Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 10281800_quality/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
 10281800_quality/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+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

10301000_scene/01_scene/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bdf9997aa9f9297658bb0f7dda1943bced7d98a442d013e837d6a6b5576dbf
+size 16318734800

10301000_scene/01_scene/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cec99641f480e55ab2847c0b94e3397ddcd250f9660856c2a9191ff32a45b20
+size 346426383

10301000_scene/01_scene/checkpoint-1300/rng_state.pth

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

10301000_scene/01_scene/checkpoint-1300/scheduler.pt

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

10301000_scene/01_scene/checkpoint-1300/trainer_state.json

@@ -0,0 +1,328 @@
+{
+  "best_metric": 0.029789932072162628,
+  "best_model_checkpoint": "outputs/10301000_scene/01_scene/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": 7.3662309646606445,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3503,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.870361566543579,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0542,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.04481216147542,
+      "eval_runtime": 162.787,
+      "eval_samples_per_second": 11.137,
+      "eval_steps_per_second": 11.137,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.507421016693115,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0396,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 1.4566999673843384,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0331,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.03566218540072441,
+      "eval_runtime": 162.7714,
+      "eval_samples_per_second": 11.138,
+      "eval_steps_per_second": 11.138,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.037930011749268,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0395,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.294311761856079,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0301,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.03191058337688446,
+      "eval_runtime": 162.7277,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 2.6978514194488525,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0319,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 5.646521091461182,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0337,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.036804407835006714,
+      "eval_runtime": 162.7513,
+      "eval_samples_per_second": 11.14,
+      "eval_steps_per_second": 11.14,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 1.923626184463501,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0221,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.145982027053833,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.024,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.040965329855680466,
+      "eval_runtime": 162.9041,
+      "eval_samples_per_second": 11.129,
+      "eval_steps_per_second": 11.129,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.581226348876953,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0278,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 1.033862590789795,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0256,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.039661359041929245,
+      "eval_runtime": 162.9549,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 2.987748384475708,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0233,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.0348806381225586,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0239,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.03564481437206268,
+      "eval_runtime": 162.7369,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 1.8054457902908325,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0226,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.0890982151031494,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0225,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.029789932072162628,
+      "eval_runtime": 162.7272,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 1.0064603090286255,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0139,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.894441843032837,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0203,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.035131826996803284,
+      "eval_runtime": 162.7591,
+      "eval_samples_per_second": 11.139,
+      "eval_steps_per_second": 11.139,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 0.24329999089241028,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0115,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 1.2898188829421997,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0147,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.03382768854498863,
+      "eval_runtime": 163.2084,
+      "eval_samples_per_second": 11.108,
+      "eval_steps_per_second": 11.108,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 1.4235050678253174,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0143,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 0.1954454779624939,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0163,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.03491608425974846,
+      "eval_runtime": 163.4456,
+      "eval_samples_per_second": 11.092,
+      "eval_steps_per_second": 11.092,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 0.8286010026931763,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0131,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 1.0664633512496948,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0109,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.03772859647870064,
+      "eval_runtime": 163.4733,
+      "eval_samples_per_second": 11.09,
+      "eval_steps_per_second": 11.09,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 1.1173100471496582,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0128,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 5.112654685974121,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0109,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.04015617072582245,
+      "eval_runtime": 163.2627,
+      "eval_samples_per_second": 11.105,
+      "eval_steps_per_second": 11.105,
+      "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
+}

10301000_scene/01_scene/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dec4172a036012213a63ad98fcd4d4d2c271fd50fd34e394ae7734cd17978f9
+size 5777

10301000_scene/01_scene/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a27ef2337e0352ae8b4dd48a93d49df553e851df91177d761e21a40ff2300e93
+size 16318734800

10301000_scene/01_scene/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a824f1ad1ef181e51bc984eaa6c7a3aa6238d6aa5c701faafd5d353f820d5f1c
+size 346426383

