Upload folder using huggingface_hub

.gitattributes

@@ -43,3 +43,4 @@ saved_model/**/* 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
+10310800_full_2/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

10310800_full_2/01_scene/checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfc8eeee3c97522b7c939bb4e4f99000d5cbc3e582757ae6d17dc146c80f84e
+size 16318734800

10310800_full_2/01_scene/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13b8739b56bf6eccb0daa70b013df03f9db4cf6ada8a1cd4255ccf44ae2704c
+size 346426383

10310800_full_2/01_scene/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b66e9a873382a15f1132970495fd76a152669d08dfe4779824f18973a5eebb
+size 14645

10310800_full_2/01_scene/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accdf7ab8b63f0e5a6da36129024cc0a3f7993a0f744a91f5ad304c5622f7645
+size 1465

10310800_full_2/01_scene/checkpoint-300/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.032693006098270416,
+  "best_model_checkpoint": "outputs/10310800_full_2/01_scene/checkpoint-300",
+  "epoch": 0.3309431880860452,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 7.177978992462158,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.35,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.5671818256378174,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0545,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.042631760239601135,
+      "eval_runtime": 163.0109,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.2585978507995605,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0406,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.1022469997406006,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0352,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.037419866770505905,
+      "eval_runtime": 162.965,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.4661026000976562,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0399,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.2521960735321045,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0307,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.032693006098270416,
+      "eval_runtime": 162.9477,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 300
+    }
+  ],
+  "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
+}

10310800_full_2/01_scene/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0768ea69794226a402cb0a7997cfd29fdcf70b9c52ae1a8c5b9b98f8f95733
+size 5777

10310800_full_2/01_scene/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bb4102cae2e5d5bb6d52e06620ff2e8a9dacb187da665e8dc60cf4385e5292
+size 16318734800

10310800_full_2/01_scene/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2c623639b85dabcfaa8494d5f03095d71625831c34f0f502064eea30109c72
+size 346426383

10310800_full_2/01_scene/checkpoint-800/rng_state.pth

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

10310800_full_2/01_scene/checkpoint-800/scheduler.pt

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

10310800_full_2/01_scene/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.032693006098270416,
+  "best_model_checkpoint": "outputs/10310800_full_2/01_scene/checkpoint-300",
+  "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": 7.177978992462158,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.35,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 3.5671818256378174,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0545,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.042631760239601135,
+      "eval_runtime": 163.0109,
+      "eval_samples_per_second": 11.122,
+      "eval_steps_per_second": 11.122,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 5.2585978507995605,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0406,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.1022469997406006,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0352,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.037419866770505905,
+      "eval_runtime": 162.965,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.4661026000976562,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0399,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.2521960735321045,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0307,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.032693006098270416,
+      "eval_runtime": 162.9477,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 1.7523733377456665,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0326,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.899393081665039,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0351,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.03346630185842514,
+      "eval_runtime": 162.9714,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 1.61797034740448,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.021,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 4.722104549407959,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.024,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.03793586790561676,
+      "eval_runtime": 162.9282,
+      "eval_samples_per_second": 11.128,
+      "eval_steps_per_second": 11.128,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.6720733642578125,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0265,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 0.5554293990135193,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0248,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.04395307973027229,
+      "eval_runtime": 162.9247,
+      "eval_samples_per_second": 11.128,
+      "eval_steps_per_second": 11.128,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 3.1665568351745605,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0244,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.2360105514526367,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0225,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.03502144664525986,
+      "eval_runtime": 162.9814,
+      "eval_samples_per_second": 11.124,
+      "eval_steps_per_second": 11.124,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.293804407119751,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0216,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.9859259128570557,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.023,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.03428233414888382,
+      "eval_runtime": 162.9451,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "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": 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
+}

10310800_full_2/01_scene/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0768ea69794226a402cb0a7997cfd29fdcf70b9c52ae1a8c5b9b98f8f95733
+size 5777

10310800_full_2/02_distortion/checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ed4a98242090ad6338ffec22ca35638aefccfcabb1e371c2626ffcbdb48eb9
+size 16318734800

10310800_full_2/02_distortion/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3a7df5682c2bb09b5d53a9e5d2afc0ad8ef996f9bc6e49d472798a3ceb1e7b
+size 346426383

10310800_full_2/02_distortion/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751236a777a1c5a9a4be8b3ef90ca78fc8043aa8c2f66a6507d4fed8f2dcee5d
+size 14645

