Training in progress, step 1500

adapter_config.json

@@ -1 +1,41 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "samoline/053bafa6-fb4c-4595-8ac4-60f27c582d9e", "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": ["v_proj", "q_proj", "gate_proj", "out_proj", "o_proj", "down_proj", "query_key_value", "up_proj", "k_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "samoline/053bafa6-fb4c-4595-8ac4-60f27c582d9e",
+  "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": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "out_proj",
+    "up_proj",
+    "gate_proj",
+    "query_key_value",
+    "down_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 sha256:3c8338d482509295b4843f7081849bcc74a9d6d6eb699feead5b0f42d901ae71
+oid sha256:bf1bb66fbb19c3e2e458d750711c64640b9bb8078a702238b1070fb5829017d5
 size 778096664

toilaluan/aa1aa1d3-b4f9-47ca-a994-eb131d5a374b/adapter_config.json

@@ -0,0 +1 @@
+{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "samoline/053bafa6-fb4c-4595-8ac4-60f27c582d9e", "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": ["v_proj", "q_proj", "gate_proj", "out_proj", "o_proj", "down_proj", "query_key_value", "up_proj", "k_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 sha256:9de6a26c98d625ea06d46253ccb96183cb1390de65bc5d6b9d348d10f70df959
+oid sha256:bac1a06ed0b8ec83e763110a9cfbe13a52a1181bd4361612d6fc233f50479b89
 size 5752