End of training

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+interpret_models/attributes_falcon-7b-instruct-FT-LoRA-8bit-test1_0it.json filter=lfs diff=lfs merge=lfs -text
+interpret_models/attributes_falcon-7b-instruct-RL-LoRA-8bit-test1_0it.json filter=lfs diff=lfs merge=lfs -text
+interpret_models/attributes_falcon-7b-instruct_0it.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
+tags:
+- generated_from_trainer
+model-index:
+- name: storage_cache
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# storage_cache
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9586
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0447        | 1.16  | 25   | 2.0142          |
+| 1.84          | 2.32  | 50   | 1.9586          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.0.0+cu117
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b609b6dc323e145ec8b4f2953306234c1ef9ea5692801e3c685a418b0016b3ee
+size 109097933

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43802f64e1c944b420474cee47f34e454d4778114d7209d698caed3f0a9972f
+size 109069176

checkpoints/fine_tune/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

checkpoints/fine_tune/.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

checkpoints/fine_tune/README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: falcon-7b-instruct-FT-LoRA-8bit-test1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# falcon-7b-instruct-FT-LoRA-8bit-test1
+
+This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9608
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5166        | 0.85  | 200  | 1.5187          |
+| 1.0449        | 1.71  | 400  | 1.1572          |
+| 0.6828        | 2.56  | 600  | 0.9608          |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.0
+- Tokenizers 0.13.3

checkpoints/fine_tune/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoints/fine_tune/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f19210f88fd1de9a6c373316ea651765081fea7898ae7c9bb7c9b463a6f2f8f
+size 261189453

checkpoints/fine_tune/checkpoint-150/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoints/fine_tune/checkpoint-150/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159e70fc13549233f169472e4163876a8e8063d560a9e70481ccbfd17597c8bd
+size 261189453

checkpoints/fine_tune/checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bab63666177a369829e36743467c8955ef878c1a3ee6521d1c20a9e80913b48
+size 522406213

checkpoints/fine_tune/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e8e987c364efd569d29d36dc1bb5ac79e67508209247c43c099c0ef1cde719
+size 14575

checkpoints/fine_tune/checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc9400cb662a1bb8b9b7e22613e20ac8ada32a353d1c4ddb8ff80949f26f36f
+size 627

checkpoints/fine_tune/checkpoint-150/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6410256410256411,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.2268,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.9252,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.3646,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015,
+      "loss": 2.0691,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.0406,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.9427,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.9141,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027,
+      "loss": 1.847,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 1.8292,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029501661129568106,
+      "loss": 1.7893,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002900332225913621,
+      "loss": 1.7282,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002850498338870432,
+      "loss": 1.7105,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002800664451827242,
+      "loss": 1.6879,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002750830564784053,
+      "loss": 1.6557,
+      "step": 150
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 4.419104855723213e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/fine_tune/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f3b5170a86663674b1afa17baf5754fce0f862af5a16e52b31a5f84fa63a06
+size 4091

checkpoints/fine_tune/checkpoint-300/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoints/fine_tune/checkpoint-300/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a35608fd0868d22e4593e36e0e705e2341bcff0d37b2597fe89df4d4d33ccd
+size 261189453

checkpoints/fine_tune/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b30ea688a2e134d9aba47d6c048b48debb930f80519936e2506bd368a472d4f
+size 522406213

checkpoints/fine_tune/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6634f297978f8e6ea09648f2904d315e738551adbbeaeacad11452e9839bb37b
+size 14575

checkpoints/fine_tune/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7d28feda5d97df64de235ffadaf4da82838c7b84a5a2b4bc75619a517da5d3
+size 627

