Training in progress, step 10

README.md

@@ -5,8 +5,8 @@ model_name: gpt-oss-20b-multilingual-reasoner
 tags:
 - generated_from_trainer
 - trl
-- unsloth
 - sft
+- unsloth
 licence: license
 ---
 
@@ -37,7 +37,7 @@ This model was trained with SFT.
 
 - TRL: 0.21.0
 - Transformers: 4.56.0.dev0
-- Pytorch: 2.7.1
+- Pytorch: 2.8.0
 - Datasets: 3.6.0
 - Tokenizers: 0.21.4
 

adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "GptOssForCausalLM",
+    "parent_library": "transformers.models.gpt_oss.modeling_gpt_oss"
+  },
+  "base_model_name_or_path": "unsloth/gpt-oss-20b",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj)))",
+  "target_parameters": [
+    "7.mlp.experts.gate_up_proj",
+    "7.mlp.experts.down_proj",
+    "15.mlp.experts.gate_up_proj",
+    "15.mlp.experts.down_proj",
+    "23.mlp.experts.gate_up_proj",
+    "23.mlp.experts.down_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b878022bdd4ee52f28012559eb52dc6ad9b0e5466c4c12169c07a201b05195e
+size 15950616

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa29ebbc6bcd967e14b62760c8a466b5f462fc86157ab08fb34e9bbd7822b89
+oid sha256:8c15f7aef3b80f38cb81f2c9f61f01cf794de78926ce8681ebd8c0fd25ef8b9b
 size 6289