10301000_scene/01_scene/checkpoint-800/rng_state.pth

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

10301000_scene/01_scene/checkpoint-800/scheduler.pt

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

10301000_scene/01_scene/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.029789932072162628,
+  "best_model_checkpoint": "outputs/10301000_scene/01_scene/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": 7.3662309646606445,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3503,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.870361566543579,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0542,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.04481216147542,
+      "eval_runtime": 162.787,
+      "eval_samples_per_second": 11.137,
+      "eval_steps_per_second": 11.137,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.507421016693115,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0396,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 1.4566999673843384,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0331,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.03566218540072441,
+      "eval_runtime": 162.7714,
+      "eval_samples_per_second": 11.138,
+      "eval_steps_per_second": 11.138,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.037930011749268,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0395,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.294311761856079,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0301,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.03191058337688446,
+      "eval_runtime": 162.7277,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 2.6978514194488525,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0319,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 5.646521091461182,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0337,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.036804407835006714,
+      "eval_runtime": 162.7513,
+      "eval_samples_per_second": 11.14,
+      "eval_steps_per_second": 11.14,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 1.923626184463501,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0221,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.145982027053833,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.024,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.040965329855680466,
+      "eval_runtime": 162.9041,
+      "eval_samples_per_second": 11.129,
+      "eval_steps_per_second": 11.129,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.581226348876953,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0278,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 1.033862590789795,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0256,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.039661359041929245,
+      "eval_runtime": 162.9549,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 2.987748384475708,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0233,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.0348806381225586,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0239,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.03564481437206268,
+      "eval_runtime": 162.7369,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 1.8054457902908325,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0226,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.0890982151031494,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0225,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.029789932072162628,
+      "eval_runtime": 162.7272,
+      "eval_samples_per_second": 11.141,
+      "eval_steps_per_second": 11.141,
+      "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
+}

10301000_scene/01_scene/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dec4172a036012213a63ad98fcd4d4d2c271fd50fd34e394ae7734cd17978f9
+size 5777

10301000_scene/03_quality/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bf64b69fe3b2d33538509d12c74c43bb29b03c8e540bc8823c30f8f5f83ad2
+size 16318734800

10301000_scene/03_quality/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8a77bcb1c2917d2262c00d957634428e5852fc4539fa5a25cf574f27c95c99
+size 346426383

