bbytxt's picture
Training in progress, step 50, checkpoint
8618ac6 verified
raw
history blame
10.1 kB
{
"best_metric": 1.986087441444397,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.008158936074735855,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001631787214947171,
"grad_norm": 0.9626743197441101,
"learning_rate": 5.000000000000001e-07,
"loss": 2.3231,
"step": 1
},
{
"epoch": 0.0001631787214947171,
"eval_loss": 2.1344542503356934,
"eval_runtime": 976.0493,
"eval_samples_per_second": 10.575,
"eval_steps_per_second": 2.644,
"step": 1
},
{
"epoch": 0.0003263574429894342,
"grad_norm": 0.8612233996391296,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.1608,
"step": 2
},
{
"epoch": 0.0004895361644841513,
"grad_norm": 0.9304367899894714,
"learning_rate": 1.5e-06,
"loss": 2.2746,
"step": 3
},
{
"epoch": 0.0006527148859788684,
"grad_norm": 0.8620933294296265,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.1838,
"step": 4
},
{
"epoch": 0.0008158936074735855,
"grad_norm": 0.8950667977333069,
"learning_rate": 2.5e-06,
"loss": 2.1265,
"step": 5
},
{
"epoch": 0.0009790723289683026,
"grad_norm": 0.8841383457183838,
"learning_rate": 3e-06,
"loss": 2.2276,
"step": 6
},
{
"epoch": 0.0011422510504630196,
"grad_norm": 0.8289633989334106,
"learning_rate": 3.5e-06,
"loss": 2.2067,
"step": 7
},
{
"epoch": 0.0013054297719577368,
"grad_norm": 0.8701562881469727,
"learning_rate": 4.000000000000001e-06,
"loss": 2.1737,
"step": 8
},
{
"epoch": 0.0014686084934524537,
"grad_norm": 0.836694598197937,
"learning_rate": 4.5e-06,
"loss": 2.1575,
"step": 9
},
{
"epoch": 0.001631787214947171,
"grad_norm": 0.8217163681983948,
"learning_rate": 5e-06,
"loss": 2.1041,
"step": 10
},
{
"epoch": 0.001794965936441888,
"grad_norm": 0.8088410496711731,
"learning_rate": 4.99847706754774e-06,
"loss": 2.1987,
"step": 11
},
{
"epoch": 0.001958144657936605,
"grad_norm": 0.8314682245254517,
"learning_rate": 4.993910125649561e-06,
"loss": 2.0736,
"step": 12
},
{
"epoch": 0.0021213233794313223,
"grad_norm": 0.8567140698432922,
"learning_rate": 4.986304738420684e-06,
"loss": 2.1567,
"step": 13
},
{
"epoch": 0.002284502100926039,
"grad_norm": 0.8521527051925659,
"learning_rate": 4.975670171853926e-06,
"loss": 2.0756,
"step": 14
},
{
"epoch": 0.0024476808224207563,
"grad_norm": 0.890558123588562,
"learning_rate": 4.962019382530521e-06,
"loss": 2.0736,
"step": 15
},
{
"epoch": 0.0026108595439154735,
"grad_norm": 0.8253862857818604,
"learning_rate": 4.9453690018345144e-06,
"loss": 2.0023,
"step": 16
},
{
"epoch": 0.0027740382654101907,
"grad_norm": 0.8322637677192688,
"learning_rate": 4.925739315689991e-06,
"loss": 2.0468,
"step": 17
},
{
"epoch": 0.0029372169869049075,
"grad_norm": 0.8288842439651489,
"learning_rate": 4.903154239845798e-06,
"loss": 1.9811,
"step": 18
},
{
"epoch": 0.0031003957083996247,
"grad_norm": 0.9009273648262024,
"learning_rate": 4.8776412907378845e-06,
"loss": 2.1364,
"step": 19
},
{
"epoch": 0.003263574429894342,
"grad_norm": 0.8775635957717896,
"learning_rate": 4.849231551964771e-06,
"loss": 2.0339,
"step": 20
},
{
"epoch": 0.0034267531513890587,
"grad_norm": 0.9163408279418945,
"learning_rate": 4.817959636416969e-06,
"loss": 2.0333,
"step": 21
},
{
"epoch": 0.003589931872883776,
"grad_norm": 0.9037641286849976,
"learning_rate": 4.783863644106502e-06,
"loss": 2.0447,
"step": 22
},
{
"epoch": 0.003753110594378493,
"grad_norm": 0.9167019724845886,
"learning_rate": 4.746985115747918e-06,
"loss": 1.9999,
"step": 23
},
{
"epoch": 0.00391628931587321,
"grad_norm": 0.8852622509002686,
"learning_rate": 4.707368982147318e-06,
"loss": 2.0036,
"step": 24
},
{
"epoch": 0.0040794680373679275,
"grad_norm": 0.890647292137146,
"learning_rate": 4.665063509461098e-06,
