Upload folder using huggingface_hub

.gitattributes

@@ -41,3 +41,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 10301400_distortion/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 10302000_full/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
 10302000_full/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+10310000_distortion_2/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
+10310000_distortion_2/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

10310000_distortion_2/02_distortion/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9284f63961668323f1f53f61d2af3b6df233d2cdad1f321cce8b7d19c43dfa
+size 16318734800

10310000_distortion_2/02_distortion/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9633c9cac85904ab8e315bf290300010bb87126ea7a32a7f6db2a8f92b375eec
+size 346426383

10310000_distortion_2/02_distortion/checkpoint-1300/rng_state.pth

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

10310000_distortion_2/02_distortion/checkpoint-1300/scheduler.pt

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

10310000_distortion_2/02_distortion/checkpoint-1300/trainer_state.json

@@ -0,0 +1,328 @@
+{
+  "best_metric": 0.06166021153330803,
+  "best_model_checkpoint": "outputs/10310000_distortion_2/02_distortion/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": 4.739708423614502,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.316,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 2.430459976196289,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0945,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.07679082453250885,
+      "eval_runtime": 163.2544,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.747685432434082,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0745,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.423708438873291,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0677,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.06493379175662994,
+      "eval_runtime": 163.2402,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.492781639099121,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0722,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.6553189754486084,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0721,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.06527131050825119,
+      "eval_runtime": 163.2696,
+      "eval_samples_per_second": 11.104,
+      "eval_steps_per_second": 11.104,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 3.287252426147461,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0703,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 3.1016173362731934,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0657,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.06253320723772049,
+      "eval_runtime": 163.2481,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 2.7413442134857178,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.059,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.087942361831665,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0598,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.06398753821849823,
+      "eval_runtime": 163.2461,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.349041700363159,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0656,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.100663423538208,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0584,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.062480632215738297,
+      "eval_runtime": 163.2237,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 1.863891839981079,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0511,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.0499167442321777,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0497,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.07299517840147018,
+      "eval_runtime": 163.3911,
+      "eval_samples_per_second": 11.096,
+      "eval_steps_per_second": 11.096,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.8057403564453125,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.051,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.9529814720153809,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0541,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.06166021153330803,
+      "eval_runtime": 163.2129,
+      "eval_samples_per_second": 11.108,
+      "eval_steps_per_second": 11.108,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 2.761169910430908,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0516,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.773878812789917,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0518,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.06496413797140121,
+      "eval_runtime": 163.2047,
+      "eval_samples_per_second": 11.109,
+      "eval_steps_per_second": 11.109,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 2.3035829067230225,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0442,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 7.975144386291504,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0395,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.07474347949028015,
+      "eval_runtime": 163.2242,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 5.005626201629639,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0396,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 4.091745376586914,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.036,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.07321278005838394,
+      "eval_runtime": 163.2447,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 1.908857822418213,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0385,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 2.34861421585083,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0352,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.06872279196977615,
+      "eval_runtime": 163.2439,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 3.3281264305114746,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0333,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 5.878439426422119,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0343,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.0736011266708374,
+      "eval_runtime": 163.3082,
+      "eval_samples_per_second": 11.102,
+      "eval_steps_per_second": 11.102,
+      "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
+}

10310000_distortion_2/02_distortion/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d788f38ca31cbfd5fc0843b4750c6de6b244773d2c00472e782d121cbec6f06e
+size 5777

10310000_distortion_2/02_distortion/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90afe8325c4020a9ce6106c9305917fa0cd01ffcb59665f8140f27a8e3fcc37f
+size 16318734800

10310000_distortion_2/02_distortion/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf599765dc2eaf3857a445fdc6d503be8e70fefe46d5d261a7878b6db380de62
+size 346426383