10301000_scene/03_quality/checkpoint-1300/rng_state.pth

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

10301000_scene/03_quality/checkpoint-1300/scheduler.pt

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

10301000_scene/03_quality/checkpoint-1300/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": 0.1208026111125946,
+  "best_model_checkpoint": "outputs/10301000_scene/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": 5.42327880859375,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.6427,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 5.0108442306518555,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1429,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.16806671023368835,
+      "eval_loss_ce": 0.13431005162211065,
+      "eval_loss_fidelity": 0.008783203234790243,
+      "eval_loss_kl": 0.49946922953335604,
+      "eval_mae": 0.381257920980585,
+      "eval_mse": 0.1923882749511589,
+      "eval_plcc": 0.9271362725922992,
+      "eval_rmse": 0.4386208783803604,
+      "eval_runtime": 193.8144,
+      "eval_samples_per_second": 9.354,
+      "eval_srcc": 0.9124191363393883,
+      "eval_steps_per_second": 9.354,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.362459659576416,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1194,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.8072218894958496,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1172,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.12831401824951172,
+      "eval_loss_ce": 0.11097296372249156,
+      "eval_loss_fidelity": 0.006253569476474416,
+      "eval_loss_kl": 0.22174966832960893,
+      "eval_mae": 0.20121037322253202,
+      "eval_mse": 0.06361294796902603,
+      "eval_plcc": 0.9468404722299074,
+      "eval_rmse": 0.25221607397036777,
+      "eval_runtime": 194.0009,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9270710175393225,
+      "eval_steps_per_second": 9.345,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 1.8970513343811035,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1152,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.407395362854004,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1089,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.1323900669813156,
+      "eval_loss_ce": 0.10430994520032695,
+      "eval_loss_fidelity": 0.00622050792183799,
+      "eval_loss_kl": 0.4371923788934042,
+      "eval_mae": 0.21929533699896214,
+      "eval_mse": 0.07086994615090463,
+      "eval_plcc": 0.9490074927574884,
+      "eval_rmse": 0.2662140983323472,
+      "eval_runtime": 193.8226,
+      "eval_samples_per_second": 9.354,
+      "eval_srcc": 0.9334829554593803,
+      "eval_steps_per_second": 9.354,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.103539943695068,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1081,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.8650267124176025,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1059,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.12093069404363632,
+      "eval_loss_ce": 0.10364307694022029,
+      "eval_loss_fidelity": 0.005853999140231895,
+      "eval_loss_kl": 0.2286723717940294,
+      "eval_mae": 0.18385793126490782,
+      "eval_mse": 0.05349869967082972,
+      "eval_plcc": 0.9540438908778303,
+      "eval_rmse": 0.23129785920070622,
+      "eval_runtime": 194.0204,
+      "eval_samples_per_second": 9.344,
+      "eval_srcc": 0.9344902330605833,
+      "eval_steps_per_second": 9.344,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.2437682151794434,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0976,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.573291778564453,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0989,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12131964415311813,
+      "eval_loss_ce": 0.10263459754093733,
+      "eval_loss_fidelity": 0.004701675696661146,
+      "eval_loss_kl": 0.27966752866980654,
+      "eval_mae": 0.19855049382371265,
+      "eval_mse": 0.06069235738311096,
+      "eval_plcc": 0.95847852622544,
+      "eval_rmse": 0.2463581891943334,
+      "eval_runtime": 194.2798,
+      "eval_samples_per_second": 9.332,
+      "eval_srcc": 0.9461807383546013,
+      "eval_steps_per_second": 9.332,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.7759504318237305,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0972,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.2406930923461914,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0969,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.12333808839321136,
+      "eval_loss_ce": 0.1073055888284193,
+      "eval_loss_fidelity": 0.005524211695686294,
+      "eval_loss_kl": 0.2101658280883385,
+      "eval_mae": 0.17873067449484487,
+      "eval_mse": 0.05457294060711482,
+      "eval_plcc": 0.9496280321348384,
+      "eval_rmse": 0.2336085199797191,
+      "eval_runtime": 193.9022,
+      "eval_samples_per_second": 9.35,
+      "eval_srcc": 0.9369566444197541,
+      "eval_steps_per_second": 9.35,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.002472877502441,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0901,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.2214629650115967,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0896,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.13337895274162292,
