llava-bacteria / checkpoint-439 /trainer_state.json
ramankamran's picture
Upload folder using huggingface_hub
5b7c48a verified
{
"best_global_step": 439,
"best_metric": 3.5333664417266846,
"best_model_checkpoint": "./llava-bacterial-colonies-finetuned/checkpoint-439",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 439,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002280501710376283,
"grad_norm": 5.25744104385376,
"learning_rate": 0.0,
"loss": 13.0435,
"step": 1
},
{
"epoch": 0.02280501710376283,
"grad_norm": 5.330052852630615,
"learning_rate": 1.8000000000000001e-06,
"loss": 13.1781,
"step": 10
},
{
"epoch": 0.04561003420752566,
"grad_norm": 5.746432781219482,
"learning_rate": 3.8000000000000005e-06,
"loss": 13.0505,
"step": 20
},
{
"epoch": 0.06841505131128849,
"grad_norm": 7.043069362640381,
"learning_rate": 5.8e-06,
"loss": 12.6685,
"step": 30
},
{
"epoch": 0.09122006841505131,
"grad_norm": 9.116937637329102,
"learning_rate": 7.800000000000002e-06,
"loss": 11.8006,
"step": 40
},
{
"epoch": 0.11402508551881414,
"grad_norm": 9.20152473449707,
"learning_rate": 9.800000000000001e-06,
"loss": 10.0323,
"step": 50
},
{
"epoch": 0.13683010262257697,
"grad_norm": 9.906583786010742,
"learning_rate": 1.18e-05,
"loss": 7.9368,
"step": 60
},
{
"epoch": 0.15963511972633979,
"grad_norm": 3.839442014694214,
"learning_rate": 1.38e-05,
"loss": 5.4885,
"step": 70
},
{
"epoch": 0.18244013683010263,
"grad_norm": 1.1425623893737793,
"learning_rate": 1.58e-05,
"loss": 4.4348,
"step": 80
},
{
"epoch": 0.20524515393386544,
"grad_norm": 0.4169151782989502,
"learning_rate": 1.7800000000000002e-05,
"loss": 4.1557,
"step": 90
},
{
"epoch": 0.22805017103762829,
"grad_norm": 0.2584823668003082,
"learning_rate": 1.98e-05,
"loss": 4.0237,
"step": 100
},
{
"epoch": 0.2508551881413911,
"grad_norm": 0.2669777572154999,
"learning_rate": 1.9965238092738643e-05,
"loss": 3.9437,
"step": 110
},
{
"epoch": 0.27366020524515394,
"grad_norm": 0.20187555253505707,
"learning_rate": 1.9845383720291392e-05,
"loss": 3.8825,
"step": 120
},
{
"epoch": 0.29646522234891676,
"grad_norm": 0.23316368460655212,
"learning_rate": 1.964103607010578e-05,
"loss": 3.8467,
"step": 130
},
{
"epoch": 0.31927023945267957,
"grad_norm": 0.20283794403076172,
"learning_rate": 1.93539488577558e-05,
"loss": 3.7906,
"step": 140
},
{
"epoch": 0.34207525655644244,
"grad_norm": 0.2323773354291916,
"learning_rate": 1.8986585871373792e-05,
"loss": 3.7574,
"step": 150
},
{
"epoch": 0.36488027366020526,
"grad_norm": 0.1659609079360962,
"learning_rate": 1.854209982737192e-05,
"loss": 3.7025,
"step": 160
},
{
"epoch": 0.38768529076396807,
"grad_norm": 0.1513194888830185,
"learning_rate": 1.8024305313767648e-05,
"loss": 3.6803,
"step": 170
},
{
"epoch": 0.4104903078677309,
"grad_norm": 0.1688281148672104,
"learning_rate": 1.743764605331392e-05,
"loss": 3.6409,
"step": 180
},
{
"epoch": 0.43329532497149376,
"grad_norm": 0.16119058430194855,
"learning_rate": 1.678715676738266e-05,
"loss": 3.6219,
"step": 190
},
{
"epoch": 0.45610034207525657,
"grad_norm": 0.11990713328123093,
"learning_rate": 1.6078419967886402e-05,
"loss": 3.5933,
"step": 200
},
{
"epoch": 0.4789053591790194,
"grad_norm": 0.12297182530164719,
"learning_rate": 1.5317518048050698e-05,
"loss": 3.5855,
"step": 210
},
{
"epoch": 0.5017103762827823,