10310800_full_2/02_distortion/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee130504e911bac261d9f7916d873a7269b69b1163abc2e292bae57486300482
+size 1465

10310800_full_2/02_distortion/checkpoint-400/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.045238666236400604,
+  "best_model_checkpoint": "outputs/10310800_full_2/02_distortion/checkpoint-400",
+  "epoch": 0.441257584114727,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 1.7813994884490967,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 1.7572373151779175,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0564,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.05146046727895737,
+      "eval_runtime": 171.4651,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 10.574,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.0402309894561768,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0455,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.0139570236206055,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0423,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.052787549793720245,
+      "eval_runtime": 171.448,
+      "eval_samples_per_second": 10.575,
+      "eval_steps_per_second": 10.575,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.270648241043091,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0431,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.0617592334747314,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.044,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.04839262366294861,
+      "eval_runtime": 171.336,
+      "eval_samples_per_second": 10.582,
+      "eval_steps_per_second": 10.582,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 1.7779405117034912,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0496,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.2150039672851562,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.4837,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.045238666236400604,
+      "eval_runtime": 171.4976,
+      "eval_samples_per_second": 10.572,
+      "eval_steps_per_second": 10.572,
+      "step": 400
+    }
+  ],
+  "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
+}

10310800_full_2/02_distortion/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b240d93d6f32d51d00a1f6f9e4a76f6722c43db19121c2dcb0cded8e2fbc002b
+size 5777

10310800_full_2/02_distortion/checkpoint-900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9f04a25bcddb6c317cd900c2274a84bc006f1aec5609bfe0e39b19386ba592
+size 16318734800

10310800_full_2/02_distortion/checkpoint-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7bfe10ebaa44f3004f5735759b4d8798393e24028bc2332a213a8b9a6e7efcb
+size 346426383

10310800_full_2/02_distortion/checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610ad3fdabe8334cb4e6a039ce5898670c97fd9ef0fad9b83825ef2a2550d6d2
+size 14645

10310800_full_2/02_distortion/checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba14b94ad57c14488b6c0eea4076b6ced0145aa73a3457dc4a1af64f738265bf
+size 1465

10310800_full_2/02_distortion/checkpoint-900/trainer_state.json

@@ -0,0 +1,240 @@
+{
+  "best_metric": 0.045238666236400604,
+  "best_model_checkpoint": "outputs/10310800_full_2/02_distortion/checkpoint-400",
+  "epoch": 0.9928295642581357,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 1.7813994884490967,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 1.7572373151779175,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0564,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.05146046727895737,
+      "eval_runtime": 171.4651,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 10.574,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.0402309894561768,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0455,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.0139570236206055,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0423,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.052787549793720245,
+      "eval_runtime": 171.448,
+      "eval_samples_per_second": 10.575,
+      "eval_steps_per_second": 10.575,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 2.270648241043091,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0431,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.0617592334747314,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.044,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.04839262366294861,
+      "eval_runtime": 171.336,
+      "eval_samples_per_second": 10.582,
+      "eval_steps_per_second": 10.582,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 1.7779405117034912,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0496,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 2.2150039672851562,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.4837,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.045238666236400604,
+      "eval_runtime": 171.4976,
+      "eval_samples_per_second": 10.572,
+      "eval_steps_per_second": 10.572,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 49.60779571533203,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0397,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 1.9584015607833862,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0522,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.047829486429691315,
+      "eval_runtime": 171.3531,
+      "eval_samples_per_second": 10.58,
+      "eval_steps_per_second": 10.58,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.2582831382751465,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0564,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 3.261294364929199,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0413,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.05362292751669884,
+      "eval_runtime": 171.3779,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 1.5613822937011719,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.036,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.5069621801376343,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0526,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.05285946652293205,
+      "eval_runtime": 171.4387,
+      "eval_samples_per_second": 10.575,
+      "eval_steps_per_second": 10.575,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.3860878944396973,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0353,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.9349839687347412,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0376,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.046992383897304535,
+      "eval_runtime": 171.4225,
+      "eval_samples_per_second": 10.576,
+      "eval_steps_per_second": 10.576,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 1.5041863918304443,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0324,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.3868069648742676,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0373,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.04909874498844147,
+      "eval_runtime": 171.3767,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 900
+    }
+  ],
+  "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
+}

10310800_full_2/02_distortion/checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b240d93d6f32d51d00a1f6f9e4a76f6722c43db19121c2dcb0cded8e2fbc002b
+size 5777

