Training in progress, step 100

adapter_config.json

@@ -1,37 +1,37 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-70B-Instruct",
-  "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 4,
-  "lora_bias": false,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 2,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "q_proj",
-    "o_proj",
-    "down_proj",
-    "gate_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 2,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 1,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc518160ca307b0f10b9afdeb3c78e06e83b5bec2aef55120480f32b0bf4b90
-size 103695192
+oid sha256:b31cde133d9c65d662341fb736f40580f31c874a361a3dedadf27608c32d9986
+size 10544144

runs/Dec26_04-21-50_3c935f30e5d3/events.out.tfevents.1735186945.3c935f30e5d3.3874.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a3c92278bed9a430cb767b97f68d3ad88d9fed4b121da54f0a23a96a08b44a
+size 27121

special_tokens_map.json

@@ -1,17 +1,17 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<|eot_id|>"
-}
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ee964e66ac2320316f04d4933f2638c7763612341e72ce6c759b7895c3dc35
-size 5624
+oid sha256:0604f2651247a3f26acc2b418bdce2dedf9797ea35a16b2870948cfdf805b2dd
+size 5560