Initial model upload

README.md

@@ -7,8 +7,6 @@ tags:
 model-index:
 - name: pythia_160m_sft
   results: []
-datasets:
-- tatsu-lab/alpaca_farm
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1033
+- Loss: 1.9831
 
 ## Model description
 
@@ -37,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 2e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -50,39 +48,39 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.3332        | 0.0889 | 100  | 2.2776          |
-| 2.3071        | 0.1778 | 200  | 2.2564          |
-| 2.2941        | 0.2667 | 300  | 2.2301          |
-| 2.2548        | 0.3556 | 400  | 2.2094          |
-| 2.2246        | 0.4444 | 500  | 2.1973          |
-| 2.2189        | 0.5333 | 600  | 2.1705          |
-| 2.181         | 0.6222 | 700  | 2.1498          |
-| 2.1515        | 0.7111 | 800  | 2.1399          |
-| 2.1333        | 0.8    | 900  | 2.1212          |
-| 2.1139        | 0.8889 | 1000 | 2.1050          |
-| 2.0778        | 0.9778 | 1100 | 2.0970          |
-| 1.8312        | 1.0667 | 1200 | 2.1071          |
-| 1.7405        | 1.1556 | 1300 | 2.1022          |
-| 1.7284        | 1.2444 | 1400 | 2.1049          |
-| 1.7554        | 1.3333 | 1500 | 2.1023          |
-| 1.732         | 1.4222 | 1600 | 2.0934          |
-| 1.7474        | 1.5111 | 1700 | 2.0917          |
-| 1.7495        | 1.6    | 1800 | 2.0820          |
-| 1.7449        | 1.6889 | 1900 | 2.0770          |
-| 1.7474        | 1.7778 | 2000 | 2.0708          |
-| 1.7447        | 1.8667 | 2100 | 2.0643          |
-| 1.7138        | 1.9556 | 2200 | 2.0550          |
-| 1.5662        | 2.0444 | 2300 | 2.1122          |
-| 1.4506        | 2.1333 | 2400 | 2.1203          |
-| 1.4282        | 2.2222 | 2500 | 2.1225          |
-| 1.4302        | 2.3111 | 2600 | 2.1173          |
-| 1.4471        | 2.4    | 2700 | 2.1156          |
-| 1.4217        | 2.4889 | 2800 | 2.1168          |
-| 1.428         | 2.5778 | 2900 | 2.1126          |
-| 1.4206        | 2.6667 | 3000 | 2.1059          |
-| 1.4315        | 2.7556 | 3100 | 2.1068          |
-| 1.4345        | 2.8444 | 3200 | 2.1037          |
-| 1.4034        | 2.9333 | 3300 | 2.1033          |
+| 2.2935        | 0.0889 | 100  | 2.1426          |
+| 2.153         | 0.1778 | 200  | 2.0977          |
+| 2.1432        | 0.2667 | 300  | 2.0771          |
+| 2.1131        | 0.3556 | 400  | 2.0633          |
+| 2.0885        | 0.4444 | 500  | 2.0510          |
+| 2.0956        | 0.5333 | 600  | 2.0403          |
+| 2.0647        | 0.6222 | 700  | 2.0354          |
+| 2.0498        | 0.7111 | 800  | 2.0273          |
+| 2.0317        | 0.8    | 900  | 2.0202          |
+| 2.0226        | 0.8889 | 1000 | 2.0150          |
+| 1.992         | 0.9778 | 1100 | 2.0114          |
+| 1.9639        | 1.0667 | 1200 | 2.0088          |
+| 1.9302        | 1.1556 | 1300 | 2.0051          |
+| 1.9381        | 1.2444 | 1400 | 2.0028          |
+| 1.9595        | 1.3333 | 1500 | 2.0009          |
+| 1.9325        | 1.4222 | 1600 | 1.9998          |
+| 1.9481        | 1.5111 | 1700 | 1.9981          |
+| 1.9572        | 1.6    | 1800 | 1.9956          |
+| 1.9456        | 1.6889 | 1900 | 1.9944          |
+| 1.9565        | 1.7778 | 2000 | 1.9922          |
+| 1.9507        | 1.8667 | 2100 | 1.9905          |
+| 1.9247        | 1.9556 | 2200 | 1.9881          |
+| 1.8998        | 2.0444 | 2300 | 1.9874          |
+| 1.9102        | 2.1333 | 2400 | 1.9873          |
+| 1.8842        | 2.2222 | 2500 | 1.9876          |
+| 1.876         | 2.3111 | 2600 | 1.9863          |
+| 1.9001        | 2.4    | 2700 | 1.9856          |
+| 1.8725        | 2.4889 | 2800 | 1.9859          |
+| 1.868         | 2.5778 | 2900 | 1.9845          |
+| 1.8803        | 2.6667 | 3000 | 1.9844          |
+| 1.9002        | 2.7556 | 3100 | 1.9838          |
+| 1.8941        | 2.8444 | 3200 | 1.9839          |
+| 1.8548        | 2.9333 | 3300 | 1.9831          |
 
 
 ### Framework versions
@@ -90,4 +88,4 @@ The following hyperparameters were used during training:
 - Transformers 4.46.2
 - Pytorch 2.5.1+cu121
 - Datasets 3.1.0
-- Tokenizers 0.20.3
+- Tokenizers 0.20.3

logs/events.out.tfevents.1731925396.05fd0bfb43a8.1118.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf7485b9b2815e9a1d2a4fdbbb5b20b745cda81a8a88da56e9aed9d73315d75
+size 21431

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b159c840b2d0d830eb19dafbd2cba433d820d7cdb45dfc0d811c0c80ee9e5c
+oid sha256:b16010f6fd8175f9600a0d54e1a8ffc3ac56d6a3f94c4f9f1f09a105106b9c8c
 size 649308728

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a25a53601ab9c07d6da59917595cc80b6bdb83ae8c0bbbe5dddfc9052d7ad4d
+oid sha256:3c05d15220df0d64e6af2e9e631e0c6bb6cedad273a907d2ae742da96528a778
 size 5240