Model save

README.md

@@ -5,7 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: vilsonrodrigues/falcon-7b-instruct-sharded
+base_model: tiiuae/falcon-7b
 model-index:
 - name: falcon7binstruct
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # falcon7binstruct
 
-This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on the None dataset.
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
 
 ## Model description
 
@@ -47,10 +47,14 @@ The following hyperparameters were used during training:
 - training_steps: 10
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### 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 0.9.1.dev0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
+  "base_model_name_or_path": "tiiuae/falcon-7b",
   "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": {},
@@ -19,11 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "dense",
     "dense_4h_to_h",
-    "query_key_value"
+    "query_key_value",
+    "dense_h_to_4h"
   ],
   "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 sha256:5967403586bbf8b5c66aabb2475c8cec61035cf4e1cb75cc2c4cb9c32ad60fcb
+oid sha256:a031bb464b6a0305756a52f74c1810ba5c3f2108a201b6f962628d638091cae7
 size 130583912

runs/Mar16_04-01-53_0bc99fd71e10/events.out.tfevents.1710561746.0bc99fd71e10.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7942ca6d75985a0fcc6863bdd1dcd87517b20fa88b709ba2c28fb5dfa8838fba
+size 11707

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d061ff7501cef667fce3218cf66f5de86959968a038ae3ec253026a3e5ee8545
-size 4792
+oid sha256:565de370674ac9fedf70cd360599dbfb92c90f74bc34691d31c6396df6c8456d
+size 4920