klora_2000_skill / 18 /trainer_state.json
RayDu0010's picture
Upload folder using huggingface_hub
09ba0d8 verified
raw
history blame
13.6 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 374,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02680965147453083,
"grad_norm": 1.2595338821411133,
"learning_rate": 2.553191489361702e-06,
"loss": 1.2564,
"step": 5
},
{
"epoch": 0.05361930294906166,
"grad_norm": 0.8211272954940796,
"learning_rate": 5.74468085106383e-06,
"loss": 1.2441,
"step": 10
},
{
"epoch": 0.08042895442359249,
"grad_norm": 0.538611114025116,
"learning_rate": 8.936170212765958e-06,
"loss": 1.2797,
"step": 15
},
{
"epoch": 0.10723860589812333,
"grad_norm": 0.5027714967727661,
"learning_rate": 1.2127659574468084e-05,
"loss": 1.2048,
"step": 20
},
{
"epoch": 0.13404825737265416,
"grad_norm": 0.5756029486656189,
"learning_rate": 1.531914893617021e-05,
"loss": 1.1463,
"step": 25
},
{
"epoch": 0.16085790884718498,
"grad_norm": 0.5522626042366028,
"learning_rate": 1.8510638297872342e-05,
"loss": 1.1146,
"step": 30
},
{
"epoch": 0.1876675603217158,
"grad_norm": 0.46792927384376526,
"learning_rate": 2.170212765957447e-05,
"loss": 1.1107,
"step": 35
},
{
"epoch": 0.21447721179624665,
"grad_norm": 0.50309157371521,
"learning_rate": 2.4893617021276595e-05,
"loss": 1.0734,
"step": 40
},
{
"epoch": 0.24128686327077747,
"grad_norm": 0.5362275242805481,
"learning_rate": 2.8085106382978723e-05,
"loss": 1.1417,
"step": 45
},
{
"epoch": 0.2680965147453083,
"grad_norm": 0.5180004835128784,
"learning_rate": 2.9999624514425663e-05,
"loss": 1.0767,
"step": 50
},
{
"epoch": 0.2949061662198391,
"grad_norm": 0.549150824546814,
"learning_rate": 2.9995400517601418e-05,
"loss": 1.0173,
"step": 55
},
{
"epoch": 0.32171581769436997,
"grad_norm": 0.5453264117240906,
"learning_rate": 2.9986484493070226e-05,
"loss": 1.0292,
"step": 60
},
{
"epoch": 0.3485254691689008,
"grad_norm": 0.4556148946285248,
"learning_rate": 2.9972879230636458e-05,
"loss": 1.0466,
"step": 65
},
{
"epoch": 0.3753351206434316,
"grad_norm": 0.5285739302635193,
"learning_rate": 2.995458898735669e-05,
"loss": 1.0229,
"step": 70
},
{
"epoch": 0.40214477211796246,
"grad_norm": 0.5649049282073975,
"learning_rate": 2.993161948620766e-05,
"loss": 0.9187,
"step": 75
},
{
"epoch": 0.4289544235924933,
"grad_norm": 0.48927125334739685,
"learning_rate": 2.9903977914295546e-05,
"loss": 0.9293,
"step": 80
},
{
"epoch": 0.45576407506702415,
"grad_norm": 0.5317280292510986,
"learning_rate": 2.9871672920607158e-05,
"loss": 0.8919,
"step": 85
},
{
"epoch": 0.48257372654155495,
"grad_norm": 0.6437996625900269,
"learning_rate": 2.983471461330368e-05,
"loss": 0.9002,
"step": 90
},
{
"epoch": 0.5093833780160858,
"grad_norm": 0.5929898023605347,
"learning_rate": 2.9793114556557854e-05,
"loss": 0.8927,
"step": 95
},
{
"epoch": 0.5361930294906166,
"grad_norm": 0.6423819065093994,
"learning_rate": 2.9746885766935564e-05,
"loss": 0.8444,
"step": 100
},
{
"epoch": 0.5630026809651475,
"grad_norm": 0.6655325889587402,
"learning_rate": 2.9696042709322998e-05,
"loss": 0.8668,
"step": 105
},
{
"epoch": 0.5898123324396782,
"grad_norm": 0.738153874874115,
"learning_rate": 2.96406012924006e-05,
"loss": 0.861,
"step": 110
},
{
"epoch": 0.6166219839142091,
"grad_norm": 0.8325274586677551,
"learning_rate": 2.9580578863665296e-05,
"loss": 0.8202,
"step": 115
},
{
"epoch": 0.6434316353887399,
"grad_norm": 0.7488914132118225,
"learning_rate": 2.9515994204002485e-05,
"loss": 0.7684,
"step": 120
},
{