"loss": 2.0591,
"step": 25
},
{
"epoch": 0.004242646758862645,
"grad_norm": 0.8380885124206543,
"learning_rate": 4.620120240391065e-06,
"loss": 2.0312,
"step": 26
},
{
"epoch": 0.004405825480357361,
"grad_norm": 0.9328538179397583,
"learning_rate": 4.572593931387604e-06,
"loss": 2.0167,
"step": 27
},
{
"epoch": 0.004569004201852078,
"grad_norm": 0.8684221506118774,
"learning_rate": 4.522542485937369e-06,
"loss": 2.0018,
"step": 28
},
{
"epoch": 0.004732182923346795,
"grad_norm": 0.9270681738853455,
"learning_rate": 4.470026884016805e-06,
"loss": 2.0179,
"step": 29
},
{
"epoch": 0.004895361644841513,
"grad_norm": 0.9681967496871948,
"learning_rate": 4.415111107797445e-06,
"loss": 2.1236,
"step": 30
},
{
"epoch": 0.00505854036633623,
"grad_norm": 0.9239471554756165,
"learning_rate": 4.357862063693486e-06,
"loss": 1.9945,
"step": 31
},
{
"epoch": 0.005221719087830947,
"grad_norm": 0.9569579362869263,
"learning_rate": 4.2983495008466285e-06,
"loss": 1.9907,
"step": 32
},
{
"epoch": 0.005384897809325664,
"grad_norm": 0.9254785776138306,
"learning_rate": 4.236645926147493e-06,
"loss": 2.0334,
"step": 33
},
{
"epoch": 0.0055480765308203814,
"grad_norm": 0.8775327205657959,
"learning_rate": 4.172826515897146e-06,
"loss": 2.049,
"step": 34
},
{
"epoch": 0.005711255252315098,
"grad_norm": 0.9445580840110779,
"learning_rate": 4.106969024216348e-06,
"loss": 1.9781,
"step": 35
},
{
"epoch": 0.005874433973809815,
"grad_norm": 0.8967560529708862,
"learning_rate": 4.039153688314146e-06,
"loss": 2.017,
"step": 36
},
{
"epoch": 0.006037612695304532,
"grad_norm": 0.9454420208930969,
"learning_rate": 3.969463130731183e-06,
"loss": 1.9148,
"step": 37
},
{
"epoch": 0.006200791416799249,
"grad_norm": 1.0066184997558594,
"learning_rate": 3.897982258676867e-06,
"loss": 2.0719,
"step": 38
},
{
"epoch": 0.006363970138293967,
"grad_norm": 0.9081863164901733,
"learning_rate": 3.824798160583012e-06,
"loss": 1.9958,
"step": 39
},
{
"epoch": 0.006527148859788684,
"grad_norm": 0.9053497314453125,
"learning_rate": 3.7500000000000005e-06,
"loss": 2.0227,
"step": 40
},
{
"epoch": 0.006690327581283401,
"grad_norm": 0.9111195206642151,
"learning_rate": 3.6736789069647273e-06,
"loss": 1.9154,
"step": 41
},
{
"epoch": 0.006853506302778117,
"grad_norm": 0.8714330792427063,
"learning_rate": 3.595927866972694e-06,
"loss": 2.0181,
"step": 42
},
{
"epoch": 0.0070166850242728345,
"grad_norm": 0.9528706073760986,
"learning_rate": 3.516841607689501e-06,
"loss": 2.1378,
"step": 43
},
{
"epoch": 0.007179863745767552,
"grad_norm": 0.9247714877128601,
"learning_rate": 3.436516483539781e-06,
"loss": 2.0865,
"step": 44
},
{
"epoch": 0.007343042467262269,
"grad_norm": 1.0060503482818604,
"learning_rate": 3.3550503583141726e-06,
"loss": 2.1272,
"step": 45
},
{
"epoch": 0.007506221188756986,
"grad_norm": 1.0275453329086304,
"learning_rate": 3.272542485937369e-06,
"loss": 2.0768,
"step": 46
},
{
"epoch": 0.007669399910251703,
"grad_norm": 1.0227175951004028,
"learning_rate": 3.189093389542498e-06,
"loss": 2.1448,
"step": 47
},
{
"epoch": 0.00783257863174642,
"grad_norm": 1.136629343032837,
"learning_rate": 3.1048047389991693e-06,
"loss": 2.2079,
"step": 48
},
{
"epoch": 0.007995757353241137,
"grad_norm": 1.1337389945983887,
"learning_rate": 3.019779227044398e-06,
"loss": 2.1598,
"step": 49
},
{
"epoch": 0.008158936074735855,
"grad_norm": 1.3956023454666138,
"learning_rate": 2.9341204441673267e-06,
"loss": 2.1415,
"step": 50
},
{
"epoch": 0.008158936074735855,
"eval_loss": 1.986087441444397,
"eval_runtime": 980.5339,
"eval_samples_per_second": 10.527,
"eval_steps_per_second": 2.632,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.791364310191309e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}