Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+10281800_quality/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
+10281800_quality/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

10281800_quality/03_quality/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433d806b6c921356be05f33c581cd1f6d3f8522458d2e6ed133b6f832d3953b2
+size 16318734800

10281800_quality/03_quality/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e843daa51c58f6ab356fa1ea878575c27396a18e3170156ade566056a4ea61
+size 346426383

10281800_quality/03_quality/checkpoint-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9b639c4d6556cd03d002c3e9e167bf95156a4561b10c3dd067151d824d3fed
+size 14645

10281800_quality/03_quality/checkpoint-1300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa7e2619b1972c904a264236840cb6f4a48f8a30e77a294592cf31567f370e3
+size 1465

10281800_quality/03_quality/checkpoint-1300/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": 0.11347765475511551,
+  "best_model_checkpoint": "outputs/10281800/03_quality/checkpoint-800",
+  "epoch": 1.4335355763927193,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 13.387487411499023,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.7191,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.996933937072754,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1638,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.1414901167154312,
+      "eval_loss_ce": 0.12415472325194428,
+      "eval_loss_fidelity": 0.005986543978814609,
+      "eval_loss_kl": 0.22697667093506782,
+      "eval_mae": 0.18657843276274777,
+      "eval_mse": 0.05594652153690635,
+      "eval_plcc": 0.9460527927812707,
+      "eval_rmse": 0.23653017045803343,
+      "eval_runtime": 193.544,
+      "eval_samples_per_second": 9.367,
+      "eval_srcc": 0.925077676034924,
+      "eval_steps_per_second": 9.367,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.102055072784424,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1352,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.436919927597046,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1282,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.1285027712583542,
+      "eval_loss_ce": 0.10867043712802572,
+      "eval_loss_fidelity": 0.006215576335637647,
+      "eval_loss_kl": 0.27233521295819274,
+      "eval_mae": 0.2016267084772917,
+      "eval_mse": 0.06523333090953998,
+      "eval_plcc": 0.9437726552976567,
+      "eval_rmse": 0.25540816531493266,
+      "eval_runtime": 193.3524,
+      "eval_samples_per_second": 9.377,
+      "eval_srcc": 0.928293724333605,
+      "eval_steps_per_second": 9.377,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.3737783432006836,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1312,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 3.0248286724090576,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1227,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13584475219249725,
+      "eval_loss_ce": 0.11012294039980884,
+      "eval_loss_fidelity": 0.00569303261405869,
+      "eval_loss_kl": 0.4005754405064472,
+      "eval_mae": 0.20651832668411751,
+      "eval_mse": 0.06894999521782383,
+      "eval_plcc": 0.9523524303458628,
+      "eval_rmse": 0.26258331100400084,
+      "eval_runtime": 194.0018,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9361026783191693,
+      "eval_steps_per_second": 9.345,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.213028907775879,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1245,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 3.453709602355957,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1177,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.11782652884721756,
+      "eval_loss_ce": 0.09938197503029741,
+      "eval_loss_fidelity": 0.0051917363655143685,
+      "eval_loss_kl": 0.2650562682683732,
+      "eval_mae": 0.17846198905191563,
+      "eval_mse": 0.050466884818599345,
+      "eval_plcc": 0.9559835849687088,
+      "eval_rmse": 0.22464835814801618,
+      "eval_runtime": 193.5174,
+      "eval_samples_per_second": 9.369,
+      "eval_srcc": 0.9406590687697203,
+      "eval_steps_per_second": 9.369,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.1485278606414795,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1064,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 3.12270188331604,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1096,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12064410001039505,
+      "eval_loss_ce": 0.10068834675460545,
+      "eval_loss_fidelity": 0.0045511185827136445,
+      "eval_loss_kl": 0.3080925738086572,
+      "eval_mae": 0.20792497815312566,
+      "eval_mse": 0.0638617994679014,
+      "eval_plcc": 0.9594447204012397,
+      "eval_rmse": 0.25270892241450715,
+      "eval_runtime": 193.5271,
+      "eval_samples_per_second": 9.368,
+      "eval_srcc": 0.9455614798534345,
+      "eval_steps_per_second": 9.368,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.704684257507324,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1092,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.2071499824523926,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1074,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.11955778300762177,
+      "eval_loss_ce": 0.10683331529363801,
+      "eval_loss_fidelity": 0.004754444213935109,
+      "eval_loss_kl": 0.15940047010791708,
+      "eval_mae": 0.156920270898759,
+      "eval_mse": 0.04126899699996245,
+      "eval_plcc": 0.9577023552725309,
+      "eval_rmse": 0.20314772211364432,
+      "eval_runtime": 193.9433,
+      "eval_samples_per_second": 9.348,
+      "eval_srcc": 0.9436656888017747,
+      "eval_steps_per_second": 9.348,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.111267566680908,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0998,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.562915325164795,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.098,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.12845788896083832,
+      "eval_loss_ce": 0.10892438954302308,
+      "eval_loss_fidelity": 0.004798042265690865,
+      "eval_loss_kl": 0.2947090462844673,
+      "eval_mae": 0.24365158858249283,
+      "eval_mse": 0.08242214042611157,
+      "eval_plcc": 0.9579876222979091,
+      "eval_rmse": 0.28709256421250545,
+      "eval_runtime": 193.6757,
+      "eval_samples_per_second": 9.361,
+      "eval_srcc": 0.9493277414212722,
+      "eval_steps_per_second": 9.361,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.9521312713623047,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0967,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.3256638050079346,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1013,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.11347765475511551,
+      "eval_loss_ce": 0.09750058033574995,
+      "eval_loss_fidelity": 0.004387858582878104,
+      "eval_loss_kl": 0.2317842715992595,
+      "eval_mae": 0.1639457520896798,
+      "eval_mse": 0.04862147689965385,
+      "eval_plcc": 0.9601418827577104,
+      "eval_rmse": 0.22050278206783208,
+      "eval_runtime": 194.1667,
+      "eval_samples_per_second": 9.337,
+      "eval_srcc": 0.9500311082194068,
+      "eval_steps_per_second": 9.337,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 3.1120851039886475,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0947,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.9989089965820312,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0984,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.12800857424736023,
+      "eval_loss_ce": 0.10576639231859454,
+      "eval_loss_fidelity": 0.004891576720206442,
+      "eval_loss_kl": 0.34701213243397405,
+      "eval_mae": 0.2238324209266911,
+      "eval_mse": 0.07038527729000887,
+      "eval_plcc": 0.9613773811437469,
+      "eval_rmse": 0.26530223762721805,
+      "eval_runtime": 193.8279,
+      "eval_samples_per_second": 9.354,
+      "eval_srcc": 0.9492197623329351,
+      "eval_steps_per_second": 9.354,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 2.069992780685425,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0865,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 3.0044455528259277,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0896,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.12097453325986862,
+      "eval_loss_ce": 0.1063119538233169,
+      "eval_loss_fidelity": 0.004434776629861424,
+      "eval_loss_kl": 0.20455601207307866,
+      "eval_mae": 0.18174353292878662,
+      "eval_mse": 0.049575773152847565,
+      "eval_plcc": 0.9623420381946777,
+      "eval_rmse": 0.22265617699234747,
+      "eval_runtime": 194.2193,
+      "eval_samples_per_second": 9.335,
+      "eval_srcc": 0.949094486040852,
+      "eval_steps_per_second": 9.335,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 3.513611316680908,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0827,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 3.6639721393585205,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0841,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.11945090442895889,
+      "eval_loss_ce": 0.10117677321901028,
+      "eval_loss_fidelity": 0.004639003587681471,
+      "eval_loss_kl": 0.27270255354733935,
+      "eval_mae": 0.18224143370435308,
+      "eval_mse": 0.050978871293168526,
+      "eval_plcc": 0.961903626945595,
+      "eval_rmse": 0.2257850112234391,
+      "eval_runtime": 193.9228,
+      "eval_samples_per_second": 9.349,
+      "eval_srcc": 0.9501964172158129,
+      "eval_steps_per_second": 9.349,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 2.529768228530884,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0829,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 2.399730920791626,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0789,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.12475463002920151,
+      "eval_loss_ce": 0.10555947181484644,
+      "eval_loss_fidelity": 0.004362800421586345,
+      "eval_loss_kl": 0.29664708894430375,
+      "eval_mae": 0.19242379656169406,
+      "eval_mse": 0.05480871773878018,
+      "eval_plcc": 0.9606206460147655,
+      "eval_rmse": 0.23411261764112626,
+      "eval_runtime": 194.012,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9501866893920268,
+      "eval_steps_per_second": 9.345,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 2.6490046977996826,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0782,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 3.5030670166015625,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0792,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.12516798079013824,
+      "eval_loss_ce": 0.10970883657030815,
+      "eval_loss_fidelity": 0.0044777433933443364,
+      "eval_loss_kl": 0.21962809194263608,
+      "eval_mae": 0.16589196663302608,
+      "eval_mse": 0.046286165250229765,
+      "eval_plcc": 0.9612706552627209,
+      "eval_rmse": 0.21514219774425883,
+      "eval_runtime": 194.0607,
+      "eval_samples_per_second": 9.342,
+      "eval_srcc": 0.9478919940531707,
+      "eval_steps_per_second": 9.342,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2718,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

10281800_quality/03_quality/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7a8ec2cc514b60a80455f00d3944f96bbfa86672bc0d86e7d08baeaca34200
+size 5777

10281800_quality/03_quality/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598cc5af8ecea3bc392301990595d547fb60aa545823a0501374754f75945789
+size 16318734800

10281800_quality/03_quality/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679a4515984eed518eadbb26000467f567c89b1c3cf40e0025ee9dcfceb60683
+size 346426383

10281800_quality/03_quality/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee283ba2c7b920d569983076de288f54daba06ab4559af0b92d02c8082ee467
+size 14645

10281800_quality/03_quality/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6abfb4d681afad7f03facbbb0c876f9fe4993cc0f1525af436f8ad8e605c5c
+size 1465

10281800_quality/03_quality/checkpoint-800/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.11347765475511551,
+  "best_model_checkpoint": "outputs/10281800/03_quality/checkpoint-800",
+  "epoch": 0.882515168229454,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 13.387487411499023,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.7191,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.996933937072754,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1638,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.1414901167154312,
+      "eval_loss_ce": 0.12415472325194428,
+      "eval_loss_fidelity": 0.005986543978814609,
+      "eval_loss_kl": 0.22697667093506782,
+      "eval_mae": 0.18657843276274777,
+      "eval_mse": 0.05594652153690635,
+      "eval_plcc": 0.9460527927812707,
+      "eval_rmse": 0.23653017045803343,
+      "eval_runtime": 193.544,
+      "eval_samples_per_second": 9.367,
+      "eval_srcc": 0.925077676034924,
+      "eval_steps_per_second": 9.367,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.102055072784424,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1352,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.436919927597046,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1282,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.1285027712583542,
+      "eval_loss_ce": 0.10867043712802572,
+      "eval_loss_fidelity": 0.006215576335637647,
+      "eval_loss_kl": 0.27233521295819274,
+      "eval_mae": 0.2016267084772917,
+      "eval_mse": 0.06523333090953998,
+      "eval_plcc": 0.9437726552976567,
+      "eval_rmse": 0.25540816531493266,
+      "eval_runtime": 193.3524,
+      "eval_samples_per_second": 9.377,
+      "eval_srcc": 0.928293724333605,
+      "eval_steps_per_second": 9.377,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.3737783432006836,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1312,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 3.0248286724090576,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1227,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13584475219249725,
+      "eval_loss_ce": 0.11012294039980884,
+      "eval_loss_fidelity": 0.00569303261405869,
+      "eval_loss_kl": 0.4005754405064472,
+      "eval_mae": 0.20651832668411751,
+      "eval_mse": 0.06894999521782383,
+      "eval_plcc": 0.9523524303458628,
+      "eval_rmse": 0.26258331100400084,
+      "eval_runtime": 194.0018,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9361026783191693,
+      "eval_steps_per_second": 9.345,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.213028907775879,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1245,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 3.453709602355957,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1177,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.11782652884721756,
+      "eval_loss_ce": 0.09938197503029741,
+      "eval_loss_fidelity": 0.0051917363655143685,
+      "eval_loss_kl": 0.2650562682683732,
+      "eval_mae": 0.17846198905191563,
+      "eval_mse": 0.050466884818599345,
+      "eval_plcc": 0.9559835849687088,
+      "eval_rmse": 0.22464835814801618,
+      "eval_runtime": 193.5174,
+      "eval_samples_per_second": 9.369,
+      "eval_srcc": 0.9406590687697203,
