Training in progress, step 189

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: mistralai/Mistral-7B-v0.3
+base_model: gpt2
 library_name: transformers
 model_name: fine_tune_e2e
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for fine_tune_e2e
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3).
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "base_model_name_or_path": "gpt2",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -15,18 +15,17 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "c_attn"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf34fde6325e2ba35addc42a9f03f5d4b1b2d2cd81085c3308703464ff94435
-size 6832600
+oid sha256:9c3a69c79de0c4938e9b6c03e33590efccfac2dea2b5068274b2cba0826b8b46
+size 1182680

special_tokens_map.json

@@ -1,23 +1,5 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a17f31cdbc6029c272d8a023e589524ede2109a16cd835dfc7c15858bb5ca8
-size 6225
+oid sha256:194a9386546a5476c11b86d7605eea2c8e41a2001f4d4b6aa2e145a367827a0c
+size 6161