checkpoints/fine_tune/checkpoint-300/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.282051282051282,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.2268,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.9252,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.3646,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015,
+      "loss": 2.0691,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.0406,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.9427,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.9141,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027,
+      "loss": 1.847,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 1.8292,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029501661129568106,
+      "loss": 1.7893,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002900332225913621,
+      "loss": 1.7282,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002850498338870432,
+      "loss": 1.7105,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002800664451827242,
+      "loss": 1.6879,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002750830564784053,
+      "loss": 1.6557,
+      "step": 150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027009966777408634,
+      "loss": 1.6357,
+      "step": 160
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026511627906976743,
+      "loss": 1.618,
+      "step": 170
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00026013289036544847,
+      "loss": 1.5717,
+      "step": 180
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00025514950166112955,
+      "loss": 1.5378,
+      "step": 190
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00025016611295681064,
+      "loss": 1.5166,
+      "step": 200
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.518738031387329,
+      "eval_runtime": 35.8579,
+      "eval_samples_per_second": 23.203,
+      "eval_steps_per_second": 5.801,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002451827242524917,
+      "loss": 1.4639,
+      "step": 210
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00024019933554817274,
+      "loss": 1.4595,
+      "step": 220
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002352159468438538,
+      "loss": 1.4605,
+      "step": 230
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00023023255813953486,
+      "loss": 1.3207,
+      "step": 240
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022524916943521595,
+      "loss": 1.2496,
+      "step": 250
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000220265780730897,
+      "loss": 1.2713,
+      "step": 260
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00021528239202657807,
+      "loss": 1.2369,
+      "step": 270
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00021029900332225913,
+      "loss": 1.2281,
+      "step": 280
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002053156146179402,
+      "loss": 1.2195,
+      "step": 290
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020033222591362126,
+      "loss": 1.1612,
+      "step": 300
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 8.856710441159885e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/fine_tune/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f3b5170a86663674b1afa17baf5754fce0f862af5a16e52b31a5f84fa63a06
+size 4091

checkpoints/fine_tune/checkpoint-450/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoints/fine_tune/checkpoint-450/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ce8152aa8fcd9a78a4e72d6a5203dd2c4b6f4de79e90ec63bdf0f65c697f89
+size 261189453

checkpoints/fine_tune/checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90cea54c279faa8952ec7746d2cae8b6fd547dc1a32db342f7f0626b173cf76e
+size 522406213

checkpoints/fine_tune/checkpoint-450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e684f70cc1031b629f17dc3ca29df44dbe519cbdf74fe1f1a697281b53f783fd
+size 14575

checkpoints/fine_tune/checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c39e3a468351763269c956caa09fa4b3a59fff10da1f2bafbf36512213a2d7
+size 627

checkpoints/fine_tune/checkpoint-450/trainer_state.json

@@ -0,0 +1,302 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9230769230769231,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.2268,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.9252,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.3646,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015,
+      "loss": 2.0691,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.0406,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.9427,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.9141,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027,
+      "loss": 1.847,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 1.8292,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029501661129568106,
+      "loss": 1.7893,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002900332225913621,
+      "loss": 1.7282,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002850498338870432,
+      "loss": 1.7105,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002800664451827242,
+      "loss": 1.6879,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002750830564784053,
+      "loss": 1.6557,
+      "step": 150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027009966777408634,
+      "loss": 1.6357,
+      "step": 160
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026511627906976743,
+      "loss": 1.618,
+      "step": 170
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00026013289036544847,
+      "loss": 1.5717,
+      "step": 180
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00025514950166112955,
+      "loss": 1.5378,
+      "step": 190
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00025016611295681064,
+      "loss": 1.5166,
+      "step": 200
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.518738031387329,
+      "eval_runtime": 35.8579,
+      "eval_samples_per_second": 23.203,
+      "eval_steps_per_second": 5.801,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002451827242524917,
+      "loss": 1.4639,
+      "step": 210
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00024019933554817274,
+      "loss": 1.4595,
+      "step": 220
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002352159468438538,
+      "loss": 1.4605,
+      "step": 230
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00023023255813953486,
+      "loss": 1.3207,
+      "step": 240
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022524916943521595,
+      "loss": 1.2496,
+      "step": 250
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000220265780730897,
+      "loss": 1.2713,
+      "step": 260
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00021528239202657807,
+      "loss": 1.2369,
+      "step": 270
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00021029900332225913,
+      "loss": 1.2281,
+      "step": 280
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002053156146179402,
+      "loss": 1.2195,
+      "step": 290
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020033222591362126,
+      "loss": 1.1612,
+      "step": 300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00019534883720930232,
+      "loss": 1.1708,
+      "step": 310
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019036544850498338,
+      "loss": 1.1457,
+      "step": 320
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00018538205980066444,
+      "loss": 1.1476,
+      "step": 330
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001803986710963455,
+      "loss": 1.0804,
+      "step": 340
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001754152823920266,
+      "loss": 1.1576,
+      "step": 350
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0001704318936877076,
+      "loss": 1.1166,
+      "step": 360
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00016544850498338866,
+      "loss": 1.0881,
+      "step": 370
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00016046511627906975,
+      "loss": 1.0565,
+      "step": 380
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001554817275747508,
+      "loss": 1.0939,
+      "step": 390
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00015049833887043187,
+      "loss": 1.0449,
+      "step": 400
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 1.1572413444519043,
+      "eval_runtime": 35.4584,
+      "eval_samples_per_second": 23.464,
+      "eval_steps_per_second": 5.866,
+      "step": 400
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00014551495016611296,
+      "loss": 1.0332,
+      "step": 410
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00014053156146179402,
+      "loss": 1.0091,
+      "step": 420
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00013554817275747508,
+      "loss": 1.0268,
+      "step": 430
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013056478405315615,
+      "loss": 1.0037,
+      "step": 440
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001255813953488372,
+      "loss": 0.972,
+      "step": 450
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 1.3337998305086669e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/fine_tune/checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f3b5170a86663674b1afa17baf5754fce0f862af5a16e52b31a5f84fa63a06
+size 4091