10310000_distortion_2/02_distortion/checkpoint-800/rng_state.pth

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

10310000_distortion_2/02_distortion/checkpoint-800/scheduler.pt

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

10310000_distortion_2/02_distortion/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.06166021153330803,
+  "best_model_checkpoint": "outputs/10310000_distortion_2/02_distortion/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": 4.739708423614502,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.316,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 2.430459976196289,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0945,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.07679082453250885,
+      "eval_runtime": 163.2544,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.747685432434082,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0745,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.423708438873291,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0677,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.06493379175662994,
+      "eval_runtime": 163.2402,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.492781639099121,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0722,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.6553189754486084,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0721,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.06527131050825119,
+      "eval_runtime": 163.2696,
+      "eval_samples_per_second": 11.104,
+      "eval_steps_per_second": 11.104,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 3.287252426147461,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0703,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 3.1016173362731934,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0657,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.06253320723772049,
+      "eval_runtime": 163.2481,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 2.7413442134857178,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.059,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.087942361831665,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0598,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.06398753821849823,
+      "eval_runtime": 163.2461,
+      "eval_samples_per_second": 11.106,
+      "eval_steps_per_second": 11.106,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.349041700363159,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0656,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.100663423538208,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0584,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.062480632215738297,
+      "eval_runtime": 163.2237,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 11.107,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 1.863891839981079,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0511,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.0499167442321777,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0497,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.07299517840147018,
+      "eval_runtime": 163.3911,
+      "eval_samples_per_second": 11.096,
+      "eval_steps_per_second": 11.096,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.8057403564453125,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.051,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.9529814720153809,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0541,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.06166021153330803,
+      "eval_runtime": 163.2129,
+      "eval_samples_per_second": 11.108,
+      "eval_steps_per_second": 11.108,
+      "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
+}

10310000_distortion_2/02_distortion/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d788f38ca31cbfd5fc0843b4750c6de6b244773d2c00472e782d121cbec6f06e
+size 5777

10310000_distortion_2/03_quality/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1c4efdf4850e900fc35c5b976bb0b9e89fee917287553b0349ce54697b72fb
+size 16318734800

10310000_distortion_2/03_quality/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0d13b839dcbf2eb412eb036f9773d85461ef2ce3f9b28b056b5b3660267d17
+size 346426383

