ai-maker-space/mistral-7binstruct-summary-100s

README.md

@@ -5,9 +5,9 @@ tags:
 - trl
 - sft
 - generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
 - generator
-base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: mistral7binstruct_summarize
   results: []
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4176
+- Loss: 1.4169
 
 ## Model description
 
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.5808        | 0.21  | 25   | 1.4563          |
-| 1.4635        | 0.42  | 50   | 1.4176          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6064        | 0.2101 | 25   | 1.4635          |
+| 1.4562        | 0.4202 | 50   | 1.4169          |
 
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e745d7b79b531c8b31b019ccf7f4bc5500058f4ea86f7382692dec304b826c
+oid sha256:5a507365e6e361577f2abbb6ce00d9b7aed703670f24ac639f0b5434ae89f257
 size 27280152

runs/Apr23_16-55-17_71eb89c5adc3/events.out.tfevents.1713891347.71eb89c5adc3.4267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad3ccb2a3e0324b096a8dfca2a80129d14f665c5cfea526559f696baf1c9c5e
+size 7112

tokenizer.json

@@ -134,6 +134,7 @@
     "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:c29a700648382a7b078a255a073ce9430583ef465454c0d783a088d6b5a25818
-size 4920
+oid sha256:7f79f912866ae220a76f4fe7b451a8659801c11b9f6a0ed238e73155998ba27c
+size 4984