Model save

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [imone/Mistral_7B_with_EOT_token](https://huggingface.co/imone/Mistral_7B_with_EOT_token) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1581
+- Loss: 0.3755
 
 ## Model description
 
@@ -38,7 +38,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6823        | 1.0   | 565  | 0.6283          |
-| 0.4922        | 2.0   | 1130 | 0.3859          |
-| 0.3003        | 3.0   | 1695 | 0.2350          |
-| 0.1776        | 4.0   | 2260 | 0.1633          |
-| 0.0793        | 5.0   | 2825 | 0.1581          |
+| 0.6331        | 1.0   | 578  | 0.6226          |
+| 0.51          | 2.0   | 1156 | 0.5023          |
+| 0.4058        | 3.0   | 1734 | 0.4172          |
+| 0.3003        | 4.0   | 2312 | 0.3773          |
+| 0.2508        | 5.0   | 2890 | 0.3755          |
 
 
 ### Framework versions
 
 - Transformers 4.40.0
 - Pytorch 2.1.2+cu118
-- Datasets 2.18.0
+- Datasets 2.19.0
 - Tokenizers 0.19.1

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 32002
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e38b93eb70a75bc1796a88024daae87822fa1048c276914b3345c1124fa371
+oid sha256:8a62c7f0a48449d090c54d4bb46049f0dba2babc8fc1e00e98fdd334183666f5
 size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8587edd9d1965007b93ecb6e6421384db0ce99dfc1eaa7a6f08f8ea8d4dbe76d
+oid sha256:02ba273e64ba948c6535ea2b1089d40576e4d52c037dfd8264be5021a989cacd
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59633e4e185330e9e5536ea22a6271ef1271c28f0017b294871f73c659a92a8f
+oid sha256:d67f94a9e1ee902ae2a0bc9a88ec88b9c931c92c8a2e88ce5c4fad33b59f8305
 size 4540532728

runs/Apr21_16-57-33_n136-128-070/events.out.tfevents.1713690007.n136-128-070.635588.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b50fb6ca7ab966e776262311b335dc80a6b4de8821c24346208bc7e6db2604
-size 111561
+oid sha256:515bb24c66f59ef3875088ebd7aba3d82b86039f33d9b2c6ddc0fbc2a29831c0
+size 128644

tokenizer.json

@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2439ae44006335aa0679b1679283eb7a0b006f5aa83a449c51ed6fc11b9455e
-size 6136
+oid sha256:aa332ee855a131766188374f885382875a0b64d355e2f53480c7a0d2aede4e5f
+size 6200