082332762, | |
| "grad_norm": 1.2438457012176514, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.205, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1526586620926245, | |
| "grad_norm": 4.233536720275879, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2622, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1801029159519725, | |
| "grad_norm": 3.1736645698547363, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2163, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 2.0878634452819824, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2141, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.234991423670669, | |
| "grad_norm": 1.501262903213501, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1938, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2624356775300172, | |
| "grad_norm": 2.856403112411499, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2086, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2898799313893654, | |
| "grad_norm": 1.4120512008666992, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2055, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3173241852487134, | |
| "grad_norm": 0.8188878893852234, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2022, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3447684391080617, | |
| "grad_norm": 1.1168948411941528, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2211, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "grad_norm": 2.3238978385925293, | |
| "learning_rate": 0.0, | |
| "loss": 0.2294, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "eval_loss": 0.2452608197927475, | |
| "eval_runtime": 7.5089, | |
| "eval_samples_per_second": 32.761, | |
| "eval_steps_per_second": 4.128, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |