Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 10301000_scene/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 10301400_distortion/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
 10301400_distortion/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+10302000_full/final_model/eval_scatter_plot.png filter=lfs diff=lfs merge=lfs -text
+10302000_full/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

10302000_full/01_scene/checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7181ba21f839a62062f55cf5b2b17cb1c74c933baef9178576c5012cbe9efdc9
+size 16318734800

10302000_full/01_scene/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd57d3025cda868cc8c1ffa02dd2669f9f56904962571bf32891c50fdc9ec593
+size 346426383

10302000_full/01_scene/checkpoint-300/rng_state.pth

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

10302000_full/01_scene/checkpoint-300/scheduler.pt

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

10302000_full/01_scene/checkpoint-300/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.031441543251276016,
+  "best_model_checkpoint": "outputs/10302000_full/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": 7.211073875427246,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.35,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 4.013247013092041,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0542,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.04501630738377571,
+      "eval_runtime": 162.973,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 4.819284915924072,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0401,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.392460823059082,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0353,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.04001997783780098,
+      "eval_runtime": 162.9586,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.6923370361328125,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0374,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.7600138187408447,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0314,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.031441543251276016,
+      "eval_runtime": 162.945,
+      "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
+}

10302000_full/01_scene/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a94d7aef7547b994c14813867db9a32341e1e788c8f9372ea4a31427e99c8aa
+size 5777

10302000_full/01_scene/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a534ad1357c07f967134a223e453cae1df9525963e3592eebc4b9243d81c932
+size 16318734800

10302000_full/01_scene/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccb727b6739aeee4da6dc4c3aec3838aedd6260e4765b96911554f70f338069
+size 346426383

10302000_full/01_scene/checkpoint-800/rng_state.pth

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

10302000_full/01_scene/checkpoint-800/scheduler.pt

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

10302000_full/01_scene/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.031441543251276016,
+  "best_model_checkpoint": "outputs/10302000_full/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": 7.211073875427246,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.35,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 4.013247013092041,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0542,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.04501630738377571,
+      "eval_runtime": 162.973,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 4.819284915924072,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0401,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.392460823059082,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0353,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.04001997783780098,
+      "eval_runtime": 162.9586,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 3.6923370361328125,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0374,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.7600138187408447,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0314,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.031441543251276016,
+      "eval_runtime": 162.945,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 2.1462252140045166,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0325,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 4.849669933319092,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0367,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.04374614357948303,
+      "eval_runtime": 162.9597,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 3.1866295337677,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0827,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 3.378995180130005,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0953,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.035981640219688416,
+      "eval_runtime": 162.9465,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 11.126,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.2808432579040527,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.032,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 0.9201453924179077,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.028,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.03953522443771362,
+      "eval_runtime": 162.9708,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 11.125,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 3.543931245803833,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.0259,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.209773302078247,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0281,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.03907668963074684,
+      "eval_runtime": 162.9784,
+      "eval_samples_per_second": 11.124,
+      "eval_steps_per_second": 11.124,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.4935171604156494,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0242,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 2.3324661254882812,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0252,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.0319170244038105,
+      "eval_runtime": 162.9522,
+      "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
+}

10302000_full/01_scene/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a94d7aef7547b994c14813867db9a32341e1e788c8f9372ea4a31427e99c8aa
+size 5777

10302000_full/02_distortion/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566612776aa0b626e9c04c402e05b9cf783e6590d2a172989720dc9eea7f50b6
+size 16318734800

10302000_full/02_distortion/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455fa3642b03193cbf950c21bacbce30e3df99cb2cb88f200fd4c097367b5996
+size 346426383

10302000_full/02_distortion/checkpoint-1300/rng_state.pth

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

10302000_full/02_distortion/checkpoint-1300/scheduler.pt

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

10302000_full/02_distortion/checkpoint-1300/trainer_state.json

@@ -0,0 +1,328 @@
+{
+  "best_metric": 0.04455012083053589,
+  "best_model_checkpoint": "outputs/10302000_full/02_distortion/checkpoint-800",
+  "epoch": 1.4335355763927193,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 1.3377962112426758,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.1294,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 1.6523388624191284,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0556,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.051050279289484024,
+      "eval_runtime": 171.4743,
+      "eval_samples_per_second": 10.573,
+      "eval_steps_per_second": 10.573,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.9036033153533936,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0458,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.11191725730896,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0421,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.051304373890161514,
+      "eval_runtime": 171.3877,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 1.5565705299377441,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0437,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.7734652757644653,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0447,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.05800703167915344,
+      "eval_runtime": 171.377,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 2.717177152633667,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0513,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 1.9755767583847046,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0461,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.04763505980372429,
+      "eval_runtime": 171.5889,
+      "eval_samples_per_second": 10.566,
+      "eval_steps_per_second": 10.566,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 2.066533088684082,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0403,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 1.5352795124053955,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.04639120027422905,
+      "eval_runtime": 171.3745,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.086174964904785,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0433,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 1.7900938987731934,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0402,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.048071522265672684,
+      "eval_runtime": 171.3891,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 309.98126220703125,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.037,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.4379602670669556,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0345,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.05097845196723938,
+      "eval_runtime": 171.3896,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.1667776107788086,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0347,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.551637887954712,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0375,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.04455012083053589,
+      "eval_runtime": 171.4596,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 10.574,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 1.5344250202178955,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.0325,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 1.479475736618042,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0353,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.04886327311396599,
+      "eval_runtime": 171.4442,
+      "eval_samples_per_second": 10.575,
+      "eval_steps_per_second": 10.575,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 1.4682869911193848,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0278,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 3.0045366287231445,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.0293,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.0576724112033844,
+      "eval_runtime": 171.5105,
+      "eval_samples_per_second": 10.571,
+      "eval_steps_per_second": 10.571,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 2.6942219734191895,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0258,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 1.9268912076950073,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.027,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.05314527824521065,
+      "eval_runtime": 171.5,
+      "eval_samples_per_second": 10.571,
+      "eval_steps_per_second": 10.571,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 1.4602032899856567,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0268,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 2.132002115249634,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.0268,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.04979213699698448,
+      "eval_runtime": 171.4966,
+      "eval_samples_per_second": 10.572,
+      "eval_steps_per_second": 10.572,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 1.543311357498169,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0237,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 2.9787299633026123,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0241,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.052592601627111435,
+      "eval_runtime": 171.5002,
+      "eval_samples_per_second": 10.571,
+      "eval_steps_per_second": 10.571,
+      "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
+}

10302000_full/02_distortion/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09eb6beb0ab9417585b65aa2ceb3d21e58e0b3e1253b648012f50be2e59900a5
+size 5777

10302000_full/02_distortion/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10114598e05a024c2b6d415c0f4c354e5dfe961a4e6698dc4aa2ba7d88e2e24c
+size 16318734800

10302000_full/02_distortion/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6360f4a51ed2f928d6abfe4e0e20697b406bc2280f1288ace59233b77f6a7611
+size 346426383

10302000_full/02_distortion/checkpoint-800/rng_state.pth

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

10302000_full/02_distortion/checkpoint-800/scheduler.pt

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

10302000_full/02_distortion/checkpoint-800/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.04455012083053589,
+  "best_model_checkpoint": "outputs/10302000_full/02_distortion/checkpoint-800",
+  "epoch": 0.882515168229454,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05515719801434087,
+      "grad_norm": 1.3377962112426758,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.1294,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 1.6523388624191284,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.0556,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.051050279289484024,
+      "eval_runtime": 171.4743,
+      "eval_samples_per_second": 10.573,
+      "eval_steps_per_second": 10.573,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 2.9036033153533936,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.0458,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 2.11191725730896,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.0421,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.051304373890161514,
+      "eval_runtime": 171.3877,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 1.5565705299377441,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0437,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 1.7734652757644653,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0447,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.05800703167915344,
+      "eval_runtime": 171.377,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 2.717177152633667,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0513,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 1.9755767583847046,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0461,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.04763505980372429,
+      "eval_runtime": 171.5889,
+      "eval_samples_per_second": 10.566,
+      "eval_steps_per_second": 10.566,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 2.066533088684082,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0403,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 1.5352795124053955,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.04639120027422905,
+      "eval_runtime": 171.3745,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 10.579,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 2.086174964904785,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0433,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 1.7900938987731934,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0402,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.048071522265672684,
+      "eval_runtime": 171.3891,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 309.98126220703125,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.037,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 1.4379602670669556,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0345,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.05097845196723938,
+      "eval_runtime": 171.3896,
+      "eval_samples_per_second": 10.578,
+      "eval_steps_per_second": 10.578,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 2.1667776107788086,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0347,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 1.551637887954712,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0375,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.04455012083053589,
+      "eval_runtime": 171.4596,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 10.574,
+      "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
+}

10302000_full/02_distortion/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09eb6beb0ab9417585b65aa2ceb3d21e58e0b3e1253b648012f50be2e59900a5
+size 5777

10302000_full/03_quality/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5c23b096c69950fcf39c579ac327874e1073613538d3c07fa03382c3025781
+size 16318734800

10302000_full/03_quality/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8df029566afa22ed48773858ed669c2b4ec667cb7a67c5f042e2e453fccaaf
+size 346426383

10302000_full/03_quality/checkpoint-1300/rng_state.pth

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

10302000_full/03_quality/checkpoint-1300/scheduler.pt

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

10302000_full/03_quality/checkpoint-1300/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": 0.1264975368976593,
+  "best_model_checkpoint": "outputs/10302000_full/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": 5.016786575317383,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3705,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 5.948491096496582,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1078,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.13704171776771545,
+      "eval_loss_ce": 0.1113771149417066,
+      "eval_loss_fidelity": 0.007213531817390208,
+      "eval_loss_kl": 0.36902147792053697,
+      "eval_mae": 0.30157978509712535,
+      "eval_mse": 0.12427899865513392,
+      "eval_plcc": 0.937119822608221,
+      "eval_rmse": 0.3525322661191936,
+      "eval_runtime": 193.6718,
+      "eval_samples_per_second": 9.361,
+      "eval_srcc": 0.9300393181858984,
+      "eval_steps_per_second": 9.361,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 15.751655578613281,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1354,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.5405540466308594,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.099,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.13450700044631958,
+      "eval_loss_ce": 0.11631542408065249,
+      "eval_loss_fidelity": 0.0062996593343917955,
+      "eval_loss_kl": 0.2378383321852988,
+      "eval_mae": 0.17954863097479642,
+      "eval_mse": 0.05381856826433036,
+      "eval_plcc": 0.9456857252789469,
+      "eval_rmse": 0.23198829337777016,
+      "eval_runtime": 193.9476,
+      "eval_samples_per_second": 9.348,
+      "eval_srcc": 0.923889012828261,
+      "eval_steps_per_second": 9.348,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.451136589050293,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0979,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.2216923236846924,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0888,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13621202111244202,
+      "eval_loss_ce": 0.11152292225536593,
+      "eval_loss_fidelity": 0.006185017513692733,
+      "eval_loss_kl": 0.37008158095752214,
+      "eval_mae": 0.2274023151765919,
+      "eval_mse": 0.07837657580673445,
+      "eval_plcc": 0.949336914105721,
+      "eval_rmse": 0.2799581679585978,
+      "eval_runtime": 194.3501,
+      "eval_samples_per_second": 9.329,
+      "eval_srcc": 0.9321839980089605,
+      "eval_steps_per_second": 9.329,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 5.278799533843994,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0964,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 5.467691898345947,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0878,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.13462145626544952,
+      "eval_loss_ce": 0.11323300575538525,
+      "eval_loss_fidelity": 0.005899251784552176,
+      "eval_loss_kl": 0.3097839682423076,
+      "eval_mae": 0.20564421533025962,
+      "eval_mse": 0.06551240013957672,
+      "eval_plcc": 0.9475868241161464,
+      "eval_rmse": 0.2559539023722372,
+      "eval_runtime": 194.3102,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.930247646679494,