10310000_distortion_2/03_quality/checkpoint-1300/rng_state.pth

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

10310000_distortion_2/03_quality/checkpoint-1300/scheduler.pt

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

10310000_distortion_2/03_quality/checkpoint-1300/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": 0.14624693989753723,
+  "best_model_checkpoint": "outputs/10310000_distortion_2/03_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": 5.370368957519531,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.5384,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.7869911193847656,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1414,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.160186767578125,
+      "eval_loss_ce": 0.13344983500312918,
+      "eval_loss_fidelity": 0.006263399597614905,
+      "eval_loss_kl": 0.4094704256032918,
+      "eval_mae": 0.2863667530705767,
+      "eval_mse": 0.11282332999649261,
+      "eval_plcc": 0.9408726626384187,
+      "eval_rmse": 0.33589184270608985,
+      "eval_runtime": 182.5353,
+      "eval_samples_per_second": 9.932,
+      "eval_srcc": 0.9272636941007913,
+      "eval_steps_per_second": 9.932,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.613536357879639,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1166,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 6.740809440612793,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1195,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.17025354504585266,
+      "eval_loss_ce": 0.13880673277880679,
+      "eval_loss_fidelity": 0.006300331372020426,
+      "eval_loss_kl": 0.5029294168544749,
+      "eval_mae": 0.2162596758596817,
+      "eval_mse": 0.07218374855072714,
+      "eval_plcc": 0.9361217402277444,
+      "eval_rmse": 0.26867033433322546,
+      "eval_runtime": 182.1844,
+      "eval_samples_per_second": 9.951,
+      "eval_srcc": 0.927159989616257,
+      "eval_steps_per_second": 9.951,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.40574836730957,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1225,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 3.181164264678955,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1144,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.16156797111034393,
+      "eval_loss_ce": 0.12712889741767164,
+      "eval_loss_fidelity": 0.006659240317795481,
+      "eval_loss_kl": 0.5555964757313863,
+      "eval_mae": 0.2448548036455385,
+      "eval_mse": 0.0901750104186955,
+      "eval_plcc": 0.9474108811152869,
+      "eval_rmse": 0.3002915423695704,
+      "eval_runtime": 182.3197,
+      "eval_samples_per_second": 9.944,
+      "eval_srcc": 0.9250822569153765,
+      "eval_steps_per_second": 9.944,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 1997.496826171875,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 1.2529,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 731.1888427734375,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 1.7702,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.394151896238327,
+      "eval_loss_ce": 0.3566026100483032,
+      "eval_loss_fidelity": 0.010292895955578883,
+      "eval_loss_kl": 0.5451278147496739,
+      "eval_mae": 0.20765985906025486,
+      "eval_mse": 0.07189019133521542,
+      "eval_plcc": 0.9343636465693904,
+      "eval_rmse": 0.2681234628584664,
+      "eval_runtime": 182.3418,
+      "eval_samples_per_second": 9.943,
+      "eval_srcc": 0.9268492690586518,
+      "eval_steps_per_second": 9.943,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 5.454637050628662,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.2437,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 4.566667079925537,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1231,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.1538752168416977,
+      "eval_loss_ce": 0.1285582930414685,
+      "eval_loss_fidelity": 0.005089966759357398,
+      "eval_loss_kl": 0.40453891455305263,
+      "eval_mae": 0.20164762244195616,
+      "eval_mse": 0.06574067616445382,
+      "eval_plcc": 0.9549123854372076,
+      "eval_rmse": 0.25639944649794744,
+      "eval_runtime": 182.2852,
+      "eval_samples_per_second": 9.946,
+      "eval_srcc": 0.9411149043408595,
+      "eval_steps_per_second": 9.946,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.4098644256591797,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1122,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 4.559642791748047,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1083,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.15377217531204224,
+      "eval_loss_ce": 0.13326466489856537,
+      "eval_loss_fidelity": 0.006129595441128265,
+      "eval_loss_kl": 0.2875580057888089,
+      "eval_mae": 0.1750286323749355,
+      "eval_mse": 0.05010185504017415,
+      "eval_plcc": 0.9511539877362545,
+      "eval_rmse": 0.22383443667178238,
+      "eval_runtime": 182.5573,
+      "eval_samples_per_second": 9.931,
+      "eval_srcc": 0.938154453462008,
+      "eval_steps_per_second": 9.931,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.346314907073975,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.099,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 4.62398099899292,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.1002,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.16349147260189056,
