Muedi's picture
Training in progress, step 6000, checkpoint
8ca6604 verified
raw
history blame
11.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.019543782959775637,
"eval_steps": 500,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003257297159962606,
"grad_norm": 2.2308592796325684,
"learning_rate": 4.99853416853153e-05,
"loss": 1.4483,
"step": 100
},
{
"epoch": 0.0006514594319925212,
"grad_norm": 2.3997225761413574,
"learning_rate": 4.996905466899897e-05,
"loss": 1.3276,
"step": 200
},
{
"epoch": 0.0009771891479887819,
"grad_norm": 1.4687339067459106,
"learning_rate": 4.995276765268264e-05,
"loss": 1.3394,
"step": 300
},
{
"epoch": 0.0013029188639850425,
"grad_norm": 0.6583470702171326,
"learning_rate": 4.993648063636631e-05,
"loss": 1.3245,
"step": 400
},
{
"epoch": 0.0016286485799813031,
"grad_norm": 1.6252340078353882,
"learning_rate": 4.992019362004997e-05,
"loss": 1.3249,
"step": 500
},
{
"epoch": 0.0019543782959775637,
"grad_norm": 2.0806777477264404,
"learning_rate": 4.9903906603733634e-05,
"loss": 1.32,
"step": 600
},
{
"epoch": 0.002280108011973824,
"grad_norm": 1.376539707183838,
"learning_rate": 4.988761958741731e-05,
"loss": 1.3133,
"step": 700
},
{
"epoch": 0.002605837727970085,
"grad_norm": 2.234644889831543,
"learning_rate": 4.987133257110097e-05,
"loss": 1.3179,
"step": 800
},
{
"epoch": 0.0029315674439663454,
"grad_norm": 1.4599684476852417,
"learning_rate": 4.985504555478464e-05,
"loss": 1.3097,
"step": 900
},
{
"epoch": 0.0032572971599626062,
"grad_norm": 1.7078094482421875,
"learning_rate": 4.9838758538468304e-05,
"loss": 1.3083,
"step": 1000
},
{
"epoch": 0.0035830268759588666,
"grad_norm": 0.6953567266464233,
"learning_rate": 4.9822471522151976e-05,
"loss": 1.3075,
"step": 1100
},
{
"epoch": 0.0039087565919551275,
"grad_norm": 1.225602626800537,
"learning_rate": 4.980618450583564e-05,
"loss": 1.3054,
"step": 1200
},
{
"epoch": 0.004234486307951388,
"grad_norm": 1.3010519742965698,
"learning_rate": 4.978989748951931e-05,
"loss": 1.3066,
"step": 1300
},
{
"epoch": 0.004560216023947648,
"grad_norm": 0.6475724577903748,
"learning_rate": 4.9773610473202974e-05,
"loss": 1.3109,
"step": 1400
},
{
"epoch": 0.004885945739943909,
"grad_norm": 1.046614646911621,
"learning_rate": 4.975732345688664e-05,
"loss": 1.3074,
"step": 1500
},
{
"epoch": 0.00521167545594017,
"grad_norm": 1.113573670387268,
"learning_rate": 4.974103644057031e-05,
"loss": 1.3083,
"step": 1600
},
{
"epoch": 0.005537405171936431,
"grad_norm": 1.4273550510406494,
"learning_rate": 4.972474942425398e-05,
"loss": 1.3018,
"step": 1700
},
{
"epoch": 0.005863134887932691,
"grad_norm": 0.5519908666610718,
"learning_rate": 4.970846240793764e-05,
"loss": 1.2945,
"step": 1800
},
{
"epoch": 0.006188864603928952,
"grad_norm": 0.6653416156768799,
"learning_rate": 4.969217539162131e-05,
"loss": 1.3004,
"step": 1900
},
{
"epoch": 0.0065145943199252125,
"grad_norm": 0.732170581817627,
