Training in progress, step 5

adapter_config.json

@@ -3,30 +3,30 @@
   "auto_mapping": null,
   "base_model_name_or_path": "echarlaix/tiny-random-mistral",
   "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": 128,
-  "lora_dropout": 0.1,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "gate_proj",
-    "down_proj",
     "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c7abdfd0b443cc17d2032f5c63d1b661db3c628a5f0971fb6829e71427615b
-size 224224
+oid sha256:39705e634a87013aa42d1d42545bec2297856ef2b320e75834c850f84ee20227
+size 58680

config.json

@@ -15,12 +15,27 @@
   "initializer_range": 0.02,
   "intermediate_size": 37,
   "is_decoder": true,
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 4056,
   "model_type": "mistral",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,

tokenizer_config.json

@@ -30,7 +30,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b558cb8d9d555d434797bb3f54570d655e1e6cbcec2de08ae0026732eb1f764c
-size 6776
+oid sha256:3938a5457f7b26d5890f6faa39ab88fd0ac91d595f45dcbd0c228f43e39583ed
+size 6584