+      "eval_steps_per_second": 9.33,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 4.230099678039551,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0857,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.8542516231536865,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0812,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.13305522501468658,
+      "eval_loss_ce": 0.1118904996408541,
+      "eval_loss_fidelity": 0.004883602631144263,
+      "eval_loss_kl": 0.3256222899783335,
+      "eval_mae": 0.2171886075088745,
+      "eval_mse": 0.06838496862929523,
+      "eval_plcc": 0.9550205287617668,
+      "eval_rmse": 0.26150519809230416,
+      "eval_runtime": 194.0084,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9398547146650336,
+      "eval_steps_per_second": 9.345,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.689825057983398,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0864,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 5.880340099334717,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0855,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.13849912583827972,
+      "eval_loss_ce": 0.12432220729321686,
+      "eval_loss_fidelity": 0.005712794197739451,
+      "eval_loss_kl": 0.16928249481249696,
+      "eval_mae": 0.17003036939302205,
+      "eval_mse": 0.049201071172228016,
+      "eval_plcc": 0.9530812462843681,
+      "eval_rmse": 0.22181314472372465,
+      "eval_runtime": 194.0394,
+      "eval_samples_per_second": 9.343,
+      "eval_srcc": 0.9404855441911246,
+      "eval_steps_per_second": 9.343,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.565411567687988,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.079,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.659329414367676,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0775,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.1500832587480545,
+      "eval_loss_ce": 0.1271633744338436,
+      "eval_loss_fidelity": 0.005004158400919163,
+      "eval_loss_kl": 0.3583144665738363,
+      "eval_mae": 0.24742476524599205,
+      "eval_mse": 0.08547339348227857,
+      "eval_plcc": 0.9551442112371081,
+      "eval_rmse": 0.2923583306189146,
+      "eval_runtime": 193.6922,
+      "eval_samples_per_second": 9.36,
+      "eval_srcc": 0.9390260963502546,
+      "eval_steps_per_second": 9.36,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.306400775909424,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0748,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 5.885075569152832,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0799,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.1264975368976593,
+      "eval_loss_ce": 0.10881793243174584,
+      "eval_loss_fidelity": 0.004938206646989665,
+      "eval_loss_kl": 0.25482803636363577,
+      "eval_mae": 0.16690754581405126,
+      "eval_mse": 0.048057996531864385,
+      "eval_plcc": 0.9567099432782478,
+      "eval_rmse": 0.2192213414151651,
+      "eval_runtime": 194.2536,
+      "eval_samples_per_second": 9.333,
+      "eval_srcc": 0.9417936374158725,
+      "eval_steps_per_second": 9.333,
+      "step": 800
+    },
+    {
+      "epoch": 0.9376723662437948,
+      "grad_norm": 3.1301374435424805,
+      "learning_rate": 0.00016095490627048551,
+      "loss": 0.1083,
+      "step": 850
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "grad_norm": 3.414059638977051,
+      "learning_rate": 0.0001561255093964205,
+      "loss": 0.0853,
+      "step": 900
+    },
+    {
+      "epoch": 0.9928295642581357,
+      "eval_loss": 0.13225458562374115,
+      "eval_loss_ce": 0.11228324533725272,
+      "eval_loss_fidelity": 0.004915323454149014,
+      "eval_loss_kl": 0.3011201763298554,
+      "eval_mae": 0.22013330643701737,
+      "eval_mse": 0.06908894754687456,
