|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.6762849413886384, |
|
"eval_steps": 500, |
|
"global_step": 6000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01127141568981064, |
|
"grad_norm": 36.142295837402344, |
|
"learning_rate": 4.1666666666666667e-07, |
|
"loss": 12.6438, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02254283137962128, |
|
"grad_norm": 30.892282485961914, |
|
"learning_rate": 8.333333333333333e-07, |
|
"loss": 12.4413, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.03381424706943192, |
|
"grad_norm": 45.94392395019531, |
|
"learning_rate": 1.25e-06, |
|
"loss": 11.4952, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.04508566275924256, |
|
"grad_norm": 19.69997787475586, |
|
"learning_rate": 1.6666666666666667e-06, |
|
"loss": 7.0421, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.0563570784490532, |
|
"grad_norm": 3.0256764888763428, |
|
"learning_rate": 2.0833333333333334e-06, |
|
"loss": 3.1071, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.06762849413886383, |
|
"grad_norm": 1.9536222219467163, |
|
"learning_rate": 2.5e-06, |
|
"loss": 2.7468, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.07889990982867448, |
|
"grad_norm": 3.0367178916931152, |
|
"learning_rate": 2.916666666666667e-06, |
|
"loss": 2.5461, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.09017132551848513, |
|
"grad_norm": 1.1410305500030518, |
|
"learning_rate": 3.3333333333333333e-06, |
|
"loss": 2.3206, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.10144274120829576, |
|
"grad_norm": 1.2108758687973022, |
|
"learning_rate": 3.7500000000000005e-06, |
|
"loss": 2.036, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.1127141568981064, |
|
"grad_norm": 1.0124415159225464, |
|
"learning_rate": 4.166666666666667e-06, |
|
"loss": 1.9927, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.12398557258791704, |
|
"grad_norm": 1.2103397846221924, |
|
"learning_rate": 4.583333333333333e-06, |
|
"loss": 1.8255, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.13525698827772767, |
|
"grad_norm": 1.2905486822128296, |
|
"learning_rate": 5e-06, |
|
"loss": 1.6822, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.14652840396753833, |
|
"grad_norm": 0.9415493607521057, |
|
"learning_rate": 4.994647308096509e-06, |
|
"loss": 1.6783, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.15779981965734896, |
|
"grad_norm": 0.9576979279518127, |
|
"learning_rate": 4.978612153434527e-06, |
|
"loss": 1.5967, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.1690712353471596, |
|
"grad_norm": 1.068982481956482, |
|
"learning_rate": 4.9519632010080765e-06, |
|
"loss": 1.5821, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.18034265103697025, |
|
"grad_norm": 0.7473943829536438, |
|
"learning_rate": 4.914814565722671e-06, |
|
"loss": 1.5587, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.19161406672678089, |
|
"grad_norm": 0.9740411043167114, |
|
"learning_rate": 4.867325323737765e-06, |
|
"loss": 1.525, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.20288548241659152, |
|
"grad_norm": 0.6997997164726257, |
|
"learning_rate": 4.809698831278217e-06, |
|
"loss": 1.49, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.21415689810640218, |
|
"grad_norm": 0.6754641532897949, |
|
"learning_rate": 4.742181853831721e-06, |
|
"loss": 1.4597, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.2254283137962128, |
|
"grad_norm": 1.0468783378601074, |
|
"learning_rate": 4.665063509461098e-06, |
|
"loss": 1.4539, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.23669972948602344, |
|
"grad_norm": 0.9208471179008484, |
|
"learning_rate": 4.578674030756364e-06, |
|
"loss": 1.4459, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.24797114517583407, |
|
"grad_norm": 0.9443785548210144, |
|
"learning_rate": 4.4833833507280884e-06, |
|
"loss": 1.4437, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.25924256086564473, |
|
"grad_norm": 1.0956292152404785, |
|
"learning_rate": 4.379599518697444e-06, |
|
"loss": 1.417, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.27051397655545534, |
|
"grad_norm": 0.8564383387565613, |
|
"learning_rate": 4.267766952966369e-06, |
|
"loss": 1.4138, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.281785392245266, |
|
"grad_norm": 0.8340147733688354, |
|
"learning_rate": 4.1483645377501726e-06, |
|
"loss": 1.3637, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.29305680793507666, |
|
"grad_norm": 1.1379494667053223, |
|
"learning_rate": 4.021903572521802e-06, |
|
"loss": 1.4079, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.30432822362488726, |
|
"grad_norm": 0.8148013353347778, |
|
"learning_rate": 3.888925582549006e-06, |
|
"loss": 1.3729, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.3155996393146979, |
|
"grad_norm": 0.9854215383529663, |
|
"learning_rate": 3.7500000000000005e-06, |
|
"loss": 1.3824, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.3268710550045086, |
|
"grad_norm": 0.9190597534179688, |
|
"learning_rate": 3.6057217255475034e-06, |
|
"loss": 1.3879, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.3381424706943192, |
|
"grad_norm": 1.1362121105194092, |
|
"learning_rate": 3.4567085809127247e-06, |
|
"loss": 1.3939, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.34941388638412985, |
|
"grad_norm": 1.2068192958831787, |
|
"learning_rate": 3.303598663257904e-06, |