10310800_full_2/03_quality/checkpoint-1100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf72a5e549336281e7247b56517c00f6ac96ed5bc10e2b156fbef66ca20c068
+size 16318734800

10310800_full_2/03_quality/checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b98000524edcb7a98124baa0a35762a7bfd71c500d47bf8b06701eae7e2a374
+size 346426383

10310800_full_2/03_quality/checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230fd075531c2aaef0f6399c6b2c67e72c0f74d9ffe1e405070b22662235fff8
+size 14645

10310800_full_2/03_quality/checkpoint-1100/scheduler.pt

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

10310800_full_2/03_quality/checkpoint-1100/trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_metric": 0.11785253882408142,
+  "best_model_checkpoint": "outputs/10310800_full_2/03_quality/checkpoint-600",
+  "epoch": 1.2129067843353558,
+  "eval_steps": 100,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 6.268257141113281,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.339,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 4.841209888458252,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1114,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.14138539135456085,
+      "eval_loss_ce": 0.11264515912568149,
+      "eval_loss_fidelity": 0.006051362207430629,
+      "eval_loss_kl": 0.45377744151144744,
+      "eval_mae": 0.3131371089521851,
+      "eval_mse": 0.132843862129213,
+      "eval_plcc": 0.9455645342231441,
+      "eval_rmse": 0.36447751937425854,
+      "eval_runtime": 194.0205,
+      "eval_samples_per_second": 9.344,
+      "eval_srcc": 0.9272293494295094,
+      "eval_steps_per_second": 9.344,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.8781661987304688,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0904,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 4.140143394470215,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0957,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.14043182134628296,
+      "eval_loss_ce": 0.11825479665782428,
+      "eval_loss_fidelity": 0.00629829395892714,
+      "eval_loss_kl": 0.3175745602621108,
+      "eval_mae": 0.19062688918779125,
+      "eval_mse": 0.058982812199893236,
+      "eval_plcc": 0.9454204779914019,
+      "eval_rmse": 0.24286377292608552,
+      "eval_runtime": 194.0083,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.925677330438757,
+      "eval_steps_per_second": 9.345,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.135570526123047,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1001,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.7002053260803223,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.093,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13470430672168732,
+      "eval_loss_ce": 0.10920124052742766,
+      "eval_loss_fidelity": 0.005924150624974609,
+      "eval_loss_kl": 0.3915783882909596,
+      "eval_mae": 0.20829842784953131,
+      "eval_mse": 0.06552576150848968,
+      "eval_plcc": 0.9514264317734025,
+      "eval_rmse": 0.25598000216518807,
+      "eval_runtime": 194.3147,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.9340198623408366,
+      "eval_steps_per_second": 9.33,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.419497013092041,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0999,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 4.320240020751953,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0961,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.12124761193990707,
+      "eval_loss_ce": 0.10150928602908865,
+      "eval_loss_fidelity": 0.005739238734378377,
+      "eval_loss_kl": 0.2799816729158771,
+      "eval_mae": 0.1937439999262141,
+      "eval_mse": 0.059168337446308256,
+      "eval_plcc": 0.9503784713104557,
+      "eval_rmse": 0.24324542636256957,
+      "eval_runtime": 194.3762,
+      "eval_samples_per_second": 9.327,
+      "eval_srcc": 0.9352994017907516,
+      "eval_steps_per_second": 9.327,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 11.886899948120117,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1021,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.7416083812713623,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1162,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12295699119567871,
+      "eval_loss_ce": 0.10277221105290064,
+      "eval_loss_fidelity": 0.0058750143047661425,
+      "eval_loss_kl": 0.28619532810469656,
+      "eval_mae": 0.20200868199953897,
+      "eval_mse": 0.06226881125142452,
+      "eval_plcc": 0.9514055523015712,
+      "eval_rmse": 0.24953719412429187,
+      "eval_runtime": 193.9937,
+      "eval_samples_per_second": 9.346,
+      "eval_srcc": 0.9409781695204527,
