Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 10281800_quality/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 10301000_scene/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
 10301000_scene/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+10301400_distortion/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
+10301400_distortion/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

10301400_distortion/02_distortion/checkpoint-1100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939f3465502a28876aaf8f6de5c6cfda35829847857dc5231cd55c258a69ee05
+size 16318734800

10301400_distortion/02_distortion/checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6892db7df48230fcc6fa95d776cd274c44f22760a342f0683e9e8d7d0606bf
+size 346426383

10301400_distortion/02_distortion/checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f0e07a1e5b3810a741ef08ce80ec1a6cbddf6ed3f076602993e67cc6333b6e
+size 14645

10301400_distortion/02_distortion/checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b483bb51f48271744dfd51aa1714402357db852d618be5c9368ed1c881f1441
+size 1465

10301400_distortion/02_distortion/checkpoint-1100/trainer_state.json

@@ -0,0 +1,284 @@
+{
+  "best_metric": 0.06113849952816963,
+  "best_model_checkpoint": "outputs/10301400_distortion/02_distortion/checkpoint-600",
+  "epoch": 1.2129067843353558,
+  "eval_steps": 100,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 4.398971080780029,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3165,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 2.1092543601989746,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0946,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.07684104144573212,
+      "eval_runtime": 163.0056,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.1530559062957764,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0752,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 4.029064178466797,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.068,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.06602887064218521,
+      "eval_runtime": 163.0122,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.3075804710388184,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0728,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.3959641456604004,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0716,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.06844848394393921,
+      "eval_runtime": 162.9561,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 3.0462310314178467,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0698,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.8907084465026855,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0658,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.061729248613119125,
+      "eval_runtime": 163.1399,
+      "eval_samples_per_second": 11.113,
+      "eval_steps_per_second": 11.113,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.0755972862243652,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0588,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 1.493543267250061,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0599,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.06286018341779709,
+      "eval_runtime": 163.1419,
+      "eval_samples_per_second": 11.113,
+      "eval_steps_per_second": 11.113,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.050912857055664,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0631,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 2.1092123985290527,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0582,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.06113849952816963,
+      "eval_runtime": 162.9295,
+      "eval_samples_per_second": 11.128,
+      "eval_steps_per_second": 11.128,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 2.8029990196228027,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0498,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.664454698562622,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.049,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.06963644176721573,
+      "eval_runtime": 162.9402,
+      "eval_samples_per_second": 11.127,
+      "eval_steps_per_second": 11.127,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.342643976211548,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0492,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.4073305130004883,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0554,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.06153091415762901,
+      "eval_runtime": 162.9695,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 2.655508518218994,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.049,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.3769479990005493,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0513,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.06811496615409851,
+      "eval_runtime": 162.9348,
+      "eval_samples_per_second": 11.127,
+      "eval_steps_per_second": 11.127,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 2.652223587036133,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.044,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 4.13876485824585,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0401,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.07864076644182205,
+      "eval_runtime": 162.9212,
+      "eval_samples_per_second": 11.128,
+      "eval_steps_per_second": 11.128,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 4.5171589851379395,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0374,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 3.778535842895508,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0367,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.07245951890945435,
+      "eval_runtime": 162.9634,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 1100
+    }
+  ],
+  "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
+}

10301400_distortion/02_distortion/checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6cfb4f0788a516920d8f8b2d465db0d17dba56351853ec82837c8b1995a75a
+size 5777

10301400_distortion/02_distortion/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55efd4ca1049a4a9852214cb7057fbb786d1ba05b1026438e55a7447d6565a50
+size 16318734800

10301400_distortion/02_distortion/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bee5d9945273220d051f2a198647e6a85307f8cb10ceb91ecb0e8ba17862a3
+size 346426383

10301400_distortion/02_distortion/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3da020fc5702afd2d09a425e03d909e62946660b8cbea8ee14066231a95e91c
+size 14645

10301400_distortion/02_distortion/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2333d34ce44a7f0bb24990dfa54f0855a3e326ff58182d8b377ba94ef1a86f4f
+size 1465

10301400_distortion/02_distortion/checkpoint-600/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 0.06113849952816963,
+  "best_model_checkpoint": "outputs/10301400_distortion/02_distortion/checkpoint-600",
+  "epoch": 0.6618863761720905,
+  "eval_steps": 100,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 4.398971080780029,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3165,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 2.1092543601989746,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0946,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.07684104144573212,
+      "eval_runtime": 163.0056,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.1530559062957764,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0752,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 4.029064178466797,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.068,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.06602887064218521,
+      "eval_runtime": 163.0122,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.3075804710388184,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0728,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.3959641456604004,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0716,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.06844848394393921,
+      "eval_runtime": 162.9561,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 3.0462310314178467,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0698,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.8907084465026855,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0658,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.061729248613119125,
+      "eval_runtime": 163.1399,
+      "eval_samples_per_second": 11.113,
+      "eval_steps_per_second": 11.113,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.0755972862243652,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0588,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 1.493543267250061,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0599,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.06286018341779709,
+      "eval_runtime": 163.1419,
+      "eval_samples_per_second": 11.113,
+      "eval_steps_per_second": 11.113,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.050912857055664,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0631,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 2.1092123985290527,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0582,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.06113849952816963,
+      "eval_runtime": 162.9295,
+      "eval_samples_per_second": 11.128,
+      "eval_steps_per_second": 11.128,
+      "step": 600
+    }
+  ],
+  "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
+}

10301400_distortion/02_distortion/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6cfb4f0788a516920d8f8b2d465db0d17dba56351853ec82837c8b1995a75a
+size 5777

10301400_distortion/03_quality/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50de3b672314c1aac9432e0ab2dd79f82859abbd5c6fc69a3b92ba25c7fec774
+size 16318734800

10301400_distortion/03_quality/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5529d253ff37bfff11358d2ff7773aaa4f4e98e1b4aa5f250f89c0384f6425b1
+size 346426383

10301400_distortion/03_quality/checkpoint-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f31f6a3d4d2187aa7d04c9591e90bf61ae1bd3a5ed786050e082be51763d49f
+size 14645

10301400_distortion/03_quality/checkpoint-1300/scheduler.pt

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

10301400_distortion/03_quality/checkpoint-1300/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": 0.13926184177398682,
+  "best_model_checkpoint": "outputs/10301400_distortion/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": 4.019044876098633,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.4814,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 7.314701557159424,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1406,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.18189866840839386,
+      "eval_loss_ce": 0.14533164459231868,
+      "eval_loss_fidelity": 0.006811229247094881,
+      "eval_loss_kl": 0.5951160711441261,
+      "eval_mae": 0.3783862858402486,
+      "eval_mse": 0.1861588633092931,
+      "eval_plcc": 0.9299245404914904,
+      "eval_rmse": 0.43146131148608574,
+      "eval_runtime": 181.8345,
+      "eval_samples_per_second": 9.971,
+      "eval_srcc": 0.9290246909826572,
+      "eval_steps_per_second": 9.971,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 4.37626838684082,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1195,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 6.289140224456787,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1223,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.16369320452213287,
+      "eval_loss_ce": 0.13419835370545616,
+      "eval_loss_fidelity": 0.006746233823122041,
+      "eval_loss_kl": 0.45497235639757433,
+      "eval_mae": 0.21657081230266675,
+      "eval_mse": 0.07855148109051084,
+      "eval_plcc": 0.9320308891193664,
+      "eval_rmse": 0.2802703714103773,
+      "eval_runtime": 182.1066,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9279595784142367,
+      "eval_steps_per_second": 9.956,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.7242300510406494,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1278,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.848776340484619,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1166,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.15656112134456635,
+      "eval_loss_ce": 0.1237022492272283,
+      "eval_loss_fidelity": 0.006558822839835765,
+      "eval_loss_kl": 0.5260009151373328,
+      "eval_mae": 0.22548518960671865,
+      "eval_mse": 0.077158616231431,
+      "eval_plcc": 0.9435173303052875,
+      "eval_rmse": 0.2777743980849045,
+      "eval_runtime": 181.3271,
+      "eval_samples_per_second": 9.999,
+      "eval_srcc": 0.930804030358631,
+      "eval_steps_per_second": 9.999,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 5.0159912109375,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1189,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 7.366439342498779,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1104,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.16486240923404694,
+      "eval_loss_ce": 0.14008669278307542,
+      "eval_loss_fidelity": 0.00680576911210496,
+      "eval_loss_kl": 0.3593987776752473,
+      "eval_mae": 0.2302044153345006,
+      "eval_mse": 0.0793010847657882,
+      "eval_plcc": 0.9406855196751255,
+      "eval_rmse": 0.28160448285811823,
+      "eval_runtime": 182.0988,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.929981883954643,
+      "eval_steps_per_second": 9.956,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 6.197667121887207,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1063,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 5.078344345092773,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1088,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.165364608168602,
+      "eval_loss_ce": 0.13470293123889415,
+      "eval_loss_fidelity": 0.005419531040611126,
+      "eval_loss_kl": 0.5048430378117814,
+      "eval_mae": 0.2759270417512745,
+      "eval_mse": 0.10269788011336219,
+      "eval_plcc": 0.9488599406491031,
+      "eval_rmse": 0.32046509968070186,
+      "eval_runtime": 182.0962,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9421177740784626,
+      "eval_steps_per_second": 9.956,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.823759078979492,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1071,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 4.291563987731934,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1084,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.1554974764585495,
+      "eval_loss_ce": 0.1307230718748236,
+      "eval_loss_fidelity": 0.006403040558755217,
+      "eval_loss_kl": 0.36742711352812146,
+      "eval_mae": 0.1864962621216477,
+      "eval_mse": 0.059592364691518615,
+      "eval_plcc": 0.9403007121592394,
+      "eval_rmse": 0.24411547409273057,
+      "eval_runtime": 181.9471,
+      "eval_samples_per_second": 9.964,
+      "eval_srcc": 0.9361725505929468,
+      "eval_steps_per_second": 9.964,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 3.360935926437378,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.1058,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.6806159019470215,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.1081,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.1540636122226715,
+      "eval_loss_ce": 0.13545093288510562,
+      "eval_loss_fidelity": 0.004986723259263978,
+      "eval_loss_kl": 0.27251889424011216,
+      "eval_mae": 0.18477290799719026,
+      "eval_mse": 0.052690209301258895,
+      "eval_plcc": 0.9575197984210698,
+      "eval_rmse": 0.22954348019767168,
+      "eval_runtime": 182.0999,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9450782704973035,
+      "eval_steps_per_second": 9.956,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 5.174151420593262,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.1092,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 3.704911947250366,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1111,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.13926184177398682,
+      "eval_loss_ce": 0.11971334508947425,
+      "eval_loss_fidelity": 0.004512659724356409,
+      "eval_loss_kl": 0.30071664116228736,
+      "eval_mae": 0.1771163505805637,
+      "eval_mse": 0.054031148850699234,
+      "eval_plcc": 0.9575330719736825,
+      "eval_rmse": 0.23244601276575866,
+      "eval_runtime": 182.1087,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9460775187213338,
+      "eval_steps_per_second": 9.956,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 4.368583679199219,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.1092,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 4.650782108306885,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.1072,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.1535249650478363,
+      "eval_loss_ce": 0.129829277290094,
+      "eval_loss_fidelity": 0.005214156694936279,
+      "eval_loss_kl": 0.3696305192246729,
+      "eval_mae": 0.2026542143734923,
+      "eval_mse": 0.06106207042162614,
+      "eval_plcc": 0.9573400997411562,
+      "eval_rmse": 0.24710740665068326,
+      "eval_runtime": 181.9088,
+      "eval_samples_per_second": 9.967,
+      "eval_srcc": 0.9471397891851714,
+      "eval_steps_per_second": 9.967,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 9.181764602661133,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0889,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 3.9697165489196777,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0883,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.17542268335819244,
+      "eval_loss_ce": 0.15021361243257159,
+      "eval_loss_fidelity": 0.005476267666212763,
+      "eval_loss_kl": 0.3946563393900852,
+      "eval_mae": 0.22412548174334704,
+      "eval_mse": 0.0713796607000969,
+      "eval_plcc": 0.9566959219273843,
+      "eval_rmse": 0.26716972264853833,
+      "eval_runtime": 182.264,
+      "eval_samples_per_second": 9.947,
+      "eval_srcc": 0.9443588347899022,
+      "eval_steps_per_second": 9.947,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 6.583629131317139,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.083,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 4.013941764831543,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0851,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.17257744073867798,
+      "eval_loss_ce": 0.15059338354285226,
+      "eval_loss_fidelity": 0.00557460600218206,
+      "eval_loss_kl": 0.3281889781664073,
+      "eval_mae": 0.176997337693742,
+      "eval_mse": 0.05091757251228375,
+      "eval_plcc": 0.9560563945655401,
+      "eval_rmse": 0.22564922448854938,
+      "eval_runtime": 182.3679,
+      "eval_samples_per_second": 9.941,
+      "eval_srcc": 0.9449560185926721,
+      "eval_steps_per_second": 9.941,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 8.078625679016113,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0833,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 5.928958415985107,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.081,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.1737450361251831,
+      "eval_loss_ce": 0.1505227568335893,
+      "eval_loss_fidelity": 0.005111747648359815,
+      "eval_loss_kl": 0.3622108250404351,
+      "eval_mae": 0.19279287687271127,
+      "eval_mse": 0.05816546113157776,
+      "eval_plcc": 0.9551609104057324,
+      "eval_rmse": 0.24117516690484067,
+      "eval_runtime": 182.5654,
+      "eval_samples_per_second": 9.931,
+      "eval_srcc": 0.9431037157554205,
+      "eval_steps_per_second": 9.931,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 3.594672679901123,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0856,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 4.762302875518799,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0782,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.18251168727874756,
+      "eval_loss_ce": 0.15954544610650548,
+      "eval_loss_fidelity": 0.0050411799255942425,
+      "eval_loss_kl": 0.35850090611987,
+      "eval_mae": 0.19589128148404525,
+      "eval_mse": 0.06094218543053067,
+      "eval_plcc": 0.9564460347678968,
+      "eval_rmse": 0.246864710784127,
+      "eval_runtime": 182.2762,
+      "eval_samples_per_second": 9.946,
+      "eval_srcc": 0.9435740591431104,
+      "eval_steps_per_second": 9.946,
+      "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
+}

10301400_distortion/03_quality/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f75bce5900ad9fb2e44035c1a0ec36300df9b8c6e4014e464a9a47c97a67e69
+size 5777

10301400_distortion/03_quality/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a35120cff650c5398d53d79d6569bb75b3d75ac60c5be3a4ff8df3a611bc4c3
+size 16318734800

10301400_distortion/03_quality/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59c3ddf3d94a034e5e66e715abac3003c9914da2922e0176483876fc095e6b1
+size 346426383

10301400_distortion/03_quality/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f9e817c129ca621daae9bd16bdb389220a5551ccd6c2d7561fd9546b87a95a
+size 14645

10301400_distortion/03_quality/checkpoint-800/scheduler.pt

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

10301400_distortion/03_quality/checkpoint-800/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.13926184177398682,
+  "best_model_checkpoint": "outputs/10301400_distortion/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": 4.019044876098633,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.4814,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 7.314701557159424,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1406,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.18189866840839386,
+      "eval_loss_ce": 0.14533164459231868,
+      "eval_loss_fidelity": 0.006811229247094881,
+      "eval_loss_kl": 0.5951160711441261,
+      "eval_mae": 0.3783862858402486,
+      "eval_mse": 0.1861588633092931,
+      "eval_plcc": 0.9299245404914904,
+      "eval_rmse": 0.43146131148608574,
+      "eval_runtime": 181.8345,
+      "eval_samples_per_second": 9.971,
+      "eval_srcc": 0.9290246909826572,
+      "eval_steps_per_second": 9.971,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 4.37626838684082,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1195,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 6.289140224456787,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1223,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.16369320452213287,
+      "eval_loss_ce": 0.13419835370545616,
+      "eval_loss_fidelity": 0.006746233823122041,
+      "eval_loss_kl": 0.45497235639757433,
+      "eval_mae": 0.21657081230266675,
+      "eval_mse": 0.07855148109051084,
+      "eval_plcc": 0.9320308891193664,
+      "eval_rmse": 0.2802703714103773,
+      "eval_runtime": 182.1066,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9279595784142367,
+      "eval_steps_per_second": 9.956,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.7242300510406494,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1278,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.848776340484619,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1166,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.15656112134456635,
+      "eval_loss_ce": 0.1237022492272283,
+      "eval_loss_fidelity": 0.006558822839835765,
+      "eval_loss_kl": 0.5260009151373328,
+      "eval_mae": 0.22548518960671865,
+      "eval_mse": 0.077158616231431,
+      "eval_plcc": 0.9435173303052875,
+      "eval_rmse": 0.2777743980849045,
+      "eval_runtime": 181.3271,
+      "eval_samples_per_second": 9.999,
+      "eval_srcc": 0.930804030358631,
+      "eval_steps_per_second": 9.999,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 5.0159912109375,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1189,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 7.366439342498779,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1104,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.16486240923404694,
+      "eval_loss_ce": 0.14008669278307542,
+      "eval_loss_fidelity": 0.00680576911210496,
+      "eval_loss_kl": 0.3593987776752473,
+      "eval_mae": 0.2302044153345006,
+      "eval_mse": 0.0793010847657882,
+      "eval_plcc": 0.9406855196751255,
+      "eval_rmse": 0.28160448285811823,
+      "eval_runtime": 182.0988,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.929981883954643,
+      "eval_steps_per_second": 9.956,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 6.197667121887207,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1063,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 5.078344345092773,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1088,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.165364608168602,
+      "eval_loss_ce": 0.13470293123889415,
+      "eval_loss_fidelity": 0.005419531040611126,
+      "eval_loss_kl": 0.5048430378117814,
+      "eval_mae": 0.2759270417512745,
+      "eval_mse": 0.10269788011336219,
+      "eval_plcc": 0.9488599406491031,
+      "eval_rmse": 0.32046509968070186,
+      "eval_runtime": 182.0962,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9421177740784626,
+      "eval_steps_per_second": 9.956,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.823759078979492,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1071,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 4.291563987731934,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1084,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.1554974764585495,
+      "eval_loss_ce": 0.1307230718748236,
+      "eval_loss_fidelity": 0.006403040558755217,
+      "eval_loss_kl": 0.36742711352812146,
+      "eval_mae": 0.1864962621216477,
+      "eval_mse": 0.059592364691518615,
+      "eval_plcc": 0.9403007121592394,
+      "eval_rmse": 0.24411547409273057,
+      "eval_runtime": 181.9471,
+      "eval_samples_per_second": 9.964,
+      "eval_srcc": 0.9361725505929468,
+      "eval_steps_per_second": 9.964,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 3.360935926437378,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.1058,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.6806159019470215,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.1081,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.1540636122226715,
+      "eval_loss_ce": 0.13545093288510562,
+      "eval_loss_fidelity": 0.004986723259263978,
+      "eval_loss_kl": 0.27251889424011216,
+      "eval_mae": 0.18477290799719026,
+      "eval_mse": 0.052690209301258895,
+      "eval_plcc": 0.9575197984210698,
+      "eval_rmse": 0.22954348019767168,
+      "eval_runtime": 182.0999,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9450782704973035,
+      "eval_steps_per_second": 9.956,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 5.174151420593262,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.1092,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 3.704911947250366,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1111,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.13926184177398682,
+      "eval_loss_ce": 0.11971334508947425,
+      "eval_loss_fidelity": 0.004512659724356409,
+      "eval_loss_kl": 0.30071664116228736,
+      "eval_mae": 0.1771163505805637,
+      "eval_mse": 0.054031148850699234,
+      "eval_plcc": 0.9575330719736825,
+      "eval_rmse": 0.23244601276575866,
+      "eval_runtime": 182.1087,
+      "eval_samples_per_second": 9.956,
+      "eval_srcc": 0.9460775187213338,
+      "eval_steps_per_second": 9.956,
+      "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
+}

10301400_distortion/03_quality/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f75bce5900ad9fb2e44035c1a0ec36300df9b8c6e4014e464a9a47c97a67e69
+size 5777

10301400_distortion/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

10301400_distortion/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": [
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_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
+}

10301400_distortion/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fabceaf2bb7640e26819e7d1a347a1ec082518faba88461bb0f3e0854125756
+size 173507576

10301400_distortion/final_model/added_tokens.json

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

10301400_distortion/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
+  }
+}

10301400_distortion/final_model/tokenizer.json

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

10301400_distortion/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
+}