prxy5606's picture
Training in progress, step 50, checkpoint
0bb750d verified
raw
history blame
9.86 kB
{
"best_metric": 0.4161189794540405,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.8733624454148472,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017467248908296942,
"grad_norm": 1.0100444555282593,
"learning_rate": 1e-05,
"loss": 0.7291,
"step": 1
},
{
"epoch": 0.017467248908296942,
"eval_loss": 1.4666682481765747,
"eval_runtime": 2.8998,
"eval_samples_per_second": 33.451,
"eval_steps_per_second": 8.621,
"step": 1
},
{
"epoch": 0.034934497816593885,
"grad_norm": 1.6248141527175903,
"learning_rate": 2e-05,
"loss": 0.9125,
"step": 2
},
{
"epoch": 0.05240174672489083,
"grad_norm": 1.6520636081695557,
"learning_rate": 3e-05,
"loss": 1.0164,
"step": 3
},
{
"epoch": 0.06986899563318777,
"grad_norm": 1.8291550874710083,
"learning_rate": 4e-05,
"loss": 1.1878,
"step": 4
},
{
"epoch": 0.08733624454148471,
"grad_norm": 1.8957704305648804,
"learning_rate": 5e-05,
"loss": 1.0702,
"step": 5
},
{
"epoch": 0.10480349344978165,
"grad_norm": 1.6647785902023315,
"learning_rate": 6e-05,
"loss": 1.1481,
"step": 6
},
{
"epoch": 0.1222707423580786,
"grad_norm": 1.678140640258789,
"learning_rate": 7e-05,
"loss": 0.9731,
"step": 7
},
{
"epoch": 0.13973799126637554,
"grad_norm": 1.7518115043640137,
"learning_rate": 8e-05,
"loss": 1.1692,
"step": 8
},
{
"epoch": 0.1572052401746725,
"grad_norm": 1.968929648399353,
"learning_rate": 9e-05,
"loss": 1.0349,
"step": 9
},
{
"epoch": 0.17467248908296942,
"grad_norm": 1.2481895685195923,
"learning_rate": 0.0001,
"loss": 0.8936,
"step": 10
},
{
"epoch": 0.19213973799126638,
"grad_norm": 2.483721971511841,
"learning_rate": 9.999059852242507e-05,
"loss": 0.9547,
"step": 11
},
{
"epoch": 0.2096069868995633,
"grad_norm": 1.7359554767608643,
"learning_rate": 9.996239762521151e-05,
"loss": 1.1258,
"step": 12
},
{
"epoch": 0.22707423580786026,
"grad_norm": 2.3270020484924316,
"learning_rate": 9.991540791356342e-05,
"loss": 1.1838,
"step": 13
},
{
"epoch": 0.2445414847161572,
"grad_norm": 2.784715175628662,
"learning_rate": 9.98496470583896e-05,
"loss": 1.1575,
"step": 14
},
{
"epoch": 0.26200873362445415,
"grad_norm": 0.8565568923950195,
"learning_rate": 9.976513978965829e-05,
"loss": 0.6597,
"step": 15
},
{
"epoch": 0.2794759825327511,
"grad_norm": 1.0250848531723022,
"learning_rate": 9.966191788709716e-05,
"loss": 0.6515,
"step": 16
},
{
"epoch": 0.29694323144104806,
"grad_norm": 0.8767344355583191,
"learning_rate": 9.954002016824227e-05,
"loss": 0.738,
"step": 17
},
{
"epoch": 0.314410480349345,
"grad_norm": 1.0085071325302124,
"learning_rate": 9.939949247384046e-05,
"loss": 0.6975,
"step": 18
},
{
"epoch": 0.3318777292576419,
"grad_norm": 0.8842006325721741,
"learning_rate": 9.924038765061042e-05,
"loss": 0.7691,
"step": 19
},
{
"epoch": 0.34934497816593885,
"grad_norm": 0.9122969508171082,
"learning_rate": 9.906276553136923e-05,
"loss": 0.7258,
"step": 20
},
{
"epoch": 0.36681222707423583,
"grad_norm": 1.0844351053237915,
"learning_rate": 9.88666929125318e-05,
"loss": 0.7773,
"step": 21
},
{
"epoch": 0.38427947598253276,
"grad_norm": 1.1110165119171143,
"learning_rate": 9.865224352899119e-05,
"loss": 0.7144,
"step": 22
},
{
"epoch": 0.4017467248908297,
"grad_norm": 1.1816184520721436,
"learning_rate": 9.84194980263903e-05,
"loss": 0.785,
"step": 23
},
{
"epoch": 0.4192139737991266,
"grad_norm": 1.3115167617797852,
"learning_rate": 9.816854393079403e-05,
"loss": 0.8229,
"step": 24
},
{
"epoch": 0.4366812227074236,
"grad_norm": 1.1766431331634521,
"learning_rate": 9.789947561577445e-05,
"loss": 0.7382,
"step": 25
},
{
"epoch": 0.45414847161572053,
