Training in progress, step 150

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,196 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-nemo-base-2407-bnb-4bit",
+  "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": 128,
+  "lora_dropout": 0.3,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.32.mlp.gate_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.35.mlp.down_proj",
+    "model.layers.32.mlp.down_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.38.self_attn.v_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.28.mlp.gate_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.36.self_attn.k_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.33.self_attn.q_proj",
+    "model.layers.33.mlp.gate_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.39.self_attn.k_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.28.mlp.up_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.36.self_attn.v_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.37.self_attn.k_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.30.self_attn.k_proj",
+    "model.layers.33.self_attn.v_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.28.mlp.down_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.39.mlp.down_proj",
+    "model.layers.32.self_attn.o_proj",
+    "model.layers.37.self_attn.v_proj",
+    "model.layers.38.self_attn.k_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.36.self_attn.o_proj",
+    "model.layers.39.self_attn.v_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.33.mlp.down_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.38.self_attn.o_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.28.self_attn.o_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.38.mlp.up_proj",
+    "model.layers.34.self_attn.v_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.29.self_attn.o_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.37.mlp.up_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.embed_tokens",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.34.mlp.up_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.35.mlp.up_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.38.mlp.down_proj",
+    "model.layers.32.mlp.up_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.38.mlp.gate_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.30.mlp.up_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.38.self_attn.q_proj",
+    "model.layers.39.self_attn.o_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.36.mlp.up_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.35.self_attn.v_proj",
+    "model.layers.29.self_attn.k_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.30.mlp.down_proj",
+    "model.layers.31.self_attn.o_proj",
+    "model.layers.34.self_attn.q_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.39.mlp.up_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.31.mlp.up_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.39.self_attn.q_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.29.mlp.up_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.39.mlp.gate_proj",
+    "model.layers.35.self_attn.q_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.37.self_attn.q_proj",
+    "model.layers.31.self_attn.k_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.34.mlp.down_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.29.self_attn.v_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.24.mlp.down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496ad04b4a072729b22dd87285c317c2b837ce4066bb8bd135be371a5a91f3e6
+size 1915531480

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31332ffd72cdee7c253df90ab08cf9ee286bd1192b662a7c97ced752d193c4c8
+size 5496