Training in progress, step 1

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "up_proj",
     "gate_proj",
+    "k_proj",
     "down_proj",
     "q_proj",
-    "k_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5399169408e0472fec79734ce74469216db17bc47fec9ded630bcd2bf4736b5d
+oid sha256:a6b45683316a2125ac85ee9ed7e75acbec145f39d178440639361092659e1dc1
 size 90207248

full_step=1/config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "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-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

full_step=1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1df53c6cd88dbd35bcf6d25d15e728352b3c997025a6def5e1663b2473643c
+size 1072905784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3237f3e057123fbc65a25db0eb3f0af442caca834014a73886eb170a736b05a
+oid sha256:21a87551c7fda5496aee98ce3e636103b6bb719e7935e827b2020aa3338fa38d
 size 5496