+      "eval_steps_per_second": 9.346,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.6171000003814697,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1016,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 2.8465514183044434,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0995,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.11785253882408142,
+      "eval_loss_ce": 0.1027444403575424,
+      "eval_loss_fidelity": 0.00513713241036482,
+      "eval_loss_kl": 0.19941954326009922,
+      "eval_mae": 0.17366857365620314,
+      "eval_mse": 0.05167644179343168,
+      "eval_plcc": 0.9534767301734327,
+      "eval_rmse": 0.22732452967823705,
+      "eval_runtime": 194.0637,
+      "eval_samples_per_second": 9.342,
+      "eval_srcc": 0.9397346835771005,
+      "eval_steps_per_second": 9.342,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.6561994552612305,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0904,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.306459665298462,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0888,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.13134773075580597,
+      "eval_loss_ce": 0.11364502980236645,
+      "eval_loss_fidelity": 0.0048337146042400775,
+      "eval_loss_kl": 0.25737956746225027,
+      "eval_mae": 0.2402090261604532,
+      "eval_mse": 0.08038102160104073,
+      "eval_plcc": 0.9571566366209564,
+      "eval_rmse": 0.2835154697737687,
+      "eval_runtime": 194.382,
+      "eval_samples_per_second": 9.327,
+      "eval_srcc": 0.9445008971227726,
+      "eval_steps_per_second": 9.327,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.8279614448547363,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0923,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 3.5929665565490723,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0913,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.11928846687078476,
+      "eval_loss_ce": 0.10357130681546235,
+      "eval_loss_fidelity": 0.004376222969159192,
+      "eval_loss_kl": 0.22681862343733505,
+      "eval_mae": 0.17016476021244326,
+      "eval_mse": 0.051565709313688236,
+      "eval_plcc": 0.9603508442047328,
+      "eval_rmse": 0.22708084312351898,
+      "eval_runtime": 194.4962,
+      "eval_samples_per_second": 9.322,
+      "eval_srcc": 0.947012995366062,
+      "eval_steps_per_second": 9.322,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 2.974454641342163,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0864,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 2.601200580596924,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0911,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.1330796331167221,
+      "eval_loss_ce": 0.11148502907710087,
+      "eval_loss_fidelity": 0.004684067335299802,
+      "eval_loss_kl": 0.3382106828762725,
+      "eval_mae": 0.22731412969369358,
+      "eval_mse": 0.07249057701706187,
+      "eval_plcc": 0.9598774651303419,
+      "eval_rmse": 0.2692407417480903,
+      "eval_runtime": 194.0965,
+      "eval_samples_per_second": 9.341,
+      "eval_srcc": 0.9472709234771934,
+      "eval_steps_per_second": 9.341,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 2.4342002868652344,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0742,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 3.188647985458374,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0753,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.1384386271238327,
+      "eval_loss_ce": 0.1232054722472261,
+      "eval_loss_fidelity": 0.004921716786510713,
+      "eval_loss_kl": 0.2062287707841337,
+      "eval_mae": 0.1805235480841391,
+      "eval_mse": 0.049899126195880154,
+      "eval_plcc": 0.959401264689665,
+      "eval_rmse": 0.22338112318609232,
+      "eval_runtime": 194.3452,
+      "eval_samples_per_second": 9.329,
+      "eval_srcc": 0.9437010156053812,
+      "eval_steps_per_second": 9.329,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 8.33721923828125,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0735,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 3.1278600692749023,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0704,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.13220161199569702,
+      "eval_loss_ce": 0.11358401440166171,
+      "eval_loss_fidelity": 0.004911785327461939,
+      "eval_loss_kl": 0.2741162578826508,
+      "eval_mae": 0.18235451354549131,
+      "eval_mse": 0.05046312097976978,
+      "eval_plcc": 0.9604004334309124,
+      "eval_rmse": 0.2246399808132332,
+      "eval_runtime": 194.5141,
+      "eval_samples_per_second": 9.321,
+      "eval_srcc": 0.9469729881448531,
+      "eval_steps_per_second": 9.321,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2718,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