+      "eval_plcc": 0.9574026281380463,
+      "eval_rmse": 0.262847764964579,
+      "eval_runtime": 194.1806,
+      "eval_samples_per_second": 9.337,
+      "eval_srcc": 0.9427551329633977,
+      "eval_steps_per_second": 9.337,
+      "step": 900
+    },
+    {
+      "epoch": 1.0474351902923331,
+      "grad_norm": 1.631306767463684,
+      "learning_rate": 0.0001510968706016788,
+      "loss": 0.0701,
+      "step": 950
+    },
+    {
+      "epoch": 1.102592388306674,
+      "grad_norm": 4.560144901275635,
+      "learning_rate": 0.00014588684122805897,
+      "loss": 0.1439,
+      "step": 1000
+    },
+    {
+      "epoch": 1.102592388306674,
+      "eval_loss": 0.14723722636699677,
+      "eval_loss_ce": 0.13140751211762725,
+      "eval_loss_fidelity": 0.005400512868111365,
+      "eval_loss_kl": 0.20858417000155124,
+      "eval_mae": 0.18222331165675623,
+      "eval_mse": 0.05252082752936385,
+      "eval_plcc": 0.9573155466629986,
+      "eval_rmse": 0.22917422963623954,
+      "eval_runtime": 194.0271,
+      "eval_samples_per_second": 9.344,
+      "eval_srcc": 0.9420141593143311,
+      "eval_steps_per_second": 9.344,
+      "step": 1000
+    },
+    {
+      "epoch": 1.157749586321015,
+      "grad_norm": 2.5360968112945557,
+      "learning_rate": 0.00014051391654215802,
+      "loss": 0.0682,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "grad_norm": 2.7947652339935303,
+      "learning_rate": 0.0001349971700783738,
+      "loss": 0.0663,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2129067843353558,
+      "eval_loss": 0.14391076564788818,
+      "eval_loss_ce": 0.12244595150615849,
+      "eval_loss_fidelity": 0.005122330334341648,
+      "eval_loss_kl": 0.3268497886338569,
+      "eval_mae": 0.21778717332956743,
+      "eval_mse": 0.06785969315954295,
+      "eval_plcc": 0.9576596915580221,
+      "eval_rmse": 0.26049893120614326,
+      "eval_runtime": 194.1409,
+      "eval_samples_per_second": 9.339,
+      "eval_srcc": 0.9433267891697489,
+      "eval_steps_per_second": 9.339,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2680639823496966,
+      "grad_norm": 4.478550434112549,
+      "learning_rate": 0.00012935618592909418,
+      "loss": 0.0675,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "grad_norm": 1.6398779153823853,
+      "learning_rate": 0.0001236109892224381,
+      "loss": 0.063,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3232211803640375,
+      "eval_loss": 0.13683147728443146,
+      "eval_loss_ce": 0.11823078792416879,
+      "eval_loss_fidelity": 0.004846085331225367,
+      "eval_loss_kl": 0.27509208383954037,
+      "eval_mae": 0.19626730677178073,
+      "eval_mse": 0.056596288147406505,
+      "eval_plcc": 0.9576392029983575,
+      "eval_rmse": 0.23789974389941346,
+      "eval_runtime": 194.1932,
+      "eval_samples_per_second": 9.336,
+      "eval_srcc": 0.9441463714952719,
+      "eval_steps_per_second": 9.336,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3783783783783785,
+      "grad_norm": 1.8871359825134277,
+      "learning_rate": 0.000117781975034349,
+      "loss": 0.0647,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "grad_norm": 4.287084579467773,
+      "learning_rate": 0.00011188983598739675,
+      "loss": 0.0622,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4335355763927193,
+      "eval_loss": 0.14778631925582886,
+      "eval_loss_ce": 0.1280554513433117,
+      "eval_loss_fidelity": 0.0048560530920212465,
+      "eval_loss_kl": 0.29749625905427696,
+      "eval_mae": 0.1903329896321957,
+      "eval_mse": 0.06137638311756013,
+      "eval_plcc": 0.9574996097590314,
+      "eval_rmse": 0.24774257429347935,
+      "eval_runtime": 194.1157,
+      "eval_samples_per_second": 9.34,
+      "eval_srcc": 0.9429579000073733,
+      "eval_steps_per_second": 9.34,
+      "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
+}