+      "eval_steps_per_second": 9.369,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.1485278606414795,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1064,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 3.12270188331604,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1096,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12064410001039505,
+      "eval_loss_ce": 0.10068834675460545,
+      "eval_loss_fidelity": 0.0045511185827136445,
+      "eval_loss_kl": 0.3080925738086572,
+      "eval_mae": 0.20792497815312566,
+      "eval_mse": 0.0638617994679014,
+      "eval_plcc": 0.9594447204012397,
+      "eval_rmse": 0.25270892241450715,
+      "eval_runtime": 193.5271,
+      "eval_samples_per_second": 9.368,
+      "eval_srcc": 0.9455614798534345,
+      "eval_steps_per_second": 9.368,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.704684257507324,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1092,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.2071499824523926,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1074,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.11955778300762177,
+      "eval_loss_ce": 0.10683331529363801,
+      "eval_loss_fidelity": 0.004754444213935109,
+      "eval_loss_kl": 0.15940047010791708,
+      "eval_mae": 0.156920270898759,
+      "eval_mse": 0.04126899699996245,
+      "eval_plcc": 0.9577023552725309,
+      "eval_rmse": 0.20314772211364432,
+      "eval_runtime": 193.9433,
+      "eval_samples_per_second": 9.348,
+      "eval_srcc": 0.9436656888017747,
+      "eval_steps_per_second": 9.348,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.111267566680908,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0998,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.562915325164795,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.098,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.12845788896083832,
+      "eval_loss_ce": 0.10892438954302308,
+      "eval_loss_fidelity": 0.004798042265690865,
+      "eval_loss_kl": 0.2947090462844673,
+      "eval_mae": 0.24365158858249283,
+      "eval_mse": 0.08242214042611157,
+      "eval_plcc": 0.9579876222979091,
+      "eval_rmse": 0.28709256421250545,
+      "eval_runtime": 193.6757,
+      "eval_samples_per_second": 9.361,
+      "eval_srcc": 0.9493277414212722,
+      "eval_steps_per_second": 9.361,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.9521312713623047,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0967,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.3256638050079346,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1013,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.11347765475511551,
+      "eval_loss_ce": 0.09750058033574995,
+      "eval_loss_fidelity": 0.004387858582878104,
+      "eval_loss_kl": 0.2317842715992595,
+      "eval_mae": 0.1639457520896798,
+      "eval_mse": 0.04862147689965385,
+      "eval_plcc": 0.9601418827577104,
+      "eval_rmse": 0.22050278206783208,
+      "eval_runtime": 194.1667,
+      "eval_samples_per_second": 9.337,
+      "eval_srcc": 0.9500311082194068,
+      "eval_steps_per_second": 9.337,
+      "step": 800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2718,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "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": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

10281800_quality/03_quality/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7a8ec2cc514b60a80455f00d3944f96bbfa86672bc0d86e7d08baeaca34200
+size 5777

10281800_quality/final_model/README.md

@@ -0,0 +1,207 @@
+---
+base_model: src/owl3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:src/owl3
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

10281800_quality/final_model/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "src/owl3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

10281800_quality/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533ae317c340f9426eaac90bdbc99e57245da062142b196b159b7b71a5054951
+size 173507576

10281800_quality/final_model/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

10281800_quality/final_model/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

10281800_quality/final_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

10281800_quality/final_model/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}