|
"loss": 1.3463, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.3606853020739405, |
|
"grad_norm": 0.952643632888794, |
|
"learning_rate": 3.147047612756302e-06, |
|
"loss": 1.3741, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.3719567177637511, |
|
"grad_norm": 0.8026754260063171, |
|
"learning_rate": 2.9877258050403214e-06, |
|
"loss": 1.3704, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.38322813345356177, |
|
"grad_norm": 0.8540117144584656, |
|
"learning_rate": 2.82631548055013e-06, |
|
"loss": 1.3904, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.39449954914337243, |
|
"grad_norm": 0.9906865954399109, |
|
"learning_rate": 2.663507823075358e-06, |
|
"loss": 1.3523, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.40577096483318303, |
|
"grad_norm": 0.8289706707000732, |
|
"learning_rate": 2.5e-06, |
|
"loss": 1.3519, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.4170423805229937, |
|
"grad_norm": 1.0827723741531372, |
|
"learning_rate": 2.3364921769246423e-06, |
|
"loss": 1.3475, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.42831379621280435, |
|
"grad_norm": 1.220688819885254, |
|
"learning_rate": 2.173684519449872e-06, |
|
"loss": 1.3243, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.43958521190261496, |
|
"grad_norm": 1.0109795331954956, |
|
"learning_rate": 2.01227419495968e-06, |
|
"loss": 1.3444, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.4508566275924256, |
|
"grad_norm": 1.041104793548584, |
|
"learning_rate": 1.852952387243698e-06, |
|
"loss": 1.3436, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.4621280432822362, |
|
"grad_norm": 0.7376370429992676, |
|
"learning_rate": 1.6964013367420967e-06, |
|
"loss": 1.3002, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 0.4733994589720469, |
|
"grad_norm": 0.8842127919197083, |
|
"learning_rate": 1.5432914190872757e-06, |
|
"loss": 1.3454, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 0.48467087466185754, |
|
"grad_norm": 1.0636272430419922, |
|
"learning_rate": 1.3942782744524974e-06, |
|
"loss": 1.3396, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 0.49594229035166815, |
|
"grad_norm": 1.2041317224502563, |
|
"learning_rate": 1.2500000000000007e-06, |
|
"loss": 1.335, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 0.5072137060414789, |
|
"grad_norm": 0.9379550218582153, |
|
"learning_rate": 1.1110744174509952e-06, |
|
"loss": 1.3213, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.5184851217312895, |
|
"grad_norm": 0.7874147891998291, |
|
"learning_rate": 9.780964274781984e-07, |
|
"loss": 1.3198, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 0.5297565374211001, |
|
"grad_norm": 0.7258532047271729, |
|
"learning_rate": 8.516354622498279e-07, |
|
"loss": 1.2681, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 0.5410279531109107, |
|
"grad_norm": 1.1035155057907104, |
|
"learning_rate": 7.322330470336314e-07, |
|
"loss": 1.3219, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 0.5522993688007214, |
|
"grad_norm": 0.7815728187561035, |
|
"learning_rate": 6.204004813025569e-07, |
|
"loss": 1.3381, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 0.563570784490532, |
|
"grad_norm": 1.0812482833862305, |
|
"learning_rate": 5.166166492719124e-07, |
|
"loss": 1.3322, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.5748422001803426, |
|
"grad_norm": 0.9642081260681152, |
|
"learning_rate": 4.2132596924363666e-07, |
|
"loss": 1.3218, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 0.5861136158701533, |
|
"grad_norm": 0.8039354085922241, |
|
"learning_rate": 3.3493649053890325e-07, |
|
"loss": 1.3216, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 0.5973850315599639, |
|
"grad_norm": 0.8643052577972412, |
|
"learning_rate": 2.5781814616827936e-07, |
|
"loss": 1.3333, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 0.6086564472497745, |
|
"grad_norm": 1.4110788106918335, |
|
"learning_rate": 1.9030116872178317e-07, |
|
"loss": 1.3412, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 0.6199278629395852, |
|
"grad_norm": 0.7792391180992126, |
|
"learning_rate": 1.3267467626223606e-07, |
|
"loss": 1.3069, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.6311992786293958, |
|
"grad_norm": 1.0475589036941528, |
|
"learning_rate": 8.518543427732951e-08, |
|
"loss": 1.3187, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 0.6424706943192064, |
|
"grad_norm": 0.9902795553207397, |
|
"learning_rate": 4.8036798991923925e-08, |
|
"loss": 1.328, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 0.6537421100090172, |
|
"grad_norm": 0.7977623343467712, |
|
"learning_rate": 2.1387846565474047e-08, |
|
"loss": 1.3175, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 0.6650135256988278, |
|
"grad_norm": 0.872138261795044, |
|
"learning_rate": 5.352691903491303e-09, |
|
"loss": 1.3116, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 0.6762849413886384, |
|
"grad_norm": 0.8640491366386414, |
|
"learning_rate": 0.0, |
|
"loss": 1.3081, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.6762849413886384, |
|
"step": 6000, |
|
"total_flos": 0.0, |
|
"train_loss": 2.13714133199056, |
|
"train_runtime": 37217.3738, |
|
"train_samples_per_second": 2.579, |
|
"train_steps_per_second": 0.161 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 6000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|