"epoch": 0.6702412868632708,
"grad_norm": 0.7176592350006104,
"learning_rate": 2.944686752180955e-05,
"loss": 0.8053,
"step": 125
},
{
"epoch": 0.6970509383378016,
"grad_norm": 0.8424944281578064,
"learning_rate": 2.9373220446672687e-05,
"loss": 0.7371,
"step": 130
},
{
"epoch": 0.7238605898123325,
"grad_norm": 0.7524424195289612,
"learning_rate": 2.929507602259908e-05,
"loss": 0.7762,
"step": 135
},
{
"epoch": 0.7506702412868632,
"grad_norm": 0.8609856367111206,
"learning_rate": 2.9212458700806445e-05,
"loss": 0.7208,
"step": 140
},
{
"epoch": 0.7774798927613941,
"grad_norm": 0.8293251991271973,
"learning_rate": 2.912539433207233e-05,
"loss": 0.7078,
"step": 145
},
{
"epoch": 0.8042895442359249,
"grad_norm": 0.9803098440170288,
"learning_rate": 2.9033910158645433e-05,
"loss": 0.6701,
"step": 150
},
{
"epoch": 0.8310991957104558,
"grad_norm": 0.8112236261367798,
"learning_rate": 2.8938034805721598e-05,
"loss": 0.6631,
"step": 155
},
{
"epoch": 0.8579088471849866,
"grad_norm": 0.8429144620895386,
"learning_rate": 2.883779827248703e-05,
"loss": 0.6774,
"step": 160
},
{
"epoch": 0.8847184986595175,
"grad_norm": 0.9313247203826904,
"learning_rate": 2.873323192273162e-05,
"loss": 0.6536,
"step": 165
},
{
"epoch": 0.9115281501340483,
"grad_norm": 0.8465601205825806,
"learning_rate": 2.8624368475035283e-05,
"loss": 0.6697,
"step": 170
},
{
"epoch": 0.938337801608579,
"grad_norm": 1.0963940620422363,
"learning_rate": 2.8511241992530403e-05,
"loss": 0.6171,
"step": 175
},
{
"epoch": 0.9651474530831099,
"grad_norm": 0.9651685357093811,
"learning_rate": 2.8393887872243528e-05,
"loss": 0.6423,
"step": 180
},
{
"epoch": 0.9919571045576407,
"grad_norm": 0.8953330516815186,
"learning_rate": 2.8272342834019738e-05,
"loss": 0.5673,
"step": 185
},
{
"epoch": 1.0160857908847185,
"grad_norm": 1.117424726486206,
"learning_rate": 2.814664490903309e-05,
"loss": 0.5467,
"step": 190
},
{
"epoch": 1.0428954423592494,
"grad_norm": 0.8842881917953491,
"learning_rate": 2.801683342788671e-05,
"loss": 0.5333,
"step": 195
},
{
"epoch": 1.0697050938337802,
"grad_norm": 1.0800713300704956,
"learning_rate": 2.7882949008306392e-05,
"loss": 0.5203,
"step": 200
},
{
"epoch": 1.096514745308311,
"grad_norm": 1.0497684478759766,
"learning_rate": 2.7745033542431358e-05,
"loss": 0.48,
"step": 205
},
{
"epoch": 1.123324396782842,
"grad_norm": 1.2430580854415894,
"learning_rate": 2.7603130183706317e-05,
"loss": 0.4952,
"step": 210
},
{
"epoch": 1.1501340482573728,
"grad_norm": 0.9467598795890808,
"learning_rate": 2.7457283333378838e-05,
"loss": 0.4694,
"step": 215
},
{
"epoch": 1.1769436997319036,
"grad_norm": 1.2572771310806274,
"learning_rate": 2.7307538626606314e-05,
"loss": 0.486,
"step": 220
},
{
"epoch": 1.2037533512064342,
"grad_norm": 1.1049180030822754,
"learning_rate": 2.71539429181768e-05,
"loss": 0.5286,
"step": 225
},
{
"epoch": 1.230563002680965,
"grad_norm": 1.1196273565292358,
"learning_rate": 2.699654426784828e-05,
"loss": 0.4741,
"step": 230
},
{
"epoch": 1.257372654155496,
"grad_norm": 1.078421711921692,
"learning_rate": 2.6835391925310842e-05,
"loss": 0.446,
"step": 235
},
{
"epoch": 1.2841823056300268,
"grad_norm": 1.0374311208724976,
"learning_rate": 2.6670536314776593e-05,
"loss": 0.4533,
"step": 240
},
{
"epoch": 1.3109919571045576,
"grad_norm": 1.030749797821045,
"learning_rate": 2.6502029019202007e-05,
"loss": 0.444,
"step": 245
},
{
"epoch": 1.3378016085790885,
"grad_norm": 1.2583510875701904,
"learning_rate": 2.632992276414775e-05,
