Training in progress, step 4500

adapter_config.json

@@ -1 +1,41 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "DeepMount00/Llama-3-8b-Ita", "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", "gate_proj", "down_proj", "q_proj", "out_proj", "query_key_value", "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": "DeepMount00/Llama-3-8b-Ita",
+  "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",
+    "down_proj",
+    "out_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_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 sha256:64b6aa33832d0d07d57dca4a7c2a8e07ac398948af54aebf07704d4493be1232
+oid sha256:e829e2de319c5684041606ea3f279775eba97da5fcdedfe992d3078175bc1c14
 size 1342238560

toilaluan/bf0c13f3-6e2f-4cf7-aa39-cafe6a49051e/adapter_config.json

@@ -1 +1 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "DeepMount00/Llama-3-8b-Ita", "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": ["out_proj", "o_proj", "v_proj", "down_proj", "q_proj", "k_proj", "query_key_value", "gate_proj", "up_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}
+{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "DeepMount00/Llama-3-8b-Ita", "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", "gate_proj", "down_proj", "q_proj", "out_proj", "query_key_value", "up_proj", "k_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:a80339fd00b8c6ec910c51b16a50018434748ecd352a5c039889a20cc0403b69
+oid sha256:77addcdce5d8fbb4db14c5505c22819cb08647c68cb6e374bc0b2ad40062c025
 size 5752