"learning_rate": 4.9675888375304975e-05,
"loss": 1.3014,
"step": 2000
},
{
"epoch": 0.006840324035921473,
"grad_norm": 0.405608594417572,
"learning_rate": 4.965960135898865e-05,
"loss": 1.2939,
"step": 2100
},
{
"epoch": 0.007166053751917733,
"grad_norm": 0.9849847555160522,
"learning_rate": 4.9643314342672306e-05,
"loss": 1.2922,
"step": 2200
},
{
"epoch": 0.007491783467913994,
"grad_norm": 0.7152832746505737,
"learning_rate": 4.962702732635598e-05,
"loss": 1.2905,
"step": 2300
},
{
"epoch": 0.007817513183910255,
"grad_norm": 1.1164734363555908,
"learning_rate": 4.9610740310039644e-05,
"loss": 1.3024,
"step": 2400
},
{
"epoch": 0.008143242899906516,
"grad_norm": 0.574243426322937,
"learning_rate": 4.959445329372332e-05,
"loss": 1.2944,
"step": 2500
},
{
"epoch": 0.008468972615902777,
"grad_norm": 0.6976324319839478,
"learning_rate": 4.9578166277406976e-05,
"loss": 1.2939,
"step": 2600
},
{
"epoch": 0.008794702331899037,
"grad_norm": 0.4648737609386444,
"learning_rate": 4.956187926109064e-05,
"loss": 1.2841,
"step": 2700
},
{
"epoch": 0.009120432047895297,
"grad_norm": 1.189271092414856,
"learning_rate": 4.9545592244774314e-05,
"loss": 1.294,
"step": 2800
},
{
"epoch": 0.009446161763891557,
"grad_norm": 0.6437670588493347,
"learning_rate": 4.952930522845798e-05,
"loss": 1.2882,
"step": 2900
},
{
"epoch": 0.009771891479887818,
"grad_norm": 1.591304898262024,
"learning_rate": 4.9513018212141646e-05,
"loss": 1.2805,
"step": 3000
},
{
"epoch": 0.010097621195884079,
"grad_norm": 0.2836475670337677,
"learning_rate": 4.949673119582531e-05,
"loss": 1.2802,
"step": 3100
},
{
"epoch": 0.01042335091188034,
"grad_norm": 1.304417610168457,
"learning_rate": 4.9480444179508984e-05,
"loss": 1.2833,
"step": 3200
},
{
"epoch": 0.0107490806278766,
"grad_norm": 0.27579864859580994,
"learning_rate": 4.946415716319265e-05,
"loss": 1.2852,
"step": 3300
},
{
"epoch": 0.011074810343872862,
"grad_norm": 1.1080585718154907,
"learning_rate": 4.9447870146876315e-05,
"loss": 1.289,
"step": 3400
},
{
"epoch": 0.011400540059869122,
"grad_norm": 0.2783690392971039,
"learning_rate": 4.943158313055998e-05,
"loss": 1.2885,
"step": 3500
},
{
"epoch": 0.011726269775865382,
"grad_norm": 0.6603112816810608,
"learning_rate": 4.941529611424365e-05,
"loss": 1.2882,
"step": 3600
},
{
"epoch": 0.012051999491861642,
"grad_norm": 0.9498095512390137,
"learning_rate": 4.939900909792732e-05,
"loss": 1.2835,
"step": 3700
},
{
"epoch": 0.012377729207857903,
"grad_norm": 0.5274548530578613,
"learning_rate": 4.9382722081610985e-05,
"loss": 1.279,
"step": 3800
},
{
"epoch": 0.012703458923854164,
"grad_norm": 0.5299821496009827,
"learning_rate": 4.936643506529465e-05,
"loss": 1.2879,
"step": 3900
},
{
"epoch": 0.013029188639850425,
"grad_norm": 1.0898863077163696,
"learning_rate": 4.9350148048978316e-05,
"loss": 1.2913,
"step": 4000
},
{
"epoch": 0.013354918355846686,
"grad_norm": 0.6892501711845398,
