Training in progress, epoch 1

adapter_config.json

@@ -3,15 +3,15 @@
   "auto_mapping": null,
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
   "bias": "none",
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
@@ -19,17 +19,17 @@
     "lm_head"
   ],
   "peft_type": "LORA",
-  "r": 128,
+  "r": 32,
   "rank_pattern": {},
-  "revision": "unsloth",
+  "revision": null,
   "target_modules": [
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
     "down_proj",
     "o_proj",
-    "v_proj",
-    "q_proj",
-    "k_proj",
-    "up_proj",
-    "gate_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d2ea2c53bae73716e36ef6ef01ee5cad72301210222229e23ef62077ab397f
-size 2336289560
+oid sha256:588591505247958507363d98bfb2535733c13dde0ff41a2d5c05267a8ab37eb1
+size 848358568

config.json

@@ -5,8 +5,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 32013,
-  "eos_token_id": 32021,
+  "bos_token_id": 32022,
+  "eos_token_id": 32023,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -17,6 +17,21 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "factor": 4.0,
@@ -26,7 +41,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",
-  "unsloth_version": "2024.6",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32256
 }

special_tokens_map.json

@@ -1,22 +1,22 @@
 {
   "bos_token": {
-    "content": "<｜begin▁of▁sentence｜>",
+    "content": "<|begin_of_sentence|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|EOT|>",
+    "content": "<|end_of_sentence|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<｜end▁of▁sentence｜>",
+    "content": "<|end_of_sentence|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -200,6 +200,24 @@
       "rstrip": false,
       "normalized": true,
       "special": true
+    },
+    {
+      "id": 32022,
+      "content": "<|begin_of_sentence|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32023,
+      "content": "<|end_of_sentence|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -258,7 +276,7 @@
     "single": [
       {
         "SpecialToken": {
-          "id": "<｜begin▁of▁sentence｜>",
+          "id": "<|begin_of_sentence|>",
           "type_id": 0
         }
       },
@@ -272,7 +290,7 @@
     "pair": [
       {
         "SpecialToken": {
-          "id": "<｜begin▁of▁sentence｜>",
+          "id": "<|begin_of_sentence|>",
           "type_id": 0
         }
       },
@@ -284,7 +302,7 @@
       },
       {
         "SpecialToken": {
-          "id": "<｜begin▁of▁sentence｜>",
+          "id": "<|begin_of_sentence|>",
           "type_id": 1
         }
       },
@@ -296,13 +314,13 @@
       }
     ],
     "special_tokens": {
-      "<｜begin▁of▁sentence｜>": {
-        "id": "<｜begin▁of▁sentence｜>",
+      "<|begin_of_sentence|>": {
+        "id": "<|begin_of_sentence|>",
         "ids": [
-          32013
+          32022
         ],
         "tokens": [
-          "<｜begin▁of▁sentence｜>"
+          "<|begin_of_sentence|>"
         ]
       }
     }

tokenizer_config.json

@@ -177,18 +177,34 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32022": {
+      "content": "<|begin_of_sentence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<|end_of_sentence|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "bos_token": "<｜begin▁of▁sentence｜>",
+  "bos_token": "<|begin_of_sentence|>",
   "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|EOT|>",
+  "eos_token": "<|end_of_sentence|>",
   "legacy": true,
   "model_max_length": 16384,
-  "pad_token": "<｜end▁of▁sentence｜>",
-  "padding_side": "left",
+  "pad_token": "<|end_of_sentence|>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb5dadad399f56bab17c0969fd231762f07aae4fc36f59d67ab4a339e567cfc
+oid sha256:0eaa08222fb80db93edb290a2d6190a3b510a1f8d4226cb8cefe6ee779fbded5
 size 5880