+      "eval_loss_ce": 0.14273829341974464,
+      "eval_loss_fidelity": 0.005069877849470555,
+      "eval_loss_kl": 0.31366612849745773,
+      "eval_mae": 0.20003803770514528,
+      "eval_mse": 0.06089766426469378,
+      "eval_plcc": 0.954459737630765,
+      "eval_rmse": 0.2467745211011335,
+      "eval_runtime": 182.8147,
+      "eval_samples_per_second": 9.917,
+      "eval_srcc": 0.9393287127453113,
+      "eval_steps_per_second": 9.917,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 12.061041831970215,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.101,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 4.110635280609131,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1018,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.14624693989753723,
+      "eval_loss_ce": 0.12524422347726444,
+      "eval_loss_fidelity": 0.0047643733655461625,
+      "eval_loss_kl": 0.3247666384098087,
+      "eval_mae": 0.17847601419250017,
+      "eval_mse": 0.05593952531051613,
+      "eval_plcc": 0.9571452056776578,
+      "eval_rmse": 0.2365153807060254,
+      "eval_runtime": 182.692,
+      "eval_samples_per_second": 9.924,
+      "eval_srcc": 0.9438882190466003,
+      "eval_steps_per_second": 9.924,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 8.00714111328125,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.1137,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 2.868720054626465,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.1135,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.14885397255420685,
+      "eval_loss_ce": 0.12435331336858026,
+      "eval_loss_fidelity": 0.005504329942418,
+      "eval_loss_kl": 0.3799265777282273,
+      "eval_mae": 0.21171917825920833,
+      "eval_mse": 0.06485850597136998,
+      "eval_plcc": 0.9566522167314164,
+      "eval_rmse": 0.254673331881,
+      "eval_runtime": 182.3813,
+      "eval_samples_per_second": 9.941,
+      "eval_srcc": 0.9462734038540416,
+      "eval_steps_per_second": 9.941,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 3.6468873023986816,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.092,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 12.779086112976074,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0911,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.1758156269788742,
+      "eval_loss_ce": 0.15648763587876077,
+      "eval_loss_fidelity": 0.005138602388238815,
+      "eval_loss_kl": 0.2837877967618344,
+      "eval_mae": 0.20581173765284544,
+      "eval_mse": 0.062408888762529535,
+      "eval_plcc": 0.9567477939221787,
+      "eval_rmse": 0.24981771106654854,
+      "eval_runtime": 182.4879,
+      "eval_samples_per_second": 9.935,
+      "eval_srcc": 0.9434693615819273,
+      "eval_steps_per_second": 9.935,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 6.436306953430176,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0878,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 3.543393135070801,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0849,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.15879832208156586,
+      "eval_loss_ce": 0.13702476198255392,
+      "eval_loss_fidelity": 0.00529953807555663,
+      "eval_loss_kl": 0.3294804731185635,
+      "eval_mae": 0.18171725316528978,
+      "eval_mse": 0.05326614476549163,
+      "eval_plcc": 0.957127332416401,
+      "eval_rmse": 0.23079459431601,
+      "eval_runtime": 182.4219,
+      "eval_samples_per_second": 9.939,
+      "eval_srcc": 0.9446427302709183,
+      "eval_steps_per_second": 9.939,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 6.421344757080078,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0867,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 2.195136308670044,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0838,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.17306554317474365,
+      "eval_loss_ce": 0.14609073305176853,
+      "eval_loss_fidelity": 0.005099316119306985,
+      "eval_loss_kl": 0.43750985771606654,
+      "eval_mae": 0.20550495290782528,
+      "eval_mse": 0.061717152859574145,
+      "eval_plcc": 0.9559907115381092,
+      "eval_rmse": 0.24842937197435844,
+      "eval_runtime": 182.5817,
+      "eval_samples_per_second": 9.93,
+      "eval_srcc": 0.9467990492965072,
+      "eval_steps_per_second": 9.93,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 3.6577117443084717,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0844,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 5.0923614501953125,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0803,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.17274700105190277,
+      "eval_loss_ce": 0.15164567936279633,
+      "eval_loss_fidelity": 0.005255393657487366,
+      "eval_loss_kl": 0.31691873124947023,
+      "eval_mae": 0.17286345936353867,
+      "eval_mse": 0.04938264550520843,
+      "eval_plcc": 0.9575426219099382,
+      "eval_rmse": 0.2222220634977734,
+      "eval_runtime": 182.5317,
+      "eval_samples_per_second": 9.933,
+      "eval_srcc": 0.9452522907769002,
+      "eval_steps_per_second": 9.933,
+      "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
+}