"learning_rate": 4.933386103266198e-05,
"loss": 1.2835,
"step": 4100
},
{
"epoch": 0.013680648071842947,
"grad_norm": 0.9103847146034241,
"learning_rate": 4.9317574016345655e-05,
"loss": 1.2876,
"step": 4200
},
{
"epoch": 0.014006377787839207,
"grad_norm": 0.8750960826873779,
"learning_rate": 4.9301287000029314e-05,
"loss": 1.2761,
"step": 4300
},
{
"epoch": 0.014332107503835467,
"grad_norm": 1.7296843528747559,
"learning_rate": 4.9284999983712986e-05,
"loss": 1.2825,
"step": 4400
},
{
"epoch": 0.014657837219831727,
"grad_norm": 0.7019387483596802,
"learning_rate": 4.926871296739665e-05,
"loss": 1.2774,
"step": 4500
},
{
"epoch": 0.014983566935827988,
"grad_norm": 0.9353660345077515,
"learning_rate": 4.9252425951080324e-05,
"loss": 1.2701,
"step": 4600
},
{
"epoch": 0.015309296651824249,
"grad_norm": 0.7081932425498962,
"learning_rate": 4.923613893476399e-05,
"loss": 1.276,
"step": 4700
},
{
"epoch": 0.01563502636782051,
"grad_norm": 0.8366962671279907,
"learning_rate": 4.9219851918447656e-05,
"loss": 1.2767,
"step": 4800
},
{
"epoch": 0.01596075608381677,
"grad_norm": 1.765871286392212,
"learning_rate": 4.920356490213132e-05,
"loss": 1.2617,
"step": 4900
},
{
"epoch": 0.01628648579981303,
"grad_norm": 0.2926379442214966,
"learning_rate": 4.918727788581499e-05,
"loss": 1.2762,
"step": 5000
},
{
"epoch": 0.01661221551580929,
"grad_norm": 1.1176525354385376,
"learning_rate": 4.917099086949866e-05,
"loss": 1.2647,
"step": 5100
},
{
"epoch": 0.016937945231805553,
"grad_norm": 0.384264200925827,
"learning_rate": 4.915470385318232e-05,
"loss": 1.2628,
"step": 5200
},
{
"epoch": 0.017263674947801812,
"grad_norm": 1.5339140892028809,
"learning_rate": 4.913841683686599e-05,
"loss": 1.2692,
"step": 5300
},
{
"epoch": 0.017589404663798075,
"grad_norm": 1.2026703357696533,
"learning_rate": 4.912212982054966e-05,
"loss": 1.2618,
"step": 5400
},
{
"epoch": 0.017915134379794334,
"grad_norm": 0.6754997968673706,
"learning_rate": 4.910584280423333e-05,
"loss": 1.2495,
"step": 5500
},
{
"epoch": 0.018240864095790593,
"grad_norm": 0.8240428566932678,
"learning_rate": 4.908955578791699e-05,
"loss": 1.2498,
"step": 5600
},
{
"epoch": 0.018566593811786856,
"grad_norm": 0.6363087892532349,
"learning_rate": 4.9073268771600654e-05,
"loss": 1.2514,
"step": 5700
},
{
"epoch": 0.018892323527783115,
"grad_norm": 1.393833875656128,
"learning_rate": 4.905698175528433e-05,
"loss": 1.2509,
"step": 5800
},
{
"epoch": 0.019218053243779377,
"grad_norm": 0.6422170996665955,
"learning_rate": 4.904069473896799e-05,
"loss": 1.2405,
"step": 5900
},
{
"epoch": 0.019543782959775637,
"grad_norm": 0.7575420141220093,
"learning_rate": 4.902440772265166e-05,
"loss": 1.2241,
"step": 6000
}
],
"logging_steps": 100,
"max_steps": 307003,
"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": false
},
"attributes": {}
}
},
"total_flos": 8.9157682593792e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}