baichuan-7B-alpaca-gpt4-zh / trainer_state.json
Sylvia2025's picture
Upload folder using huggingface_hub
5f9c60b verified
raw
history blame
9.69 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 375,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 0.00019991228300988585,
"loss": 2.1829,
"step": 5
},
{
"epoch": 0.08,
"learning_rate": 0.00019964928592495045,
"loss": 1.8983,
"step": 10
},
{
"epoch": 0.12,
"learning_rate": 0.0001992114701314478,
"loss": 1.7871,
"step": 15
},
{
"epoch": 0.16,
"learning_rate": 0.0001985996037070505,
"loss": 1.8482,
"step": 20
},
{
"epoch": 0.2,
"learning_rate": 0.00019781476007338058,
"loss": 1.731,
"step": 25
},
{
"epoch": 0.24,
"learning_rate": 0.0001968583161128631,
"loss": 1.6797,
"step": 30
},
{
"epoch": 0.28,
"learning_rate": 0.00019573194975320673,
"loss": 1.6694,
"step": 35
},
{
"epoch": 0.32,
"learning_rate": 0.00019443763702374812,
"loss": 1.7493,
"step": 40
},
{
"epoch": 0.36,
"learning_rate": 0.00019297764858882514,
"loss": 1.7823,
"step": 45
},
{
"epoch": 0.4,
"learning_rate": 0.0001913545457642601,
"loss": 1.6518,
"step": 50
},
{
"epoch": 0.44,
"learning_rate": 0.0001895711760239413,
"loss": 1.7334,
"step": 55
},
{
"epoch": 0.48,
"learning_rate": 0.00018763066800438636,
"loss": 1.7565,
"step": 60
},
{
"epoch": 0.52,
"learning_rate": 0.00018553642601605068,
"loss": 1.6493,
"step": 65
},
{
"epoch": 0.56,
"learning_rate": 0.00018329212407100994,
"loss": 1.7431,
"step": 70
},
{
"epoch": 0.6,
"learning_rate": 0.00018090169943749476,
"loss": 1.7561,
"step": 75
},
{
"epoch": 0.64,
"learning_rate": 0.000178369345732584,
"loss": 1.6185,
"step": 80
},
{
"epoch": 0.68,
"learning_rate": 0.00017569950556517566,
"loss": 1.6059,
"step": 85
},
{
"epoch": 0.72,
"learning_rate": 0.00017289686274214118,
"loss": 1.772,
"step": 90
},
{
"epoch": 0.76,
"learning_rate": 0.00016996633405133655,
"loss": 1.5847,
"step": 95
},
{
"epoch": 0.8,
"learning_rate": 0.00016691306063588583,
"loss": 1.615,
"step": 100
},
{
"epoch": 0.84,
"learning_rate": 0.000163742398974869,
"loss": 1.5706,
"step": 105
},
{
"epoch": 0.88,
"learning_rate": 0.0001604599114862375,
"loss": 1.6997,
"step": 110
},
{
"epoch": 0.92,
"learning_rate": 0.0001570713567684432,
"loss": 1.5529,
"step": 115
},
{
"epoch": 0.96,
"learning_rate": 0.00015358267949789966,
"loss": 1.6631,
"step": 120
},
{
"epoch": 1.0,
"learning_rate": 0.00015000000000000001,
"loss": 1.7483,
"step": 125
},
{
"epoch": 1.04,
"learning_rate": 0.00014632960351198618,
"loss": 1.708,
"step": 130
},
{
"epoch": 1.08,
"learning_rate": 0.00014257792915650728,
"loss": 1.6979,
"step": 135
},
{
"epoch": 1.12,
"learning_rate": 0.0001387515586452103,
"loss": 1.53,
"step": 140
},
{
"epoch": 1.16,
"learning_rate": 0.00013485720473218154,
"loss": 1.6821,
"step": 145
},
{
"epoch": 1.2,
"learning_rate": 0.00013090169943749476,
"loss": 1.7208,
"step": 150
},
{
"epoch": 1.24,
"learning_rate": 0.00012689198206152657,
"loss": 1.6841,
"step": 155
},
{
"epoch": 1.28,
"learning_rate": 0.00012283508701106557,
"loss": 1.544,
"step": 160
},
{
"epoch": 1.32,
"learning_rate": 0.00011873813145857249,
"loss": 1.5851,
"step": 165
},
{
"epoch": 1.36,
"learning_rate": 0.00011460830285624118,
"loss": 1.56,
"step": 170
},
{
"epoch": 1.4,
"learning_rate": 0.00011045284632676536,
"loss": 1.5691,
"step": 175
},
{
"epoch": 1.44,
"learning_rate": 0.00010627905195293135,
"loss": 1.5201,
"step": 180
},
{
"epoch": 1.48,
"learning_rate": 0.0001020942419883357,
"loss": 1.5098,
"step": 185
},
{
"epoch": 1.52,
"learning_rate": 9.790575801166432e-05,
"loss": 1.5805,
"step": 190
},
{
"epoch": 1.56,
