| { | |
| "best_metric": 0.2574620842933655, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9900990099009901, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 1.6398431062698364, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "eval_loss": 1.9324251413345337, | |
| "eval_runtime": 7.1413, | |
| "eval_samples_per_second": 47.611, | |
| "eval_steps_per_second": 6.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": 3.625762939453125, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1194, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": 2.0851995944976807, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1887, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 1.5902670621871948, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.0174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": 1.2710622549057007, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8691, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": 1.5258872509002686, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8245, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13861386138613863, | |
| "grad_norm": 2.029459238052368, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7216, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 3.381009340286255, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6468, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "grad_norm": 4.212033271789551, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": 2.7730231285095215, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21782178217821782, | |
| "grad_norm": 1.1374902725219727, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2899, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 1.3583406209945679, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.25742574257425743, | |
| "grad_norm": 0.9472855925559998, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5469, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.27722772277227725, | |
| "grad_norm": 1.2495436668395996, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.781, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": 0.980268120765686, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5808, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 0.534701406955719, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2648, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.33663366336633666, | |
| "grad_norm": 0.6623193025588989, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2866, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": 0.6710707545280457, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2469, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37623762376237624, | |
| "grad_norm": 0.5663846731185913, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2509, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 0.5517411231994629, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2508, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "grad_norm": 0.6210505366325378, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.43564356435643564, | |
| "grad_norm": 0.5595400333404541, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2429, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.45544554455445546, | |
| "grad_norm": 0.33600038290023804, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.193, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.4488532841205597, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2291, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": 0.4629361927509308, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "eval_loss": 0.29733970761299133, | |
| "eval_runtime": 7.2562, | |
| "eval_samples_per_second": 46.857, | |
| "eval_steps_per_second": 5.926, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "grad_norm": 1.579128623008728, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3964, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "grad_norm": 2.4357690811157227, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5525, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 0.5066600441932678, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2158, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5742574257425742, | |
| "grad_norm": 0.38489776849746704, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1754, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": 0.490718811750412, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6138613861386139, | |
| "grad_norm": 0.4304322600364685, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.21, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 0.4170798659324646, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2555, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "grad_norm": 0.40130844712257385, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.221, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6732673267326733, | |
| "grad_norm": 0.5818941593170166, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2613, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.693069306930693, | |
| "grad_norm": 0.3248800039291382, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1721, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": 0.4679916203022003, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1775, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7326732673267327, | |
| "grad_norm": 0.5681194067001343, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2262, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7524752475247525, | |
| "grad_norm": 0.38346973061561584, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2734, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7722772277227723, | |
| "grad_norm": 0.8030109405517578, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3437, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 0.6876556873321533, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8118811881188119, | |
| "grad_norm": 0.3529515564441681, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.168, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "grad_norm": 0.38451874256134033, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2113, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8514851485148515, | |
| "grad_norm": 0.5104249119758606, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2143, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": 0.3389572203159332, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2147, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8910891089108911, | |
| "grad_norm": 0.33520424365997314, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2277, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9108910891089109, | |
| "grad_norm": 0.42593881487846375, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.196, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9306930693069307, | |
| "grad_norm": 0.4380699694156647, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1778, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 0.2996169328689575, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1594, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9702970297029703, | |
| "grad_norm": 0.5161162614822388, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2087, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": 0.4516996741294861, | |
| "learning_rate": 0.0, | |
| "loss": 0.2422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "eval_loss": 0.2574620842933655, | |
| "eval_runtime": 7.1505, | |
| "eval_samples_per_second": 47.549, | |
| "eval_steps_per_second": 6.014, | |
| "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": 2.5852360295186432e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |