Training in progress, step 100

adapter_config.json

@@ -1,15 +1,15 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "gpt2",
-  "encoder_hidden_size": 768,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "encoder_hidden_size": 4096,
   "inference_mode": true,
-  "num_attention_heads": 12,
-  "num_layers": 12,
+  "num_attention_heads": 32,
+  "num_layers": 32,
   "num_transformer_submodules": 1,
   "num_virtual_tokens": 80,
   "peft_type": "PREFIX_TUNING",
   "prefix_projection": false,
   "revision": null,
   "task_type": "CAUSAL_LM",
-  "token_dim": 768
+  "token_dim": 4096
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f439244e7eae3937b808ce07053f38c06bdce0debd39e20c31a517e5bd03862
-size 5898368
+oid sha256:c37ea77673a47ee74de15aed49216b444f1d0cf22e52f9c13e3692b0bd43d8fa
+size 83886208

runs/Jan19_05-07-13_calcul-bigcpu-lahc-6/events.out.tfevents.1705637236.calcul-bigcpu-lahc-6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0c7d1e80adb3cce3d325d6a71f3c81ae768d0d6329b09ab8fdea91aadd6580
+size 4383

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "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
+  }
 }

tokenizer_config.json

@@ -1,20 +1,39 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd93d0fad8eff319edcfaaf5044708aa3941dc3e49386410f744605b44386ac4
+oid sha256:2dd3e1545ea84bff2ce2b963dd95c6a6286bacb6032742e792fc5d646167be3b
 size 4600