+      "eval_loss_ce": 0.1124543054116673,
+      "eval_loss_fidelity": 0.005232234648721019,
+      "eval_loss_kl": 0.3138483108976271,
+      "eval_mae": 0.22865299493386743,
+      "eval_mse": 0.07488270896452447,
+      "eval_plcc": 0.956187979339341,
+      "eval_rmse": 0.27364705181040133,
+      "eval_runtime": 194.2639,
+      "eval_samples_per_second": 9.333,
+      "eval_srcc": 0.9451516040682881,
+      "eval_steps_per_second": 9.333,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.340487480163574,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0857,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 3.1692540645599365,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0928,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.1208026111125946,
+      "eval_loss_ce": 0.10572340061104206,
+      "eval_loss_fidelity": 0.004452917122480373,
+      "eval_loss_kl": 0.21252604568622682,
+      "eval_mae": 0.16965420668255343,
+      "eval_mse": 0.05175068374163564,
+      "eval_plcc": 0.9604690894495514,
+      "eval_rmse": 0.22748776613619387,
+      "eval_runtime": 194.3097,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.9484231224700905,
+      "eval_steps_per_second": 9.33,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 3.3101210594177246,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0918,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.8725101947784424,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0939,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.1232498437166214,
+      "eval_loss_ce": 0.10415053878840463,
+      "eval_loss_fidelity": 0.004926572107222965,
+      "eval_loss_kl": 0.28345453551668887,
+      "eval_mae": 0.20001942691918703,
+      "eval_mse": 0.058741716633982324,
+      "eval_plcc": 0.9586843103642018,
+      "eval_rmse": 0.24236690498907298,
+      "eval_runtime": 194.213,
+      "eval_samples_per_second": 9.335,
+      "eval_srcc": 0.9478432622299423,
+      "eval_steps_per_second": 9.335,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 1.8655438423156738,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0802,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 3.0188446044921875,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0794,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.1259012073278427,
+      "eval_loss_ce": 0.11297351326968087,
+      "eval_loss_fidelity": 0.004811328074863896,
+      "eval_loss_kl": 0.16232713172289298,
+      "eval_mae": 0.16140954111796746,
+      "eval_mse": 0.04242565071497381,
+      "eval_plcc": 0.9606445316327052,
+      "eval_rmse": 0.20597487884442076,
+      "eval_runtime": 194.0891,
+      "eval_samples_per_second": 9.341,
+      "eval_srcc": 0.9466799856388746,
+      "eval_steps_per_second": 9.341,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 2.7614400386810303,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0767,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 3.723970413208008,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0753,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.12658272683620453,
+      "eval_loss_ce": 0.10874817815444382,
+      "eval_loss_fidelity": 0.004757831160092631,
+      "eval_loss_kl": 0.2615344605105017,
+      "eval_mae": 0.18044947019546517,
+      "eval_mse": 0.051002855666950855,
+      "eval_plcc": 0.9610017883719589,
+      "eval_rmse": 0.22583811827712091,
+      "eval_runtime": 194.2498,
+      "eval_samples_per_second": 9.333,
+      "eval_srcc": 0.948460617931723,
+      "eval_steps_per_second": 9.333,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 2.500993251800537,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0749,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 3.0908048152923584,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0733,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.13037295639514923,
+      "eval_loss_ce": 0.11334916856910436,
+      "eval_loss_fidelity": 0.004606792521103086,
+      "eval_loss_kl": 0.24833992168397714,
+      "eval_mae": 0.17167855269068588,
+      "eval_mse": 0.04605128884904391,
+      "eval_plcc": 0.9591189196722906,
+      "eval_rmse": 0.21459564033093476,
+      "eval_runtime": 194.4584,
+      "eval_samples_per_second": 9.323,
+      "eval_srcc": 0.9475971464294937,
+      "eval_steps_per_second": 9.323,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 2.856445074081421,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0733,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 3.217556953430176,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0738,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.131883442401886,
+      "eval_loss_ce": 0.11484843639629162,
+      "eval_loss_fidelity": 0.004598084652590397,
+      "eval_loss_kl": 0.24873833341233256,
+      "eval_mae": 0.1736117241728457,
+      "eval_mse": 0.04932509981302436,
+      "eval_plcc": 0.9597831882383727,
+      "eval_rmse": 0.2220925478556729,
+      "eval_runtime": 194.3555,
+      "eval_samples_per_second": 9.328,
+      "eval_srcc": 0.9469294077832586,
+      "eval_steps_per_second": 9.328,
+      "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
+}

