mistral-neo-v0.01

README.md

@@ -5,9 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- generator
-base_model: mistralai/Mixtral-8x7B-v0.1
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
 model-index:
 - name: Mixtral_Alpace_v2
   results: []
@@ -18,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mixtral_Alpace_v2
 
-This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4367
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the None dataset.
 
 ## Model description
 
@@ -40,49 +36,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2.5e-05
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 0.03
-- training_steps: 250
+- training_steps: 8
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.9894        | 0.01  | 10   | 2.0548          |
-| 1.8953        | 0.03  | 20   | 1.9843          |
-| 1.8277        | 0.04  | 30   | 1.8909          |
-| 1.7951        | 0.05  | 40   | 1.8240          |
-| 1.7125        | 0.06  | 50   | 1.7710          |
-| 1.65          | 0.08  | 60   | 1.7196          |
-| 1.6006        | 0.09  | 70   | 1.6751          |
-| 1.5773        | 0.1   | 80   | 1.6351          |
-| 1.5904        | 0.11  | 90   | 1.5976          |
-| 1.5122        | 0.13  | 100  | 1.5603          |
-| 1.4715        | 0.14  | 110  | 1.5330          |
-| 1.481         | 0.15  | 120  | 1.5132          |
-| 1.4293        | 0.16  | 130  | 1.4993          |
-| 1.4464        | 0.18  | 140  | 1.4872          |
-| 1.4326        | 0.19  | 150  | 1.4764          |
-| 1.4018        | 0.2   | 160  | 1.4674          |
-| 1.3775        | 0.21  | 170  | 1.4611          |
-| 1.4324        | 0.23  | 180  | 1.4554          |
-| 1.3947        | 0.24  | 190  | 1.4506          |
-| 1.3759        | 0.25  | 200  | 1.4467          |
-| 1.3792        | 0.26  | 210  | 1.4429          |
-| 1.3784        | 0.28  | 220  | 1.4402          |
-| 1.3762        | 0.29  | 230  | 1.4383          |
-| 1.3918        | 0.3   | 240  | 1.4371          |
-| 1.3394        | 0.31  | 250  | 1.4367          |
 
 
 ### Framework versions
 
 - PEFT 0.7.1
-- Transformers 4.36.2
+- Transformers 4.37.1
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
-    "gate_proj",
-    "o_proj",
     "k_proj",
-    "lm_head",
+    "q_proj",
     "down_proj",
-    "q_proj"
+    "lm_head",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:60b6e49810e5dc54e2eea44a77e013ecf9c3e727bd5c04a3535824030bd804c3
+size 751667752

runs/Jan29_02-18-39_3bfcd385ea78/events.out.tfevents.1706497940.3bfcd385ea78.4670.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362b9de978cc9c24b93ae98fa538713c3857c1cacab2ec8e822ac8dfaa812752
+size 4869

runs/Jan29_03-30-47_3bfcd385ea78/events.out.tfevents.1706499146.3bfcd385ea78.37969.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99aa0855218216f563766862402604c4d6dec85ca4988eb0bb77ac193993c86f
+size 5833

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Left",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -29,6 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d475c228645c8734b8c51f5803623fa6c4b04984c7eb91d0ac76d5dbb338c5
+oid sha256:0855712b68966787a349fe1324845f731daf4e4a02486dcfa24dc6eca2110d7a
 size 4728