Training in progress, step 22

adapter_config.json

@@ -6,7 +6,7 @@
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj",
     "up_proj",
-    "k_proj"
+    "v_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b281a229a8fd65ec463fd1fcfa32828855e1f3455cc455cfca5b3735454e623
+oid sha256:e2d5d562dcd4288015dbb98d9133f69b9e1dfe10cbaf7dea02c3350d8237e2c2
 size 87360584

config.json

@@ -17,12 +17,27 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
+  "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_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
   "use_cache": false,
   "use_sliding_window": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb0dc6f3cc30baa00bc2a623279155157ebafc0dfb868fd6aecf72fb696be8d
+oid sha256:140f363667f4cb829aad2682e5aa13c993bc684134792e1e8bdb3d908fcf05a0
 size 7224