Training in progress, step 33

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "tiiuae/falcon-mamba-7b-instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "k_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "v_proj"
+    "dt_proj",
+    "out_proj",
+    "in_proj",
+    "x_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1674df1b342e63face0598782767beb1f2c10d71624e812bdce591edca3e9e9
-size 1342238560
+oid sha256:a81c0d1b995f4a9f1fc234e03e6550c8997207163a894ea31ac327cdb249494f
+size 1628509400

runs/Aug30_11-44-20_ip-172-16-25-197.us-west-2.compute.internal/events.out.tfevents.1725018313.ip-172-16-25-197.us-west-2.compute.internal.1114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90be0ed34aab6d547ad26a526cbe342b59836aa8e277f39517539c1e5713377c
+size 9401

special_tokens_map.json

@@ -1,27 +1,33 @@
 {
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": ">>TITLE<<",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,10 +1,8 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": ">>TITLE<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +10,7 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": ">>ABSTRACT<<",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,7 +18,79 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "assistant",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|end_of_text|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,17 +98,32 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    "assistant",
+    "<|begin_of_text|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 2048,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "pad_to_multiple_of": null,
+  "pad_token": ">>TITLE<<",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59704644335132eeb5500846634d0397b1d9549c348430e1cede5d673037d74
-size 6072
+oid sha256:09c04c387d31a9747d273916dc37318c4cadec0505dbf16177f88610cf7c10ee
+size 6264