"grad_norm": 0.1178373396396637,
"learning_rate": 1.4510981083195188e-05,
"loss": 3.5786,
"step": 220
},
{
"epoch": 0.5245153933865451,
"grad_norm": 0.10542675107717514,
"learning_rate": 1.366573078949813e-05,
"loss": 3.5658,
"step": 230
},
{
"epoch": 0.5473204104903079,
"grad_norm": 0.1223284974694252,
"learning_rate": 1.2789021121691273e-05,
"loss": 3.5616,
"step": 240
},
{
"epoch": 0.5701254275940707,
"grad_norm": 0.11651907861232758,
"learning_rate": 1.1888376019476966e-05,
"loss": 3.5549,
"step": 250
},
{
"epoch": 0.5929304446978335,
"grad_norm": 0.1205676719546318,
"learning_rate": 1.097152483692886e-05,
"loss": 3.5555,
"step": 260
},
{
"epoch": 0.6157354618015963,
"grad_norm": 0.12340816110372543,
"learning_rate": 1.0046336009022435e-05,
"loss": 3.5497,
"step": 270
},
{
"epoch": 0.6385404789053591,
"grad_norm": 0.1562206894159317,
"learning_rate": 9.12074952457048e-06,
"loss": 3.5409,
"step": 280
},
{
"epoch": 0.661345496009122,
"grad_norm": 0.1315656453371048,
"learning_rate": 8.202708785082122e-06,
"loss": 3.5483,
"step": 290
},
{
"epoch": 0.6841505131128849,
"grad_norm": 0.11144094169139862,
"learning_rate": 7.300092434334021e-06,
"loss": 3.5359,
"step": 300
},
{
"epoch": 0.7069555302166477,
"grad_norm": 0.11713874340057373,
"learning_rate": 6.420646743693715e-06,
"loss": 3.5395,
"step": 310
},
{
"epoch": 0.7297605473204105,
"grad_norm": 0.11104694753885269,
"learning_rate": 5.571919133465605e-06,
"loss": 3.5275,
"step": 320
},
{
"epoch": 0.7525655644241733,
"grad_norm": 0.12047022581100464,
"learning_rate": 4.761193400780667e-06,
"loss": 3.5344,
"step": 330
},
{
"epoch": 0.7753705815279361,
"grad_norm": 0.11065001040697098,
"learning_rate": 3.9954272099054696e-06,
"loss": 3.5284,
"step": 340
},
{
"epoch": 0.798175598631699,
"grad_norm": 0.12179698050022125,
"learning_rate": 3.281192381429894e-06,
"loss": 3.5311,
"step": 350
},
{
"epoch": 0.8209806157354618,
"grad_norm": 0.1203538179397583,
"learning_rate": 2.6246184927728913e-06,
"loss": 3.5357,
"step": 360
},
{
"epoch": 0.8437856328392246,
"grad_norm": 0.12471099942922592,
"learning_rate": 2.031340274027891e-06,
"loss": 3.5312,
"step": 370
},
{
"epoch": 0.8665906499429875,
"grad_norm": 0.1266399621963501,
"learning_rate": 1.5064492505977234e-06,
"loss": 3.5367,
"step": 380
},
{
"epoch": 0.8893956670467503,
"grad_norm": 0.11641562730073929,
"learning_rate": 1.0544500476229713e-06,
"loss": 3.5343,
"step": 390
},
{
"epoch": 0.9122006841505131,
"grad_norm": 0.12872786819934845,
"learning_rate": 6.79221731199936e-07,
"loss": 3.5371,
"step": 400
},
{
"epoch": 0.935005701254276,
"grad_norm": 0.10604371130466461,
"learning_rate": 3.8398451815870984e-07,
"loss": 3.5314,
"step": 410
},
{
"epoch": 0.9578107183580388,
"grad_norm": 0.12464912980794907,
"learning_rate": 1.7127214009868387e-07,
"loss": 3.53,
"step": 420
},
{
"epoch": 0.9806157354618016,
"grad_norm": 0.10792865604162216,
"learning_rate": 4.291009885385333e-08,
"loss": 3.5283,
"step": 430
},
{
"epoch": 1.0,
"eval_loss": 3.5333664417266846,
"eval_runtime": 856.2424,
"eval_samples_per_second": 2.891,
"eval_steps_per_second": 0.181,
"step": 439
}
],
"logging_steps": 10,
"max_steps": 439,
"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": true
},
"attributes": {}
}
},
"total_flos": 4.120770218544906e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}