Training in progress, step 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "base_model_name_or_path": "/content/drive/MyDrive/orpo-phi3",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "down_proj",
     "o_proj",
-    "qkv_proj"
+    "qkv_proj",
+    "down_proj",
+    "gate_up_proj"
   ],
   "task_type": "CASUAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38054949cbe86ec95f572195212be242e0dd8d6202cf29ee94b5013c6e81ee2
-size 887450008
+oid sha256:3f03e2df0bfd8c621ecf3089601c65af2141446ab2a056dbe84c33356a6dedea
+size 100697728

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 32011,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32012,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32012,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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"
+  },
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32013
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32011,
+  "eos_token_id": 32012,
+  "pad_token_id": 32012,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb114b687d788996e8b2427f623f149786a03c933043566292e18033231ac41
+size 2263483252

runs/Jul19_06-15-38_4de18fa006b0/events.out.tfevents.1721369745.4de18fa006b0.333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52253db3971012bec47eebc2a5cf0ebfe0cab86c7b7c00401534a4846130f33
+size 6411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c18a4cc48c71b139483fe3050e1e12d55b9a944d63dd39b85e480602fead1b
+oid sha256:4c0125fed4015d9601a6fef061c897280f33ffd8cad6f0e6c104cfc76960aaea
 size 5496