Update model (trained for one more epoch)

adapter_config.json

@@ -1,5 +1,4 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "Locutusque/TinyMistral-248M",
   "bias": "none",
@@ -13,7 +12,6 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
-  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf4afe44da097b7e5503ecdf06c785e87db2e054f5d7996d4bfae76d298e60f
+size 2572670

config.json

@@ -19,7 +19,7 @@
   "sliding_window": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32003
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2167bd8b9ea40693c70afbc71422c46e75dcad1b616f2cac3c7c157c5ce157b
+size 496075846

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1536,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -54,15 +56,11 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": true,
-  "max_length": 1536,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24b4b32e33ca71ba9e658a2871c9230e51b45f3c94190439d92c65ec9b48270
-size 4600
+oid sha256:21eae65f4c26b0c16e3e46446fd425ca78580db9e0a0f97b3315795b3d2a65fd
+size 4536

training_params.json

@@ -1 +1,47 @@
-{"model": "Locutusque/TinyMistral-248M", "data_path": "Felladrin/autotrain-data-TinyMistral-248M", "project_name": "/tmp/model", "train_split": "train", "valid_split": null, "text_column": "autotrain_text", "rejected_text_column": null, "lr": 0.0002, "epochs": 1, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": true, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.1, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "Felladrin/TinyMistral-248M-1", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "Felladrin", "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": null}
+{
+    "model": "Felladrin/TinyMistral-248M-Evol-Instruct",
+    "data_path": "data/",
+    "project_name": "TinyMistral-248M-Evol-Instruct",
+    "train_split": "train",
+    "valid_split": null,
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "token": null,
+    "lr": 0.0002,
+    "epochs": 1,
+    "batch_size": 12,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "add_eos_token": false,
+    "block_size": 1024,
+    "use_peft": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "fp16": false,
+    "push_to_hub": false,
+    "use_int8": true,
+    "model_max_length": 1024,
+    "repo_id": null,
+    "use_int4": false,
+    "trainer": "sft",
+    "target_modules": null,
+    "merge_adapter": true,
+    "username": null,
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt"
+}