"grad_norm": 1.5775043964385986,
"learning_rate": 9.761239426692077e-05,
"loss": 0.8968,
"step": 26
},
{
"epoch": 0.47161572052401746,
"grad_norm": 1.766829490661621,
"learning_rate": 9.730740784378753e-05,
"loss": 0.863,
"step": 27
},
{
"epoch": 0.4890829694323144,
"grad_norm": 2.7797858715057373,
"learning_rate": 9.698463103929542e-05,
"loss": 0.899,
"step": 28
},
{
"epoch": 0.5065502183406113,
"grad_norm": 0.5734480023384094,
"learning_rate": 9.664418523660004e-05,
"loss": 0.5252,
"step": 29
},
{
"epoch": 0.5240174672489083,
"grad_norm": 0.7527353763580322,
"learning_rate": 9.628619846344454e-05,
"loss": 0.5005,
"step": 30
},
{
"epoch": 0.5414847161572053,
"grad_norm": 0.9429885149002075,
"learning_rate": 9.591080534401371e-05,
"loss": 0.6192,
"step": 31
},
{
"epoch": 0.5589519650655022,
"grad_norm": 0.797751247882843,
"learning_rate": 9.551814704830734e-05,
"loss": 0.6492,
"step": 32
},
{
"epoch": 0.5764192139737991,
"grad_norm": 0.7790107131004333,
"learning_rate": 9.51083712390519e-05,
"loss": 0.5706,
"step": 33
},
{
"epoch": 0.5938864628820961,
"grad_norm": 0.8417590856552124,
"learning_rate": 9.468163201617062e-05,
"loss": 0.5481,
"step": 34
},
{
"epoch": 0.611353711790393,
"grad_norm": 0.9345868229866028,
"learning_rate": 9.423808985883289e-05,
"loss": 0.626,
"step": 35
},
{
"epoch": 0.62882096069869,
"grad_norm": 1.1942213773727417,
"learning_rate": 9.377791156510455e-05,
"loss": 0.6025,
"step": 36
},
{
"epoch": 0.6462882096069869,
"grad_norm": 0.9529750943183899,
"learning_rate": 9.330127018922194e-05,
"loss": 0.5216,
"step": 37
},
{
"epoch": 0.6637554585152838,
"grad_norm": 1.2015634775161743,
"learning_rate": 9.280834497651334e-05,
"loss": 0.6232,
"step": 38
},
{
"epoch": 0.6812227074235808,
"grad_norm": 1.266699194908142,
"learning_rate": 9.229932129599205e-05,
"loss": 0.6139,
"step": 39
},
{
"epoch": 0.6986899563318777,
"grad_norm": 1.4141474962234497,
"learning_rate": 9.177439057064683e-05,
"loss": 0.7265,
"step": 40
},
{
"epoch": 0.7161572052401747,
"grad_norm": 1.8044284582138062,
"learning_rate": 9.123375020545535e-05,
"loss": 0.6337,
"step": 41
},
{
"epoch": 0.7336244541484717,
"grad_norm": 1.9032659530639648,
"learning_rate": 9.067760351314838e-05,
"loss": 0.8511,
"step": 42
},
{
"epoch": 0.7510917030567685,
"grad_norm": 0.765811026096344,
"learning_rate": 9.01061596377522e-05,
"loss": 0.444,
"step": 43
},
{
"epoch": 0.7685589519650655,
"grad_norm": 0.8824454545974731,
"learning_rate": 8.951963347593797e-05,
"loss": 0.4689,
"step": 44
},
{
"epoch": 0.7860262008733624,
"grad_norm": 0.7503276467323303,
"learning_rate": 8.891824559620801e-05,
"loss": 0.426,
"step": 45
},
{
"epoch": 0.8034934497816594,
"grad_norm": 1.1007099151611328,
"learning_rate": 8.83022221559489e-05,
"loss": 0.5502,
"step": 46
},
{
"epoch": 0.8209606986899564,
"grad_norm": 0.8477142453193665,
"learning_rate": 8.767179481638303e-05,
"loss": 0.451,
"step": 47
},
{
"epoch": 0.8384279475982532,
"grad_norm": 0.9551414847373962,
"learning_rate": 8.702720065545024e-05,
"loss": 0.3994,
"step": 48
},
{
"epoch": 0.8558951965065502,
"grad_norm": 1.0447505712509155,
"learning_rate": 8.636868207865244e-05,
"loss": 0.4649,
"step": 49
},
{
"epoch": 0.8733624454148472,
"grad_norm": 1.1280784606933594,
"learning_rate": 8.569648672789497e-05,
"loss": 0.395,
"step": 50
},
{
"epoch": 0.8733624454148472,
"eval_loss": 0.4161189794540405,
"eval_runtime": 2.9162,
"eval_samples_per_second": 33.263,
"eval_steps_per_second": 8.573,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 172,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 1.381134508228608e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}