Model save

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
 tags:
 - trl
 - sft
@@ -15,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model was trained from scratch on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3747
+- Loss: 0.9156
 
 ## Model description
 
@@ -36,14 +38,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 8
-- eval_batch_size: 4
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
@@ -53,12 +55,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8468        | 1.0   | 212  | 1.3747          |
+| 0.9189        | 1.0   | 1107 | 0.9156          |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.39.3
 - Pytorch 2.1.2+cu118
 - Datasets 2.16.1
 - Tokenizers 0.15.2

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "transformers_version": "4.38.2"
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc7cb9e4badbf8993c1426656d83a5ae438c39b7ded5e918ff101906d47cdf44
-size 4943178720
+oid sha256:97bc9ba5fda3820613528c7020adc08e0324d9d17eb34b2df064f9466c077ab6
+size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012a56111d83215c50a688f649ae445d3835d2ff9e1c35dde0ef9d90a163150f
+oid sha256:6465729604922a61a5823ced600e8f4687c65d7d905528cc934843c6815fcdc8
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676c1a2fb57fd3e8f69cd479063cc2c9c72dade61e81cb89f912f0d42442068c
-size 4540532728
+oid sha256:e4f90c8a0b887397147f13592416daeda1551a36a7951d8b609a064cfe8cd8aa
+size 4540516344

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483496960
+    "total_size": 14483464192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

runs/Jun12_23-56-37_n136-129-074/events.out.tfevents.1718210521.n136-129-074.3717215.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd40992adc7954210a53463a6b9f1515ebb3d374c7951c7b3f3bcc8940690f82
-size 51281
+oid sha256:7f2aed5119ca9a8d3b598059ce7b678e97182c035a061146d7524dfba04d893c
+size 52117