Training in progress, epoch 1

adapter_config.json

@@ -6,7 +6,7 @@
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": true,
+  "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
@@ -24,9 +24,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
-    "c_attn",
-    "q_proj"
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c264c6db5b67204bcd495a4e7ceb3221b18f0ba697f77d3bc009d01e44e41458
+oid sha256:dd5ec9da20f6576a4c05397fca6abe70cafd2a70cb7d17aa29d6b38d1fcfa36c
 size 1182680

tokenizer_config.json

@@ -16,8 +16,15 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 512,
   "model_max_length": 1024,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a405d576fc2a3b71897f01b2a6776f775085c25f3aa4a1cdfde5e913cf32ce09
+oid sha256:8998c80922fae99c9d261875e66c2b228622fde546c2d1028eeb4cc02ca893dd
 size 5304