10310000_distortion_2/03_quality/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416451fec5efa329c6b28958c64adf438399e47db5e85fbd58229a33b4a6c4bf
+size 5777

10310000_distortion_2/03_quality/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ba96b725137ef266fc4a10d59a2ab34d7376aa2e36d83dee453be92ea0ec4c
+size 16318734800

10310000_distortion_2/03_quality/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f308226aa26f6c2307c692384a7ef8875e824973388c3aa858cfe1f92884b12f
+size 346426383

10310000_distortion_2/03_quality/checkpoint-800/rng_state.pth

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

10310000_distortion_2/03_quality/checkpoint-800/scheduler.pt

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

10310000_distortion_2/03_quality/checkpoint-800/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.14624693989753723,
+  "best_model_checkpoint": "outputs/10310000_distortion_2/03_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": 5.370368957519531,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.5384,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.7869911193847656,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1414,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.160186767578125,
+      "eval_loss_ce": 0.13344983500312918,
+      "eval_loss_fidelity": 0.006263399597614905,
+      "eval_loss_kl": 0.4094704256032918,
+      "eval_mae": 0.2863667530705767,
+      "eval_mse": 0.11282332999649261,
+      "eval_plcc": 0.9408726626384187,
+      "eval_rmse": 0.33589184270608985,
+      "eval_runtime": 182.5353,
+      "eval_samples_per_second": 9.932,
+      "eval_srcc": 0.9272636941007913,
+      "eval_steps_per_second": 9.932,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.613536357879639,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1166,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 6.740809440612793,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1195,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.17025354504585266,
+      "eval_loss_ce": 0.13880673277880679,
+      "eval_loss_fidelity": 0.006300331372020426,
+      "eval_loss_kl": 0.5029294168544749,
+      "eval_mae": 0.2162596758596817,
+      "eval_mse": 0.07218374855072714,
+      "eval_plcc": 0.9361217402277444,
+      "eval_rmse": 0.26867033433322546,
+      "eval_runtime": 182.1844,
+      "eval_samples_per_second": 9.951,
+      "eval_srcc": 0.927159989616257,
+      "eval_steps_per_second": 9.951,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.40574836730957,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1225,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 3.181164264678955,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1144,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.16156797111034393,
+      "eval_loss_ce": 0.12712889741767164,
+      "eval_loss_fidelity": 0.006659240317795481,
+      "eval_loss_kl": 0.5555964757313863,
+      "eval_mae": 0.2448548036455385,
+      "eval_mse": 0.0901750104186955,
+      "eval_plcc": 0.9474108811152869,
+      "eval_rmse": 0.3002915423695704,
+      "eval_runtime": 182.3197,
+      "eval_samples_per_second": 9.944,
+      "eval_srcc": 0.9250822569153765,
+      "eval_steps_per_second": 9.944,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 1997.496826171875,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 1.2529,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 731.1888427734375,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 1.7702,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.394151896238327,
+      "eval_loss_ce": 0.3566026100483032,
+      "eval_loss_fidelity": 0.010292895955578883,
+      "eval_loss_kl": 0.5451278147496739,
+      "eval_mae": 0.20765985906025486,
+      "eval_mse": 0.07189019133521542,
+      "eval_plcc": 0.9343636465693904,
+      "eval_rmse": 0.2681234628584664,
+      "eval_runtime": 182.3418,
+      "eval_samples_per_second": 9.943,
+      "eval_srcc": 0.9268492690586518,
+      "eval_steps_per_second": 9.943,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 5.454637050628662,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.2437,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 4.566667079925537,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1231,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.1538752168416977,
+      "eval_loss_ce": 0.1285582930414685,
+      "eval_loss_fidelity": 0.005089966759357398,
+      "eval_loss_kl": 0.40453891455305263,
+      "eval_mae": 0.20164762244195616,
+      "eval_mse": 0.06574067616445382,
+      "eval_plcc": 0.9549123854372076,
+      "eval_rmse": 0.25639944649794744,
+      "eval_runtime": 182.2852,
+      "eval_samples_per_second": 9.946,
+      "eval_srcc": 0.9411149043408595,
+      "eval_steps_per_second": 9.946,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.4098644256591797,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1122,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 4.559642791748047,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.1083,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.15377217531204224,
+      "eval_loss_ce": 0.13326466489856537,
+      "eval_loss_fidelity": 0.006129595441128265,
+      "eval_loss_kl": 0.2875580057888089,
+      "eval_mae": 0.1750286323749355,
+      "eval_mse": 0.05010185504017415,
+      "eval_plcc": 0.9511539877362545,
+      "eval_rmse": 0.22383443667178238,
+      "eval_runtime": 182.5573,
+      "eval_samples_per_second": 9.931,
+      "eval_srcc": 0.938154453462008,
+      "eval_steps_per_second": 9.931,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.346314907073975,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.099,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 4.62398099899292,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.1002,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.16349147260189056,
+      "eval_loss_ce": 0.14273829341974464,
+      "eval_loss_fidelity": 0.005069877849470555,
+      "eval_loss_kl": 0.31366612849745773,
+      "eval_mae": 0.20003803770514528,
+      "eval_mse": 0.06089766426469378,
+      "eval_plcc": 0.954459737630765,
+      "eval_rmse": 0.2467745211011335,
+      "eval_runtime": 182.8147,
+      "eval_samples_per_second": 9.917,
+      "eval_srcc": 0.9393287127453113,
+      "eval_steps_per_second": 9.917,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 12.061041831970215,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.101,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 4.110635280609131,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.1018,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.14624693989753723,
+      "eval_loss_ce": 0.12524422347726444,
+      "eval_loss_fidelity": 0.0047643733655461625,
+      "eval_loss_kl": 0.3247666384098087,
+      "eval_mae": 0.17847601419250017,
+      "eval_mse": 0.05593952531051613,
+      "eval_plcc": 0.9571452056776578,
+      "eval_rmse": 0.2365153807060254,
+      "eval_runtime": 182.692,
+      "eval_samples_per_second": 9.924,
+      "eval_srcc": 0.9438882190466003,
+      "eval_steps_per_second": 9.924,
+      "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
+}

10310000_distortion_2/03_quality/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416451fec5efa329c6b28958c64adf438399e47db5e85fbd58229a33b4a6c4bf
+size 5777

10310000_distortion_2/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

10310000_distortion_2/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": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

10310000_distortion_2/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe37ce6aaa84c9c3ef35c034959785238218ce65f0a6fadd52289726e5081ca
+size 173507576

10310000_distortion_2/final_model/added_tokens.json

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

10310000_distortion_2/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
+  }
+}

10310000_distortion_2/final_model/tokenizer.json

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

10310000_distortion_2/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
+}