Upload folder using huggingface_hub

README.md

@@ -0,0 +1,10 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "tiiuae/falcon-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9346b9bdb0b0d7fc3e555dc21f401422f73a7102e7e1c5fa849cc95fa764ef5a
+size 261189453

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d56167de0cbb796019c6b1df86d9c1122876c4cae810d8231c8a5b6a9adb6f4
+size 522348805

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfc96dc9be5642d06c809572ec989df6b2ec19869f171677758e9ae9d5fa071
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc9f914380ce6a3c801c27f7620226b1ff060a4b0603d5fa3205fe837822f49
+size 627

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 1.4523780345916748,
+  "best_model_checkpoint": "./results/checkpoint-64",
+  "epoch": 0.05200081251269551,
+  "eval_steps": 8,
+  "global_step": 64,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 1.604,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.5865,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.58369779586792,
+      "eval_runtime": 33.9799,
+      "eval_samples_per_second": 15.244,
+      "eval_steps_per_second": 1.913,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.4024,
+      "step": 12
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.3627,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 1.503720998764038,
+      "eval_runtime": 34.2342,
+      "eval_samples_per_second": 15.131,
+      "eval_steps_per_second": 1.899,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 1.3242,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 1.2733,
+      "step": 24
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.4826295375823975,
+      "eval_runtime": 34.4234,
+      "eval_samples_per_second": 15.048,
+      "eval_steps_per_second": 1.888,
+      "step": 24
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0002,
+      "loss": 1.507,
+      "step": 28
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 1.472,
+      "step": 32
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4713466167449951,
+      "eval_runtime": 34.5227,
+      "eval_samples_per_second": 15.005,
+      "eval_steps_per_second": 1.883,
+      "step": 32
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 1.4269,
+      "step": 36
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 1.6282,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4705039262771606,
+      "eval_runtime": 34.5472,
+      "eval_samples_per_second": 14.994,
+      "eval_steps_per_second": 1.881,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 1.6744,
+      "step": 44
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 1.789,
+      "step": 48
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 1.4801452159881592,
+      "eval_runtime": 34.5611,
+      "eval_samples_per_second": 14.988,
+      "eval_steps_per_second": 1.881,
+      "step": 48
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 1.7547,
+      "step": 52
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002,
+      "loss": 1.3081,
+      "step": 56
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.465359091758728,
+      "eval_runtime": 34.5837,
+      "eval_samples_per_second": 14.978,
+      "eval_steps_per_second": 1.88,
+      "step": 56
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002,
+      "loss": 1.2313,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0002,
+      "loss": 1.4273,
+      "step": 64
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4523780345916748,
+      "eval_runtime": 34.6395,
+      "eval_samples_per_second": 14.954,
+      "eval_steps_per_second": 1.876,
+      "step": 64
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 64,
+  "num_train_epochs": 1,
+  "save_steps": 8,
+  "total_flos": 7578875318034432.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c344a89cdc0be10f4f9108a8b6a79229619c02326bc5d60fb8aa724a57e46f6b
+size 4027