pavitemple's picture
End of training
0dc0056
{
"best_metric": 0.6956521739130435,
"best_model_checkpoint": "finetuned-Accident-SingleLabel-Final-v3/checkpoint-60",
"epoch": 16.015384615384615,
"eval_steps": 500,
"global_step": 65,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"eval_accuracy": 0.17391304347826086,
"eval_loss": 1.8584030866622925,
"eval_runtime": 179.5451,
"eval_samples_per_second": 0.067,
"eval_steps_per_second": 0.006,
"step": 4
},
{
"epoch": 1.06,
"eval_accuracy": 0.34782608695652173,
"eval_loss": 1.65483558177948,
"eval_runtime": 175.4832,
"eval_samples_per_second": 0.068,
"eval_steps_per_second": 0.006,
"step": 8
},
{
"epoch": 2.03,
"learning_rate": 4.741379310344828e-05,
"loss": 1.6685,
"step": 10
},
{
"epoch": 2.06,
"eval_accuracy": 0.5217391304347826,
"eval_loss": 1.4048935174942017,
"eval_runtime": 176.3647,
"eval_samples_per_second": 0.068,
"eval_steps_per_second": 0.006,
"step": 12
},
{
"epoch": 3.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 1.1539908647537231,
"eval_runtime": 175.7427,
"eval_samples_per_second": 0.068,
"eval_steps_per_second": 0.006,
"step": 16
},
{
"epoch": 4.06,
"learning_rate": 3.8793103448275865e-05,
"loss": 1.0202,
"step": 20
},
{
"epoch": 4.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 1.1245999336242676,
"eval_runtime": 175.4478,
"eval_samples_per_second": 0.068,
"eval_steps_per_second": 0.006,
"step": 20
},
{
"epoch": 5.06,
"eval_accuracy": 0.43478260869565216,
"eval_loss": 1.0257611274719238,
"eval_runtime": 151.2816,
"eval_samples_per_second": 0.079,
"eval_steps_per_second": 0.007,
"step": 24
},
{
"epoch": 6.06,
"eval_accuracy": 0.5217391304347826,
"eval_loss": 0.9199802279472351,
"eval_runtime": 154.3945,
"eval_samples_per_second": 0.078,
"eval_steps_per_second": 0.006,
"step": 28
},
{
"epoch": 7.03,
"learning_rate": 3.017241379310345e-05,
"loss": 0.9738,
"step": 30
},
{
"epoch": 7.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 0.8941669464111328,
"eval_runtime": 151.3946,
"eval_samples_per_second": 0.079,
"eval_steps_per_second": 0.007,
"step": 32
},
{
"epoch": 8.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 0.8555505275726318,
"eval_runtime": 148.1025,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 36
},
{
"epoch": 9.06,
"learning_rate": 2.1551724137931033e-05,
"loss": 0.7315,
"step": 40
},
{
"epoch": 9.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 0.9505789279937744,
"eval_runtime": 148.2855,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 40
},
{
"epoch": 10.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 0.9271984100341797,
"eval_runtime": 147.3782,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 44
},
{
"epoch": 11.06,
"eval_accuracy": 0.5652173913043478,
"eval_loss": 0.8047608733177185,
"eval_runtime": 147.4456,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 48
},
{
"epoch": 12.03,
"learning_rate": 1.2931034482758622e-05,
"loss": 0.7004,
"step": 50
},
{
"epoch": 12.06,
"eval_accuracy": 0.5217391304347826,
"eval_loss": 0.853692352771759,
"eval_runtime": 148.0966,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 52
},
{
"epoch": 13.06,
"eval_accuracy": 0.6086956521739131,
"eval_loss": 0.8057894706726074,
"eval_runtime": 152.6302,
"eval_samples_per_second": 0.079,
"eval_steps_per_second": 0.007,
"step": 56
},
{
"epoch": 14.06,
"learning_rate": 4.310344827586207e-06,
"loss": 0.7426,
"step": 60
},
{
"epoch": 14.06,
"eval_accuracy": 0.6956521739130435,
"eval_loss": 1.0632764101028442,
"eval_runtime": 155.1467,
"eval_samples_per_second": 0.077,
"eval_steps_per_second": 0.006,
"step": 60
},
{
"epoch": 15.06,
"eval_accuracy": 0.6521739130434783,
"eval_loss": 0.9449359178543091,
"eval_runtime": 147.86,
"eval_samples_per_second": 0.081,
"eval_steps_per_second": 0.007,
"step": 64
},
{
"epoch": 16.02,
"eval_accuracy": 0.6521739130434783,
"eval_loss": 0.8109930157661438,
"eval_runtime": 162.2761,
"eval_samples_per_second": 0.074,
"eval_steps_per_second": 0.006,
"step": 65
},
{
"epoch": 16.02,
"step": 65,
"total_flos": 1.0168249496056627e+18,
"train_loss": 0.9587483846224272,
"train_runtime": 11819.0424,
"train_samples_per_second": 0.088,
"train_steps_per_second": 0.005
},
{
"epoch": 16.02,
"eval_accuracy": 0.6470588235294118,
"eval_loss": 0.7990540862083435,
"eval_runtime": 249.512,
"eval_samples_per_second": 0.068,
"eval_steps_per_second": 0.008,
"step": 65
},
{
"epoch": 16.02,
"eval_accuracy": 0.6470588235294118,
"eval_loss": 0.7942163944244385,
"eval_runtime": 226.0124,
"eval_samples_per_second": 0.075,
"eval_steps_per_second": 0.009,
"step": 65
}
],
"logging_steps": 10,
"max_steps": 65,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"total_flos": 1.0168249496056627e+18,
"trial_name": null,
"trial_params": null
}