checkpoints/fine_tune/checkpoint-600/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoints/fine_tune/checkpoint-600/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8903f85cab418a9eb872eebf7995b32e2f3c25e625beb9ecf899de2eb643fe4f
+size 261189453

checkpoints/fine_tune/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209aec2bd690091eb106d556af7c87e1615c1ae91c5d7c737ea2ecbf5c89fbf1
+size 522406213

checkpoints/fine_tune/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8437378f46f20da19d2284c1f3b8d6fb1ae4c9039f1338f31038ec8a12cd7f
+size 14575

checkpoints/fine_tune/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a476200915fa13159d98e2efceca649b5a621e2846757bec5d72720c21ce94f
+size 627

checkpoints/fine_tune/checkpoint-600/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.564102564102564,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 3.2268,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.9252,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 2.3646,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 2.1557,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00015,
+      "loss": 2.0691,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 2.0406,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.9427,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.9141,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027,
+      "loss": 1.847,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 1.8292,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00029501661129568106,
+      "loss": 1.7893,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002900332225913621,
+      "loss": 1.7282,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002850498338870432,
+      "loss": 1.7105,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002800664451827242,
+      "loss": 1.6879,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002750830564784053,
+      "loss": 1.6557,
+      "step": 150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00027009966777408634,
+      "loss": 1.6357,
+      "step": 160
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00026511627906976743,
+      "loss": 1.618,
+      "step": 170
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00026013289036544847,
+      "loss": 1.5717,
+      "step": 180
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00025514950166112955,
+      "loss": 1.5378,
+      "step": 190
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00025016611295681064,
+      "loss": 1.5166,
+      "step": 200
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.518738031387329,
+      "eval_runtime": 35.8579,
+      "eval_samples_per_second": 23.203,
+      "eval_steps_per_second": 5.801,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0002451827242524917,
+      "loss": 1.4639,
+      "step": 210
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00024019933554817274,
+      "loss": 1.4595,
+      "step": 220
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0002352159468438538,
+      "loss": 1.4605,
+      "step": 230
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00023023255813953486,
+      "loss": 1.3207,
+      "step": 240
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00022524916943521595,
+      "loss": 1.2496,
+      "step": 250
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.000220265780730897,
+      "loss": 1.2713,
+      "step": 260
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00021528239202657807,
+      "loss": 1.2369,
+      "step": 270
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00021029900332225913,
+      "loss": 1.2281,
+      "step": 280
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002053156146179402,
+      "loss": 1.2195,
+      "step": 290
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00020033222591362126,
+      "loss": 1.1612,
+      "step": 300
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00019534883720930232,
+      "loss": 1.1708,
+      "step": 310
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00019036544850498338,
+      "loss": 1.1457,
+      "step": 320
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00018538205980066444,
+      "loss": 1.1476,
+      "step": 330
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001803986710963455,
+      "loss": 1.0804,
+      "step": 340
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001754152823920266,
+      "loss": 1.1576,
+      "step": 350
