Training in progress, step 25

adapter_config.json

@@ -1,31 +1,17 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
-  "bias": "none",
-  "fan_in_fan_out": false,
+  "encoder_dropout": 0.0,
+  "encoder_hidden_size": 250,
+  "encoder_num_layers": 2,
+  "encoder_reparameterization_type": "MLP",
   "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 64,
-  "rank_pattern": {},
+  "num_attention_heads": 16,
+  "num_layers": 24,
+  "num_transformer_submodules": 1,
+  "num_virtual_tokens": 50,
+  "peft_type": "P_TUNING",
   "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj"
-  ],
   "task_type": "CAUSAL_LM",
-  "use_rslora": false
+  "token_dim": 2048
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ea4013ae1aa6d2396b15bfbb8779f41752fb078446ebfd2094474cc00adf3a
-size 214734488
+oid sha256:6c945edd10f35879916a0745576f8dbb873eeb3a0c78fd256818c286b4baae36
+size 409720

special_tokens_map.json

@@ -13,5 +13,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "stic"
+  "pad_token": "Ġsq"
 }

tokenizer_config.json

@@ -185,7 +185,7 @@
   "eos_token": "<|EOT|>",
   "legacy": true,
   "model_max_length": 16384,
-  "pad_token": "stic",
+  "pad_token": "Ġsq",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afff67173769f97f112b041e85b114e179e83ce3ce340bf45e9ade06cbfdfca
+oid sha256:759434762d7bfb55a21f68b18a6e6125b5035fbd73274ea67425ff0b6cc062ad
 size 4664