10302000_full/03_quality/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4fb071fdc96cc5f5acb1a4f06afee253beb396316fb8e97d544881db9369c36
+size 5777

10302000_full/03_quality/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ad531354be49e472f3a293249ce03e39d7b3d8b89b09c5f9792966f08b6e3b
+size 16318734800

10302000_full/03_quality/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864eda192b960e186ed703617b420e8b3e9854fb6d29e275012ce22c5d14788a
+size 346426383

10302000_full/03_quality/checkpoint-800/rng_state.pth

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

10302000_full/03_quality/checkpoint-800/scheduler.pt

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

10302000_full/03_quality/checkpoint-800/trainer_state.json

@@ -0,0 +1,282 @@
+{
+  "best_metric": 0.1264975368976593,
+  "best_model_checkpoint": "outputs/10302000_full/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": 5.016786575317383,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.3705,
+      "step": 50
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "grad_norm": 5.948491096496582,
+      "learning_rate": 0.0001999769904941157,
+      "loss": 0.1078,
+      "step": 100
+    },
+    {
+      "epoch": 0.11031439602868175,
+      "eval_loss": 0.13704171776771545,
+      "eval_loss_ce": 0.1113771149417066,
+      "eval_loss_fidelity": 0.007213531817390208,
+      "eval_loss_kl": 0.36902147792053697,
+      "eval_mae": 0.30157978509712535,
+      "eval_mse": 0.12427899865513392,
+      "eval_plcc": 0.937119822608221,
+      "eval_rmse": 0.3525322661191936,
+      "eval_runtime": 193.6718,
+      "eval_samples_per_second": 9.361,
+      "eval_srcc": 0.9300393181858984,
+      "eval_steps_per_second": 9.361,
+      "step": 100
+    },
+    {
+      "epoch": 0.1654715940430226,
+      "grad_norm": 15.751655578613281,
+      "learning_rate": 0.00019967178452785585,
+      "loss": 0.1354,
+      "step": 150
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 3.5405540466308594,
+      "learning_rate": 0.0001990127501865814,
+      "loss": 0.099,
+      "step": 200
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 0.13450700044631958,
+      "eval_loss_ce": 0.11631542408065249,
+      "eval_loss_fidelity": 0.0062996593343917955,
+      "eval_loss_kl": 0.2378383321852988,
+      "eval_mae": 0.17954863097479642,
+      "eval_mse": 0.05381856826433036,
+      "eval_plcc": 0.9456857252789469,
+      "eval_rmse": 0.23198829337777016,
+      "eval_runtime": 193.9476,
+      "eval_samples_per_second": 9.348,
+      "eval_srcc": 0.923889012828261,
+      "eval_steps_per_second": 9.348,
+      "step": 200
+    },
+    {
+      "epoch": 0.27578599007170435,
+      "grad_norm": 4.451136589050293,
+      "learning_rate": 0.0001980022269994896,
+      "loss": 0.0979,
+      "step": 250
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "grad_norm": 2.2216923236846924,
+      "learning_rate": 0.00019664380225839926,
+      "loss": 0.0888,
+      "step": 300
+    },
+    {
+      "epoch": 0.3309431880860452,
+      "eval_loss": 0.13621202111244202,
+      "eval_loss_ce": 0.11152292225536593,
+      "eval_loss_fidelity": 0.006185017513692733,
+      "eval_loss_kl": 0.37008158095752214,
+      "eval_mae": 0.2274023151765919,
+      "eval_mse": 0.07837657580673445,
+      "eval_plcc": 0.949336914105721,
+      "eval_rmse": 0.2799581679585978,
+      "eval_runtime": 194.3501,
+      "eval_samples_per_second": 9.329,
+      "eval_srcc": 0.9321839980089605,
+      "eval_steps_per_second": 9.329,
+      "step": 300
+    },
+    {
+      "epoch": 0.3861003861003861,
+      "grad_norm": 5.278799533843994,
+      "learning_rate": 0.00019494229828309726,
+      "loss": 0.0964,
+      "step": 350
+    },
+    {
+      "epoch": 0.441257584114727,
+      "grad_norm": 5.467691898345947,
+      "learning_rate": 0.0001929037553024158,
+      "loss": 0.0878,
+      "step": 400
+    },
+    {
+      "epoch": 0.441257584114727,
+      "eval_loss": 0.13462145626544952,
+      "eval_loss_ce": 0.11323300575538525,
+      "eval_loss_fidelity": 0.005899251784552176,
+      "eval_loss_kl": 0.3097839682423076,
+      "eval_mae": 0.20564421533025962,
+      "eval_mse": 0.06551240013957672,
+      "eval_plcc": 0.9475868241161464,
+      "eval_rmse": 0.2559539023722372,
+      "eval_runtime": 194.3102,
+      "eval_samples_per_second": 9.33,
+      "eval_srcc": 0.930247646679494,
+      "eval_steps_per_second": 9.33,
+      "step": 400
+    },
+    {
+      "epoch": 0.49641478212906787,
