Training in progress, epoch 0

adapter_config.json

@@ -1,32 +1,24 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "MistralForCausalLM",
-    "parent_library": "transformers.models.mistral.modeling_mistral"
+    "base_model_class": "MarianMTModel",
+    "parent_library": "transformers.models.marian.modeling_marian"
   },
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "Helsinki-NLP/opus-mt-de-en",
   "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": 32,
   "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
-  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
     "v_proj"
   ],
-  "task_type": null,
-  "use_dora": false,
-  "use_rslora": false
+  "task_type": null
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7189708c7e729ed8056bc769b02116a2616e96fdb75d18571a6e8b6738dc7c1d
-size 109069176
+oid sha256:936e3cdccabfa9461dafce7d916d5605e4fdf89d2d48223039874589dcaae7a7
+size 9447288

special_tokens_map.json

@@ -1,24 +1,5 @@
 {
-  "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": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,9 +1,7 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,15 +9,15 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "58100": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -27,16 +25,14 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "de",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a712b5bef0955a52b4f98e5e92e74d7e37465da135ff4a6e01695d5297c2dd0
-size 4984
+oid sha256:9f8a6599acc397e1d8c883a81e569b4a14c9654f5683265f0fdc88fb56bb53ca
+size 4920