Model save

README.md

@@ -5,6 +5,7 @@ license: apache-2.0
 tags:
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: Qwen-1.5b-sft-qlora

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 2.4013425932721193e+18,
     "train_loss": 0.0,
-    "train_runtime": 0.0528,
+    "train_runtime": 0.0617,
     "train_samples": 207864,
-    "train_samples_per_second": 3940185.324,
-    "train_steps_per_second": 328348.777
+    "train_samples_per_second": 3368693.42,
+    "train_steps_per_second": 280724.452
 }

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "Qwen/Qwen2-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "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-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

runs/Sep26_13-57-34_interactive79915/events.out.tfevents.1727330275.interactive79915.116894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca818c0b116da1c1348db5edf439b23c873dbfd428437cfd6c205f7ebea7ff50
+size 6880

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 2.4013425932721193e+18,
     "train_loss": 0.0,
-    "train_runtime": 0.0528,
+    "train_runtime": 0.0617,
     "train_samples": 207864,
-    "train_samples_per_second": 3940185.324,
-    "train_steps_per_second": 328348.777
+    "train_samples_per_second": 3368693.42,
+    "train_steps_per_second": 280724.452
 }

trainer_state.json

@@ -24268,9 +24268,9 @@
       "step": 17322,
       "total_flos": 2.4013425932721193e+18,
       "train_loss": 0.0,
-      "train_runtime": 0.0528,
-      "train_samples_per_second": 3940185.324,
-      "train_steps_per_second": 328348.777
+      "train_runtime": 0.0617,
+      "train_samples_per_second": 3368693.42,
+      "train_steps_per_second": 280724.452
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70fd547b854e0290ba245f13d741823cf38735fde2fbd11c3f6e63946fac002
+oid sha256:46f41662c700aa2b459e4260e58b5e312345f8e51ab835dd9f230cc31e2b1775
 size 6200