| { | |
| "best_metric": 0.9118998050689697, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6606110652353427, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013212221304706853, | |
| "grad_norm": 1.2870376110076904, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013212221304706853, | |
| "eval_loss": 1.7167054414749146, | |
| "eval_runtime": 14.6603, | |
| "eval_samples_per_second": 34.788, | |
| "eval_steps_per_second": 4.366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026424442609413706, | |
| "grad_norm": 1.4486762285232544, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5022, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03963666391412056, | |
| "grad_norm": 1.2452460527420044, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4693, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05284888521882741, | |
| "grad_norm": 0.6154419183731079, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2748, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06606110652353427, | |
| "grad_norm": 0.9659808874130249, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2324, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07927332782824112, | |
| "grad_norm": 0.8188905715942383, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1943, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "grad_norm": 0.5846065282821655, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1858, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10569777043765483, | |
| "grad_norm": 0.4987255036830902, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1155, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11890999174236168, | |
| "grad_norm": 0.5043891668319702, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13212221304706853, | |
| "grad_norm": 0.42246687412261963, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0906, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1453344343517754, | |
| "grad_norm": 0.4438551664352417, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15854665565648224, | |
| "grad_norm": 0.5291683673858643, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9808, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1717588769611891, | |
| "grad_norm": 0.793207049369812, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0404, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "grad_norm": 0.6453374028205872, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9871, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1981833195706028, | |
| "grad_norm": 0.6586290597915649, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0034, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21139554087530965, | |
| "grad_norm": 0.879540205001831, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9909, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22460776218001652, | |
| "grad_norm": 0.4398188889026642, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9698, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23781998348472336, | |
| "grad_norm": 0.8094491958618164, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9729, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2510322047894302, | |
| "grad_norm": 0.3331429660320282, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.957, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26424442609413706, | |
| "grad_norm": 0.5275089740753174, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9532, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2774566473988439, | |
| "grad_norm": 0.5583062767982483, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2906688687035508, | |
| "grad_norm": 0.4108506143093109, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9306, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.30388109000825764, | |
| "grad_norm": 0.36984366178512573, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9647, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3170933113129645, | |
| "grad_norm": 0.39156898856163025, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9098, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33030553261767137, | |
| "grad_norm": 0.6336630582809448, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8419, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33030553261767137, | |
| "eval_loss": 0.9369022250175476, | |
| "eval_runtime": 14.6426, | |
| "eval_samples_per_second": 34.83, | |
| "eval_steps_per_second": 4.371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3435177539223782, | |
| "grad_norm": 0.4335106909275055, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9927, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35672997522708505, | |
| "grad_norm": 0.4817415177822113, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9772, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3699421965317919, | |
| "grad_norm": 0.4249557852745056, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9824, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3831544178364988, | |
| "grad_norm": 0.37584105134010315, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9446, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3963666391412056, | |
| "grad_norm": 0.3376809060573578, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9574, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40957886044591246, | |
| "grad_norm": 0.274263858795166, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.915, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4227910817506193, | |
| "grad_norm": 0.2863050103187561, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9271, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4360033030553262, | |
| "grad_norm": 0.2439480870962143, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9205, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44921552436003304, | |
| "grad_norm": 0.327269583940506, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8951, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4624277456647399, | |
| "grad_norm": 0.33922868967056274, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4756399669694467, | |
| "grad_norm": 0.3129810392856598, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9269, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4888521882741536, | |
| "grad_norm": 0.505581259727478, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5020644095788604, | |
| "grad_norm": 0.36821824312210083, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9218, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5152766308835673, | |
| "grad_norm": 0.4120348393917084, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.9595, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5284888521882741, | |
| "grad_norm": 0.38509809970855713, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.541701073492981, | |
| "grad_norm": 0.32172009348869324, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9401, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5549132947976878, | |
| "grad_norm": 0.2821166515350342, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9336, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5681255161023947, | |
| "grad_norm": 0.20851825177669525, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9049, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5813377374071016, | |
| "grad_norm": 0.23832282423973083, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.931, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5945499587118084, | |
| "grad_norm": 0.23053020238876343, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.919, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6077621800165153, | |
| "grad_norm": 0.32718178629875183, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9049, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6209744013212222, | |
| "grad_norm": 0.3872445821762085, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9391, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.634186622625929, | |
| "grad_norm": 0.34386420249938965, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9179, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6473988439306358, | |
| "grad_norm": 0.3821120262145996, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9039, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6606110652353427, | |
| "grad_norm": 0.6619767546653748, | |
| "learning_rate": 0.0, | |
| "loss": 0.8356, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6606110652353427, | |
| "eval_loss": 0.9118998050689697, | |
| "eval_runtime": 14.644, | |
| "eval_samples_per_second": 34.826, | |
| "eval_steps_per_second": 4.37, | |
| "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": 5.259104775831552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |