Training in progress, step 2500

adapter_config.json

@@ -1 +1,41 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "unsloth/Qwen2.5-Math-7B-Instruct", "bias": "none", "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": 256, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 128, "rank_pattern": {}, "revision": null, "target_modules": ["o_proj", "k_proj", "up_proj", "query_key_value", "q_proj", "out_proj", "gate_proj", "down_proj", "v_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-Math-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "query_key_value",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "out_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d311a6e07b29b5b7deaee4357520e131ac71af1c3232104fd77aa02d4e38f9e5
+oid sha256:990b210f00d3fd79e72528a99845e3119d791adf4d3d861b6d2a048cdab00e30
 size 1291899160

toilaluan/84b5262c-9e41-4939-9c06-b67b5cdd9044/adapter_config.json

@@ -1 +1 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "unsloth/Qwen2.5-Math-7B-Instruct", "bias": "none", "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": 256, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 128, "rank_pattern": {}, "revision": null, "target_modules": ["gate_proj", "o_proj", "out_proj", "v_proj", "k_proj", "q_proj", "query_key_value", "up_proj", "down_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}
+{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "unsloth/Qwen2.5-Math-7B-Instruct", "bias": "none", "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": 256, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 128, "rank_pattern": {}, "revision": null, "target_modules": ["o_proj", "k_proj", "up_proj", "query_key_value", "q_proj", "out_proj", "gate_proj", "down_proj", "v_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f6651393a12e39c286071f29714ec1bd15310e5c509b57dff436d175f48c715
+oid sha256:3fdcfcbd453fe5500e54844c52290ab47950e2dae775f5e623f7cf153ff2601b
 size 5752