"learning_rate": 9.372094804706867e-05,
"loss": 1.6742,
"step": 195
},
{
"epoch": 1.6,
"learning_rate": 8.954715367323468e-05,
"loss": 1.5656,
"step": 200
},
{
"epoch": 1.64,
"learning_rate": 8.539169714375885e-05,
"loss": 1.6301,
"step": 205
},
{
"epoch": 1.68,
"learning_rate": 8.126186854142752e-05,
"loss": 1.6027,
"step": 210
},
{
"epoch": 1.72,
"learning_rate": 7.716491298893442e-05,
"loss": 1.6494,
"step": 215
},
{
"epoch": 1.76,
"learning_rate": 7.310801793847344e-05,
"loss": 1.5962,
"step": 220
},
{
"epoch": 1.8,
"learning_rate": 6.909830056250527e-05,
"loss": 1.5375,
"step": 225
},
{
"epoch": 1.84,
"learning_rate": 6.51427952678185e-05,
"loss": 1.596,
"step": 230
},
{
"epoch": 1.88,
"learning_rate": 6.12484413547897e-05,
"loss": 1.6401,
"step": 235
},
{
"epoch": 1.92,
"learning_rate": 5.7422070843492734e-05,
"loss": 1.5735,
"step": 240
},
{
"epoch": 1.96,
"learning_rate": 5.3670396488013854e-05,
"loss": 1.6057,
"step": 245
},
{
"epoch": 2.0,
"learning_rate": 5.000000000000002e-05,
"loss": 1.5428,
"step": 250
},
{
"epoch": 2.04,
"learning_rate": 4.6417320502100316e-05,
"loss": 1.6843,
"step": 255
},
{
"epoch": 2.08,
"learning_rate": 4.2928643231556844e-05,
"loss": 1.6004,
"step": 260
},
{
"epoch": 2.12,
"learning_rate": 3.954008851376252e-05,
"loss": 1.5231,
"step": 265
},
{
"epoch": 2.16,
"learning_rate": 3.6257601025131026e-05,
"loss": 1.6147,
"step": 270
},
{
"epoch": 2.2,
"learning_rate": 3.308693936411421e-05,
"loss": 1.5095,
"step": 275
},
{
"epoch": 2.24,
"learning_rate": 3.0033665948663448e-05,
"loss": 1.6355,
"step": 280
},
{
"epoch": 2.28,
"learning_rate": 2.7103137257858868e-05,
"loss": 1.4353,
"step": 285
},
{
"epoch": 2.32,
"learning_rate": 2.4300494434824373e-05,
"loss": 1.5886,
"step": 290
},
{
"epoch": 2.36,
"learning_rate": 2.163065426741603e-05,
"loss": 1.5915,
"step": 295
},
{
"epoch": 2.4,
"learning_rate": 1.9098300562505266e-05,
"loss": 1.5584,
"step": 300
},
{
"epoch": 2.44,
"learning_rate": 1.6707875928990058e-05,
"loss": 1.4628,
"step": 305
},
{
"epoch": 2.48,
"learning_rate": 1.4463573983949341e-05,
"loss": 1.5502,
"step": 310
},
{
"epoch": 2.52,
"learning_rate": 1.2369331995613665e-05,
"loss": 1.4882,
"step": 315
},
{
"epoch": 2.56,
"learning_rate": 1.042882397605871e-05,
"loss": 1.6666,
"step": 320
},
{
"epoch": 2.6,
"learning_rate": 8.645454235739903e-06,
"loss": 1.4874,
"step": 325
},
{
"epoch": 2.64,
"learning_rate": 7.022351411174866e-06,
"loss": 1.6158,
"step": 330
},
{
"epoch": 2.68,
"learning_rate": 5.562362976251901e-06,
"loss": 1.4376,
"step": 335
},
{
"epoch": 2.72,
"learning_rate": 4.268050246793276e-06,
"loss": 1.6202,
"step": 340
},
{
"epoch": 2.76,
"learning_rate": 3.1416838871368924e-06,
"loss": 1.5493,
"step": 345
},
{
"epoch": 2.8,
"learning_rate": 2.1852399266194314e-06,
"loss": 1.6157,
"step": 350
},
{
"epoch": 2.84,
"learning_rate": 1.400396292949513e-06,
"loss": 1.5631,
"step": 355
},
{
"epoch": 2.88,
"learning_rate": 7.885298685522235e-07,
"loss": 1.5326,
"step": 360
},
{
"epoch": 2.92,
"learning_rate": 3.50714075049563e-07,
"loss": 1.5978,
"step": 365
},
{
"epoch": 2.96,
"learning_rate": 8.771699011416168e-08,
"loss": 1.4251,
"step": 370
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 1.6276,
"step": 375
},
{
"epoch": 3.0,
"step": 375,
"total_flos": 4.32034079145984e+16,
"train_loss": 1.628477378845215,
"train_runtime": 1045.5144,
"train_samples_per_second": 5.739,
"train_steps_per_second": 0.359
}
],
"logging_steps": 5,
"max_steps": 375,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 4.32034079145984e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}