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0001704318936877076,
+      "loss": 1.1166,
+      "step": 360
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00016544850498338866,
+      "loss": 1.0881,
+      "step": 370
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00016046511627906975,
+      "loss": 1.0565,
+      "step": 380
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001554817275747508,
+      "loss": 1.0939,
+      "step": 390
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00015049833887043187,
+      "loss": 1.0449,
+      "step": 400
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 1.1572413444519043,
+      "eval_runtime": 35.4584,
+      "eval_samples_per_second": 23.464,
+      "eval_steps_per_second": 5.866,
+      "step": 400
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00014551495016611296,
+      "loss": 1.0332,
+      "step": 410
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00014053156146179402,
+      "loss": 1.0091,
+      "step": 420
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00013554817275747508,
+      "loss": 1.0268,
+      "step": 430
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013056478405315615,
+      "loss": 1.0037,
+      "step": 440
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0001255813953488372,
+      "loss": 0.972,
+      "step": 450
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00012059800664451827,
+      "loss": 0.9832,
+      "step": 460
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.00011561461794019933,
+      "loss": 0.9448,
+      "step": 470
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00011063122923588038,
+      "loss": 0.7447,
+      "step": 480
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00010564784053156144,
+      "loss": 0.7475,
+      "step": 490
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00010066445182724251,
+      "loss": 0.7368,
+      "step": 500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.568106312292358e-05,
+      "loss": 0.7267,
+      "step": 510
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.069767441860464e-05,
+      "loss": 0.7436,
+      "step": 520
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.57142857142857e-05,
+      "loss": 0.7427,
+      "step": 530
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.073089700996676e-05,
+      "loss": 0.7302,
+      "step": 540
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 7.574750830564784e-05,
+      "loss": 0.7289,
+      "step": 550
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.07641196013289e-05,
+      "loss": 0.7012,
+      "step": 560
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.578073089700996e-05,
+      "loss": 0.7147,
+      "step": 570
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 6.079734219269102e-05,
+      "loss": 0.6841,
+      "step": 580
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 5.581395348837209e-05,
+      "loss": 0.6981,
+      "step": 590
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.083056478405315e-05,
+      "loss": 0.6828,
+      "step": 600
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.9608005881309509,
+      "eval_runtime": 34.8102,
+      "eval_samples_per_second": 23.901,
+      "eval_steps_per_second": 5.975,
+      "step": 600
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 1.7806438440045773e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/fine_tune/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f3b5170a86663674b1afa17baf5754fce0f862af5a16e52b31a5f84fa63a06
+size 4091

checkpoints/fine_tune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f3b5170a86663674b1afa17baf5754fce0f862af5a16e52b31a5f84fa63a06
+size 4091

interpret_models/attributes_falcon-7b-instruct-FT-LoRA-8bit-test1_0it.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ccc086272e8bbb8f4179b2537e0a2d302a2d8980a41f3154bf846cc0f4ca13
+size 56039282

interpret_models/attributes_falcon-7b-instruct-RL-LoRA-8bit-test1_0it.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07845fe00cb52687d1e67fe1b1979f22c646aa7b46a45b6e81737c25c666123
+size 49347897

interpret_models/attributes_falcon-7b-instruct_0it.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8913cb771fdc55fd2471f76ff8ddc58c2f99efc12c474906918199cb29679988
+size 46783782

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b75f5614ded2fe3a966d8c1f23f6cfb84e5f1c0cbe6646d427fd1ac9355c11
+size 4155