tigerbhai/mistral-texmin-generation

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+model-index:
+- name: mistral_texmin_generation
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mistral_texmin_generation
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0188
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4867        | 1.05  | 20   | 0.2200          |
+| 0.0692        | 2.11  | 40   | 0.0339          |
+| 0.0153        | 3.16  | 60   | 0.0216          |
+| 0.0082        | 4.21  | 80   | 0.0200          |
+| 0.0066        | 5.26  | 100  | 0.0188          |
+
+
+### Framework versions
+
+- PEFT 0.7.0
+- Transformers 4.36.0
+- Pytorch 2.1.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13681324ed6a61b945a5d7ad0e687b9734d31a6987f95de51073438d28117912
+size 109069176

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2023-12-12T10:43:57,codecarbon,13659cc8-98ed-4c0e-9d48-4ae6ddb3f54c,520.3776621818542,0.0637235308693738,0.000122456314904433,85.61359180743857,339.371,141.57511711120605,0.012249414379245885,0.06738561938377176,0.02037333255833762,0.10000836632135526,India,IND,,,,Linux-5.15.0-1041-nvidia-x86_64-with-glibc2.35,3.10.12,2.2.3,128,AMD EPYC 7742 64-Core Processor,4,4 x NVIDIA A100-SXM4-40GB,79.0011,21.9974,377.5336456298828,machine,N,1.0

runs/Dec12_09-23-50_d8955a52ad75/events.out.tfevents.1702373049.d8955a52ad75.5388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5beb6a70d6a4572adc055c5ad566e3372d96bbc5f653f09d67324ea5b871b552
+size 4808

runs/Dec12_09-41-45_d8955a52ad75/events.out.tfevents.1702374110.d8955a52ad75.9734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8f3ee0517d79d528d02ac09fb8efabd9a11d6004abf8939e214429c1806faf
+size 4808

runs/Dec12_10-23-24_d8955a52ad75/events.out.tfevents.1702376618.d8955a52ad75.10648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60d83e35ded378f78422556cff90500dc9d91d1db86a0602732e70e2de78181
+size 4184

runs/Dec12_10-26-07_d8955a52ad75/events.out.tfevents.1702376773.d8955a52ad75.11093.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83fc49af47333e71d4b1f952cb7bdb6df41b2304f7e2aa18bf740701f075e21
+size 4808

runs/Dec12_10-30-07_d8955a52ad75/events.out.tfevents.1702377012.d8955a52ad75.11703.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f79efdd79c4e5e5090ac6297d9b9469e67c4e5fafa72b01451712885b29149
+size 8026

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac95f528ff265269ce3426d0f3050aae56e99033d5314835f17954ad5abe4bd
+size 4728