16-clusters-balanced-9 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-9
304d9f3 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3878,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.025786487880350695,
"grad_norm": 0.1338733434677124,
"learning_rate": 6.666666666666667e-06,
"loss": 2.5125,
"step": 100
},
{
"epoch": 0.05157297576070139,
"grad_norm": 0.17936278879642487,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4886,
"step": 200
},
{
"epoch": 0.07735946364105209,
"grad_norm": 0.2758166491985321,
"learning_rate": 2e-05,
"loss": 2.4178,
"step": 300
},
{
"epoch": 0.10314595152140278,
"grad_norm": 0.38494062423706055,
"learning_rate": 1.9961477891705203e-05,
"loss": 2.4016,
"step": 400
},
{
"epoch": 0.12893243940175347,
"grad_norm": 0.408550888299942,
"learning_rate": 1.98462083573863e-05,
"loss": 2.3598,
"step": 500
},
{
"epoch": 0.15471892728210418,
"grad_norm": 0.43653976917266846,
"learning_rate": 1.9655079482140115e-05,
"loss": 2.3474,
"step": 600
},
{
"epoch": 0.18050541516245489,
"grad_norm": 0.5025712251663208,
"learning_rate": 1.9389563803412753e-05,
"loss": 2.3225,
"step": 700
},
{
"epoch": 0.20629190304280556,
"grad_norm": 0.565731406211853,
"learning_rate": 1.9051706965950192e-05,
"loss": 2.2821,
"step": 800
},
{
"epoch": 0.23207839092315627,
"grad_norm": 0.5192058682441711,
"learning_rate": 1.8644111961288605e-05,
"loss": 2.3188,
"step": 900
},
{
"epoch": 0.25786487880350695,
"grad_norm": 0.8693593740463257,
"learning_rate": 1.816991907320999e-05,
"loss": 2.2895,
"step": 1000
},
{
"epoch": 0.28365136668385765,
"grad_norm": 0.6395590901374817,
"learning_rate": 1.7632781683671787e-05,
"loss": 2.2892,
"step": 1100
},
{
"epoch": 0.30943785456420836,
"grad_norm": 0.7124245166778564,
"learning_rate": 1.703683812561179e-05,
"loss": 2.2695,
"step": 1200
},
{
"epoch": 0.33522434244455906,
"grad_norm": 0.6226526498794556,
"learning_rate": 1.6386679799486236e-05,
"loss": 2.2573,
"step": 1300
},
{
"epoch": 0.36101083032490977,
"grad_norm": 0.7176969051361084,
"learning_rate": 1.568731579918468e-05,
"loss": 2.2483,
"step": 1400
},
{
"epoch": 0.3867973182052604,
"grad_norm": 0.6624855399131775,
"learning_rate": 1.494413431985854e-05,
"loss": 2.2084,
"step": 1500
},
{
"epoch": 0.4125838060856111,
"grad_norm": 0.669903039932251,
"learning_rate": 1.4162861144993671e-05,
"loss": 2.2376,
"step": 1600
},
{
"epoch": 0.43837029396596183,
"grad_norm": 0.7109538316726685,
"learning_rate": 1.3349515532560074e-05,
"loss": 2.2318,
"step": 1700
},
{
"epoch": 0.46415678184631254,
"grad_norm": 0.7055323123931885,
"learning_rate": 1.2510363840110396e-05,
"loss": 2.2585,
"step": 1800
},
{
"epoch": 0.48994326972666324,
"grad_norm": 0.8980267643928528,
"learning_rate": 1.1651871246119102e-05,
"loss": 2.2008,
"step": 1900
},
{
"epoch": 0.5157297576070139,
"grad_norm": 0.774202287197113,
"learning_rate": 1.0780651939521396e-05,
"loss": 2.2063,
"step": 2000
},
{
"epoch": 0.5415162454873647,
"grad_norm": 0.9350955486297607,
"learning_rate": 9.903418161212732e-06,
"loss": 2.2451,
"step": 2100
},
{
"epoch": 0.5673027333677153,
"grad_norm": 0.9068596959114075,
"learning_rate": 9.026928490114683e-06,
"loss": 2.2293,
"step": 2200
},
{
"epoch": 0.5930892212480661,
"grad_norm": 0.7404003739356995,
"learning_rate": 8.15793577223311e-06,
"loss": 2.2155,
"step": 2300
},
{
"epoch": 0.6188757091284167,
"grad_norm": 0.8607114553451538,
"learning_rate": 7.303135093885141e-06,
"loss": 2.2158,
"step": 2400
},
{
"epoch": 0.6446621970087674,
"grad_norm": 0.7401602864265442,
"learning_rate": 6.469112199931131e-06,
"loss": 2.1806,
"step": 2500
},
{
"epoch": 0.6704486848891181,
"grad_norm": 0.818596363067627,
"learning_rate": 5.662292754419332e-06,
"loss": 2.1965,
"step": 2600
},
{
"epoch": 0.6962351727694688,
"grad_norm": 0.9028757810592651,
"learning_rate": 4.888892834560608e-06,
"loss": 2.2402,
"step": 2700
},
{
"epoch": 0.7220216606498195,
"grad_norm": 0.8473127484321594,
"learning_rate": 4.154871039448561e-06,
"loss": 2.2167,
"step": 2800
},
{
"epoch": 0.7478081485301702,
"grad_norm": 0.7806875705718994,
"learning_rate": 3.4658825824996036e-06,
"loss": 2.2116,
"step": 2900
},
{
"epoch": 0.7735946364105208,
"grad_norm": 0.7143692970275879,
"learning_rate": 2.82723572130422e-06,
"loss": 2.2068,
"step": 3000
},
{
"epoch": 0.7993811242908716,
"grad_norm": 0.8515029549598694,
"learning_rate": 2.243850860572239e-06,
"loss": 2.1972,
"step": 3100
},
{
"epoch": 0.8251676121712223,
"grad_norm": 0.770374596118927,
"learning_rate": 1.7202226432601833e-06,
"loss": 2.2316,
"step": 3200
},
{
"epoch": 0.850954100051573,
"grad_norm": 0.7793726325035095,
"learning_rate": 1.260385321946761e-06,
"loss": 2.2046,
"step": 3300
},
{
"epoch": 0.8767405879319237,
"grad_norm": 1.0234565734863281,
"learning_rate": 8.678816772498988e-07,
"loss": 2.1848,
"step": 3400
},
{
"epoch": 0.9025270758122743,
"grad_norm": 0.8092569708824158,
"learning_rate": 5.457357227510152e-07,
"loss": 2.2268,
"step": 3500
},
{
"epoch": 0.9283135636926251,
"grad_norm": 0.9072908759117126,
"learning_rate": 2.964294067193008e-07,
"loss": 2.2251,
"step": 3600
},
{
"epoch": 0.9541000515729757,
"grad_norm": 0.6942015886306763,
"learning_rate": 1.2188349013570356e-07,
"loss": 2.2285,
"step": 3700
},
{
"epoch": 0.9798865394533265,
"grad_norm": 0.8001830577850342,
"learning_rate": 2.344274834043425e-08,
"loss": 2.2278,
"step": 3800
},
{
"epoch": 1.0,
"step": 3878,
"total_flos": 7.04757648064512e+16,
"train_loss": 2.263120666000264,
"train_runtime": 1207.6216,
"train_samples_per_second": 6.423,
"train_steps_per_second": 3.211
}
],
"logging_steps": 100,
"max_steps": 3878,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7.04757648064512e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}