PEFT
Safetensors
English
Paligemma2_lora / trainer_state.json
LuciexJune's picture
Upload 8 files
61cf3ac verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13333333333333333,
"grad_norm": 51.06103515625,
"learning_rate": 1.869158878504673e-05,
"loss": 1.1397,
"step": 100
},
{
"epoch": 0.26666666666666666,
"grad_norm": 29.371679306030273,
"learning_rate": 1.7356475300400533e-05,
"loss": 0.6966,
"step": 200
},
{
"epoch": 0.4,
"grad_norm": 37.94963455200195,
"learning_rate": 1.602136181575434e-05,
"loss": 0.4605,
"step": 300
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.42650002241134644,
"learning_rate": 1.4686248331108147e-05,
"loss": 0.5428,
"step": 400
},
{
"epoch": 0.6666666666666666,
"grad_norm": 202.76437377929688,
"learning_rate": 1.335113484646195e-05,
"loss": 0.4785,
"step": 500
},
{
"epoch": 0.8,
"grad_norm": 0.011508260853588581,
"learning_rate": 1.2016021361815755e-05,
"loss": 0.3989,
"step": 600
},
{
"epoch": 0.9333333333333333,
"grad_norm": 6.5181193351745605,
"learning_rate": 1.068090787716956e-05,
"loss": 0.5321,
"step": 700
},
{
"epoch": 1.0666666666666667,
"grad_norm": 30.055387496948242,
"learning_rate": 9.345794392523365e-06,
"loss": 0.4692,
"step": 800
},
{
"epoch": 1.2,
"grad_norm": 172.0653533935547,
"learning_rate": 8.01068090787717e-06,
"loss": 0.4043,
"step": 900
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.040170542895793915,
"learning_rate": 6.675567423230975e-06,
"loss": 0.3241,
"step": 1000
},
{
"epoch": 1.4666666666666668,
"grad_norm": 201.94967651367188,
"learning_rate": 5.34045393858478e-06,
"loss": 0.3917,
"step": 1100
},
{
"epoch": 1.6,
"grad_norm": 0.024023059755563736,
"learning_rate": 4.005340453938585e-06,
"loss": 0.2185,
"step": 1200
},
{
"epoch": 1.7333333333333334,
"grad_norm": 0.1882331371307373,
"learning_rate": 2.67022696929239e-06,
"loss": 0.4324,
"step": 1300
},
{
"epoch": 1.8666666666666667,
"grad_norm": 0.01553017646074295,
"learning_rate": 1.335113484646195e-06,
"loss": 0.2871,
"step": 1400
},
{
"epoch": 2.0,
"grad_norm": 471.4150085449219,
"learning_rate": 0.0,
"loss": 0.3236,
"step": 1500
}
],
"logging_steps": 100,
"max_steps": 1500,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.971060451616e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}