"loss": 0.4296,
"step": 250
},
{
"epoch": 1.3646112600536193,
"grad_norm": 1.0695934295654297,
"learning_rate": 2.615427140128096e-05,
"loss": 0.4416,
"step": 255
},
{
"epoch": 1.3914209115281502,
"grad_norm": 1.1195570230484009,
"learning_rate": 2.5975129891525173e-05,
"loss": 0.431,
"step": 260
},
{
"epoch": 1.418230563002681,
"grad_norm": 1.295849084854126,
"learning_rate": 2.5792554287863197e-05,
"loss": 0.3968,
"step": 265
},
{
"epoch": 1.4450402144772119,
"grad_norm": 1.0494529008865356,
"learning_rate": 2.5606601717798212e-05,
"loss": 0.41,
"step": 270
},
{
"epoch": 1.4718498659517425,
"grad_norm": 1.0004347562789917,
"learning_rate": 2.541733036547876e-05,
"loss": 0.41,
"step": 275
},
{
"epoch": 1.4986595174262733,
"grad_norm": 1.2617030143737793,
"learning_rate": 2.5224799453492993e-05,
"loss": 0.4061,
"step": 280
},
{
"epoch": 1.5254691689008042,
"grad_norm": 1.0547535419464111,
"learning_rate": 2.5029069224338105e-05,
"loss": 0.4104,
"step": 285
},
{
"epoch": 1.552278820375335,
"grad_norm": 1.1151704788208008,
"learning_rate": 2.4830200921570557e-05,
"loss": 0.4109,
"step": 290
},
{
"epoch": 1.579088471849866,
"grad_norm": 1.1136678457260132,
"learning_rate": 2.4628256770643114e-05,
"loss": 0.4338,
"step": 295
},
{
"epoch": 1.6058981233243967,
"grad_norm": 1.028518795967102,
"learning_rate": 2.4423299959434637e-05,
"loss": 0.353,
"step": 300
},
{
"epoch": 1.6327077747989276,
"grad_norm": 1.1373231410980225,
"learning_rate": 2.421539461847874e-05,
"loss": 0.3443,
"step": 305
},
{
"epoch": 1.6595174262734584,
"grad_norm": 0.9851738810539246,
"learning_rate": 2.4004605800897486e-05,
"loss": 0.3587,
"step": 310
},
{
"epoch": 1.6863270777479893,
"grad_norm": 1.0971182584762573,
"learning_rate": 2.3790999462046397e-05,
"loss": 0.3598,
"step": 315
},
{
"epoch": 1.7131367292225201,
"grad_norm": 1.130505919456482,
"learning_rate": 2.3574642438877183e-05,
"loss": 0.3877,
"step": 320
},
{
"epoch": 1.739946380697051,
"grad_norm": 1.1338894367218018,
"learning_rate": 2.3355602429024606e-05,
"loss": 0.3538,
"step": 325
},
{
"epoch": 1.7667560321715818,
"grad_norm": 1.183328628540039,
"learning_rate": 2.313394796962403e-05,
"loss": 0.3291,
"step": 330
},
{
"epoch": 1.7935656836461127,
"grad_norm": 1.1300513744354248,
"learning_rate": 2.2909748415866312e-05,
"loss": 0.3378,
"step": 335
},
{
"epoch": 1.8203753351206435,
"grad_norm": 1.3838099241256714,
"learning_rate": 2.2683073919296715e-05,
"loss": 0.3279,
"step": 340
},
{
"epoch": 1.8471849865951744,
"grad_norm": 1.07172429561615,
"learning_rate": 2.245399540586464e-05,
"loss": 0.3473,
"step": 345
},
{
"epoch": 1.8739946380697052,
"grad_norm": 1.7059202194213867,
"learning_rate": 2.2222584553731058e-05,
"loss": 0.3221,
"step": 350
},
{
"epoch": 1.900804289544236,
"grad_norm": 1.2840522527694702,
"learning_rate": 2.1988913770840563e-05,
"loss": 0.348,
"step": 355
},
{
"epoch": 1.9276139410187667,
"grad_norm": 1.2816296815872192,
"learning_rate": 2.17530561722651e-05,
"loss": 0.3025,
"step": 360
},
{
"epoch": 1.9544235924932976,
"grad_norm": 1.3507882356643677,
"learning_rate": 2.1515085557326404e-05,
"loss": 0.2958,
"step": 365
},
{
"epoch": 1.9812332439678284,
"grad_norm": 1.867775559425354,
"learning_rate": 2.127507638650437e-05,
"loss": 0.3157,
"step": 370
}
],
"logging_steps": 5,
"max_steps": 935,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 2000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 5.810805485128909e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}