10310800_full_2/03_quality/checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b208c81f047c276f392a1ce4bf6dcd9414dee4d08adb8b40ae69ce14eeefd2b
+size 5777

10310800_full_2/03_quality/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e072b7c7fc052b0d5574a365f8076c00b708b3cc19ca3bb82687564c88c0f09
+size 16318734800

10310800_full_2/03_quality/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5d30812533e6f3392c19276dfb7b046a298730367410045bbb4c526ede3d96
+size 346426383

10310800_full_2/03_quality/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f498f6052bf626d5298871544c4320aad1cf35bd6edfc2ff388e1b1913c6faf7
+size 14645

10310800_full_2/03_quality/checkpoint-600/scheduler.pt

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

10310800_full_2/03_quality/checkpoint-600/trainer_state.json

@@ -0,0 +1,222 @@
+{
+  "best_metric": 0.11785253882408142,
+  "best_model_checkpoint": "outputs/10310800_full_2/03_quality/checkpoint-600",
+  "epoch": 0.6618863761720905,
+  "eval_steps": 100,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 6.268257141113281,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.339,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 4.841209888458252,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1114,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.14138539135456085,
+      "eval_loss_ce": 0.11264515912568149,
+      "eval_loss_fidelity": 0.006051362207430629,
+      "eval_loss_kl": 0.45377744151144744,
+      "eval_mae": 0.3131371089521851,
+      "eval_mse": 0.132843862129213,
+      "eval_plcc": 0.9455645342231441,
+      "eval_rmse": 0.36447751937425854,
+      "eval_runtime": 194.0205,
+      "eval_samples_per_second": 9.344,
+      "eval_srcc": 0.9272293494295094,
+      "eval_steps_per_second": 9.344,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.8781661987304688,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0904,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 4.140143394470215,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0957,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.14043182134628296,
+      "eval_loss_ce": 0.11825479665782428,
+      "eval_loss_fidelity": 0.00629829395892714,
+      "eval_loss_kl": 0.3175745602621108,
+      "eval_mae": 0.19062688918779125,
+      "eval_mse": 0.058982812199893236,
+      "eval_plcc": 0.9454204779914019,
+      "eval_rmse": 0.24286377292608552,
+      "eval_runtime": 194.0083,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.925677330438757,
+      "eval_steps_per_second": 9.345,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.135570526123047,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.1001,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.7002053260803223,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.093,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13470430672168732,
+      "eval_loss_ce": 0.10920124052742766,
+      "eval_loss_fidelity": 0.005924150624974609,
+      "eval_loss_kl": 0.3915783882909596,
+      "eval_mae": 0.20829842784953131,
+      "eval_mse": 0.06552576150848968,
+      "eval_plcc": 0.9514264317734025,
+      "eval_rmse": 0.25598000216518807,
+      "eval_runtime": 194.3147,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.9340198623408366,
+      "eval_steps_per_second": 9.33,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 4.419497013092041,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0999,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 4.320240020751953,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0961,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.12124761193990707,
+      "eval_loss_ce": 0.10150928602908865,
+      "eval_loss_fidelity": 0.005739238734378377,
+      "eval_loss_kl": 0.2799816729158771,
+      "eval_mae": 0.1937439999262141,
+      "eval_mse": 0.059168337446308256,
+      "eval_plcc": 0.9503784713104557,
+      "eval_rmse": 0.24324542636256957,
+      "eval_runtime": 194.3762,
+      "eval_samples_per_second": 9.327,
+      "eval_srcc": 0.9352994017907516,
+      "eval_steps_per_second": 9.327,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 11.886899948120117,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.1021,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.7416083812713623,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.1162,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.12295699119567871,
+      "eval_loss_ce": 0.10277221105290064,
+      "eval_loss_fidelity": 0.0058750143047661425,
+      "eval_loss_kl": 0.28619532810469656,
+      "eval_mae": 0.20200868199953897,
+      "eval_mse": 0.06226881125142452,
+      "eval_plcc": 0.9514055523015712,
+      "eval_rmse": 0.24953719412429187,
+      "eval_runtime": 193.9937,
+      "eval_samples_per_second": 9.346,
+      "eval_srcc": 0.9409781695204527,
+      "eval_steps_per_second": 9.346,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 3.6171000003814697,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.1016,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 2.8465514183044434,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0995,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.11785253882408142,
+      "eval_loss_ce": 0.1027444403575424,
+      "eval_loss_fidelity": 0.00513713241036482,
+      "eval_loss_kl": 0.19941954326009922,
+      "eval_mae": 0.17366857365620314,
+      "eval_mse": 0.05167644179343168,
+      "eval_plcc": 0.9534767301734327,
+      "eval_rmse": 0.22732452967823705,
+      "eval_runtime": 194.0637,
+      "eval_samples_per_second": 9.342,
+      "eval_srcc": 0.9397346835771005,
+      "eval_steps_per_second": 9.342,
+      "step": 600
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2718,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

10310800_full_2/03_quality/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b208c81f047c276f392a1ce4bf6dcd9414dee4d08adb8b40ae69ce14eeefd2b
+size 5777

10310800_full_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

10310800_full_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": [
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

10310800_full_2/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0491555df823f7a1821ab41a4672cd5e825d88a156169946f285794b4609c3a6
+size 173507576

10310800_full_2/final_model/added_tokens.json

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

10310800_full_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
+  }
+}

10310800_full_2/final_model/tokenizer.json

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

10310800_full_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
+}