Upload 9 files

README.md

@@ -1,4 +1,32 @@
 ---
-tags:
-- text-generation-inference
----
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fd3532725422b1cbe5f69e16681b4ce3d5a2f298686b413f19bfa2685eb54c
+size 1044539653

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd6572be3f919f507dab392a96fe55b1b2eebc14915ed566a79df814505bea6
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a25f133d8edd724f544d8f0f5d6f5fc7c5822269fb2ddbe4f1912a4b23a53a
+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 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 96.0,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0002,
+      "loss": 3.2324,
+      "step": 10
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.0002,
+      "loss": 1.4712,
+      "step": 20
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3733,
+      "step": 30
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0691,
+      "step": 40
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0563,
+      "step": 50
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0523,
+      "step": 60
+    },
+    {
+      "epoch": 56.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0511,
+      "step": 70
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0516,
+      "step": 80
+    },
+    {
+      "epoch": 72.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0518,
+      "step": 90
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0504,
+      "step": 100
+    },
+    {
+      "epoch": 88.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0503,
+      "step": 110
+    },
+    {
+      "epoch": 96.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0508,
+      "step": 120
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 500,
+  "total_flos": 4188956688451584.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34528282b7c46dcfd7c599ae7c30e6e9e637863bb1e3a857ebb54fa3de84a2df
+size 3963