+      "grad_norm": 4.230099678039551,
+      "learning_rate": 0.00019053541001181153,
+      "loss": 0.0857,
+      "step": 450
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "grad_norm": 2.8542516231536865,
+      "learning_rate": 0.00018784566988356584,
+      "loss": 0.0812,
+      "step": 500
+    },
+    {
+      "epoch": 0.5515719801434087,
+      "eval_loss": 0.13305522501468658,
+      "eval_loss_ce": 0.1118904996408541,
+      "eval_loss_fidelity": 0.004883602631144263,
+      "eval_loss_kl": 0.3256222899783335,
+      "eval_mae": 0.2171886075088745,
+      "eval_mse": 0.06838496862929523,
+      "eval_plcc": 0.9550205287617668,
+      "eval_rmse": 0.26150519809230416,
+      "eval_runtime": 194.0084,
+      "eval_samples_per_second": 9.345,
+      "eval_srcc": 0.9398547146650336,
+      "eval_steps_per_second": 9.345,
+      "step": 500
+    },
+    {
+      "epoch": 0.6067291781577496,
+      "grad_norm": 4.689825057983398,
+      "learning_rate": 0.00018484408332080296,
+      "loss": 0.0864,
+      "step": 550
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "grad_norm": 5.880340099334717,
+      "learning_rate": 0.00018154130576127794,
+      "loss": 0.0855,
+      "step": 600
+    },
+    {
+      "epoch": 0.6618863761720905,
+      "eval_loss": 0.13849912583827972,
+      "eval_loss_ce": 0.12432220729321686,
+      "eval_loss_fidelity": 0.005712794197739451,
+      "eval_loss_kl": 0.16928249481249696,
+      "eval_mae": 0.17003036939302205,
+      "eval_mse": 0.049201071172228016,
+      "eval_plcc": 0.9530812462843681,
+      "eval_rmse": 0.22181314472372465,
+      "eval_runtime": 194.0394,
+      "eval_samples_per_second": 9.343,
+      "eval_srcc": 0.9404855441911246,
+      "eval_steps_per_second": 9.343,
+      "step": 600
+    },
+    {
+      "epoch": 0.7170435741864313,
+      "grad_norm": 4.565411567687988,
+      "learning_rate": 0.00017794906185126307,
+      "loss": 0.079,
+      "step": 650
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "grad_norm": 2.659329414367676,
+      "learning_rate": 0.0001740801038238137,
+      "loss": 0.0775,
+      "step": 700
+    },
+    {
+      "epoch": 0.7722007722007722,
+      "eval_loss": 0.1500832587480545,
+      "eval_loss_ce": 0.1271633744338436,
+      "eval_loss_fidelity": 0.005004158400919163,
+      "eval_loss_kl": 0.3583144665738363,
+      "eval_mae": 0.24742476524599205,
+      "eval_mse": 0.08547339348227857,
+      "eval_plcc": 0.9551442112371081,
+      "eval_rmse": 0.2923583306189146,
+      "eval_runtime": 193.6922,
+      "eval_samples_per_second": 9.36,
+      "eval_srcc": 0.9390260963502546,
+      "eval_steps_per_second": 9.36,
+      "step": 700
+    },
+    {
+      "epoch": 0.827357970215113,
+      "grad_norm": 3.306400775909424,
+      "learning_rate": 0.00016994816622916724,
+      "loss": 0.0748,
+      "step": 750
+    },
+    {
+      "epoch": 0.882515168229454,
+      "grad_norm": 5.885075569152832,
+      "learning_rate": 0.0001655679171779801,
+      "loss": 0.0799,
+      "step": 800
+    },
+    {
+      "epoch": 0.882515168229454,
+      "eval_loss": 0.1264975368976593,
+      "eval_loss_ce": 0.10881793243174584,
+      "eval_loss_fidelity": 0.004938206646989665,
+      "eval_loss_kl": 0.25482803636363577,
+      "eval_mae": 0.16690754581405126,
+      "eval_mse": 0.048057996531864385,
+      "eval_plcc": 0.9567099432782478,
+      "eval_rmse": 0.2192213414151651,
+      "eval_runtime": 194.2536,
+      "eval_samples_per_second": 9.333,
+      "eval_srcc": 0.9417936374158725,
+      "eval_steps_per_second": 9.333,
+      "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
+}

10302000_full/03_quality/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4fb071fdc96cc5f5acb1a4f06afee253beb396316fb8e97d544881db9369c36
+size 5777

10302000_full/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

10302000_full/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": [
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

10302000_full/final_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ac9451f4c86cbbf1cdf84f4393e61b5643971c773d39e290f5ae8514b4e0fd
+size 173507576

10302000_full/final_model/added_tokens.json

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

10302000_full/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
+  }
+}

10302000_full/final_model/tokenizer.json

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

10302000_full/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
+}