10301000_scene/03_quality/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf7d848a8c13168f9141e1827d269205a4a2fb4462363014d18b450cf94a020
+size 5777

10301000_scene/03_quality/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65d5f1deedbffb5285c91025681fb7ada70cf7e2bc5fa83a1f1c65cca655d53
+size 16318734800

10301000_scene/03_quality/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20696d5271bcfb472148fdaa215c0b031391bf8cf8de1dba8574ba1256a467c5
+size 346426383

10301000_scene/03_quality/checkpoint-800/rng_state.pth

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

10301000_scene/03_quality/checkpoint-800/scheduler.pt

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

10301000_scene/03_quality/checkpoint-800/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.1208026111125946,
+  "best_model_checkpoint": "outputs/10301000_scene/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": 5.42327880859375,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.6427,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 5.0108442306518555,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1429,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.16806671023368835,
+      "eval_loss_ce": 0.13431005162211065,
+      "eval_loss_fidelity": 0.008783203234790243,
+      "eval_loss_kl": 0.49946922953335604,
+      "eval_mae": 0.381257920980585,
+      "eval_mse": 0.1923882749511589,
+      "eval_plcc": 0.9271362725922992,
+      "eval_rmse": 0.4386208783803604,
+      "eval_runtime": 193.8144,
+      "eval_samples_per_second": 9.354,
+      "eval_srcc": 0.9124191363393883,
+      "eval_steps_per_second": 9.354,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 3.362459659576416,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1194,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.8072218894958496,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.1172,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.12831401824951172,
+      "eval_loss_ce": 0.11097296372249156,
+      "eval_loss_fidelity": 0.006253569476474416,
+      "eval_loss_kl": 0.22174966832960893,
+      "eval_mae": 0.20121037322253202,
+      "eval_mse": 0.06361294796902603,
+      "eval_plcc": 0.9468404722299074,
+      "eval_rmse": 0.25221607397036777,
+      "eval_runtime": 194.0009,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9270710175393225,
+      "eval_steps_per_second": 9.345,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 1.8970513343811035,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1152,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.407395362854004,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.1089,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.1323900669813156,
+      "eval_loss_ce": 0.10430994520032695,
+      "eval_loss_fidelity": 0.00622050792183799,
+      "eval_loss_kl": 0.4371923788934042,
+      "eval_mae": 0.21929533699896214,
+      "eval_mse": 0.07086994615090463,
+      "eval_plcc": 0.9490074927574884,
+      "eval_rmse": 0.2662140983323472,
+      "eval_runtime": 193.8226,
+      "eval_samples_per_second": 9.354,
+      "eval_srcc": 0.9334829554593803,
+      "eval_steps_per_second": 9.354,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.103539943695068,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.1081,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.8650267124176025,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.1059,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.12093069404363632,
+      "eval_loss_ce": 0.10364307694022029,
+      "eval_loss_fidelity": 0.005853999140231895,
+      "eval_loss_kl": 0.2286723717940294,
+      "eval_mae": 0.18385793126490782,
+      "eval_mse": 0.05349869967082972,
+      "eval_plcc": 0.9540438908778303,
+      "eval_rmse": 0.23129785920070622,
+      "eval_runtime": 194.0204,
+      "eval_samples_per_second": 9.344,
+      "eval_srcc": 0.9344902330605833,
+      "eval_steps_per_second": 9.344,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.2437682151794434,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0976,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.573291778564453,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0989,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12131964415311813,
+      "eval_loss_ce": 0.10263459754093733,
+      "eval_loss_fidelity": 0.004701675696661146,
+      "eval_loss_kl": 0.27966752866980654,
+      "eval_mae": 0.19855049382371265,
+      "eval_mse": 0.06069235738311096,
+      "eval_plcc": 0.95847852622544,
+      "eval_rmse": 0.2463581891943334,
+      "eval_runtime": 194.2798,
+      "eval_samples_per_second": 9.332,
+      "eval_srcc": 0.9461807383546013,
+      "eval_steps_per_second": 9.332,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.7759504318237305,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0972,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.2406930923461914,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0969,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.12333808839321136,
+      "eval_loss_ce": 0.1073055888284193,
+      "eval_loss_fidelity": 0.005524211695686294,
+      "eval_loss_kl": 0.2101658280883385,
+      "eval_mae": 0.17873067449484487,
+      "eval_mse": 0.05457294060711482,
+      "eval_plcc": 0.9496280321348384,
+      "eval_rmse": 0.2336085199797191,
+      "eval_runtime": 193.9022,
+      "eval_samples_per_second": 9.35,
+      "eval_srcc": 0.9369566444197541,
+      "eval_steps_per_second": 9.35,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.002472877502441,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0901,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.2214629650115967,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0896,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.13337895274162292,
+      "eval_loss_ce": 0.1124543054116673,
+      "eval_loss_fidelity": 0.005232234648721019,
+      "eval_loss_kl": 0.3138483108976271,
+      "eval_mae": 0.22865299493386743,
+      "eval_mse": 0.07488270896452447,
+      "eval_plcc": 0.956187979339341,
+      "eval_rmse": 0.27364705181040133,
+      "eval_runtime": 194.2639,
+      "eval_samples_per_second": 9.333,
+      "eval_srcc": 0.9451516040682881,
+      "eval_steps_per_second": 9.333,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.340487480163574,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0857,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 3.1692540645599365,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0928,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.1208026111125946,
+      "eval_loss_ce": 0.10572340061104206,
+      "eval_loss_fidelity": 0.004452917122480373,
+      "eval_loss_kl": 0.21252604568622682,
+      "eval_mae": 0.16965420668255343,
+      "eval_mse": 0.05175068374163564,
+      "eval_plcc": 0.9604690894495514,
+      "eval_rmse": 0.22748776613619387,
+      "eval_runtime": 194.3097,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.9484231224700905,
+      "eval_steps_per_second": 9.33,
+      "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
+}

10301000_scene/03_quality/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf7d848a8c13168f9141e1827d269205a4a2fb4462363014d18b450cf94a020
+size 5777

10301000_scene/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

10301000_scene/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": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

10301000_scene/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90940f213df745a78ad1d7eebed22f4dd81177f95153abbaf717c3ebe786498b
+size 173507576

10301000_scene/final_model/added_tokens.json

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

10301000_scene/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
+  }
+}

10301000_scene/final_model/tokenizer.json

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

10301000_scene/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
+}