End of training

README.md

@@ -1,21 +1,22 @@
 ---
+license: unknown
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: ybelkada/falcon-7b-sharded-bf16
+base_model: tiiuae/falcon-11B
 model-index:
-- name: results
+- name: falcon2_guanaco
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# results
+# falcon2_guanaco
 
-This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
+This model is a fine-tuned version of [tiiuae/falcon-11B](https://huggingface.co/tiiuae/falcon-11B) on an unknown dataset.
 
 ## Model description
 
@@ -43,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 10
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -52,8 +53,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.7.2.dev0
-- Transformers 4.36.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.0
+- PEFT 0.11.2.dev0
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "base_model_name_or_path": "tiiuae/falcon-11B",
   "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": {},
@@ -20,10 +21,11 @@
   "revision": null,
   "target_modules": [
     "query_key_value",
-    "dense_4h_to_h",
     "dense",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6c5ddef636364bef3e0b130c7248ba8b25b9fddffdbe6ab2ae90cca57eec75
-size 522227376
+oid sha256:ac31ef1ec252339091ab4d16b5ca8b5a05c6c02684b29c656fe2f9446d4b5339
+size 912329728

runs/May28_02-50-04_8ac7dcedda8d/events.out.tfevents.1716864618.8ac7dcedda8d.217.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5741b5a8e970336f3ecf70d0dc836f0c1216ae05ef10cbe9d7f77c276ec45208
+size 16885

special_tokens_map.json

@@ -12,6 +12,13 @@
     ">>SUFFIX<<",
     ">>MIDDLE<<"
   ],
+  "bos_token": {
+    "content": ">>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -110,6 +115,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 500,
+      "content": ">>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,
@@ -155,6 +169,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       ">>TITLE<<": 0,
       ">>ABSTRACT<<": 1,

tokenizer_config.json

@@ -96,6 +96,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "500": {
+      "content": ">>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -111,9 +119,17 @@
     ">>SUFFIX<<",
     ">>MIDDLE<<"
   ],
+  "bos_token": ">>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: \n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ 'System: ' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Falcon:\n'  + message['content']}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Falcon:' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": true,
+  "device_map": "cuda:2",
   "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabcc1d61edf5c2326c342c0809acf4d925cf2a4c2f09ef4a0e9c259c76caf83
-size 4728
+oid sha256:01c5d62e82cd4c9f81d64135c00c4f3635a978975b236ee7c8b859ffdf0e66e2
+size 5112