llama2-supervised-ft-5epochs

README.md

@@ -0,0 +1,83 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: Trelis/Llama-2-7b-chat-hf-sharded-bf16
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [Trelis/Llama-2-7b-chat-hf-sharded-bf16](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-sharded-bf16) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1986
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.591         | 0.23  | 4    | 2.3712          |
+| 2.6663        | 0.46  | 8    | 2.3530          |
+| 2.4782        | 0.69  | 12   | 2.3351          |
+| 2.2831        | 0.91  | 16   | 2.3186          |
+| 2.4023        | 1.14  | 20   | 2.3037          |
+| 2.2617        | 1.37  | 24   | 2.2902          |
+| 2.2799        | 1.6   | 28   | 2.2779          |
+| 2.3633        | 1.83  | 32   | 2.2665          |
+| 2.2249        | 2.06  | 36   | 2.2560          |
+| 2.5186        | 2.29  | 40   | 2.2464          |
+| 2.4234        | 2.51  | 44   | 2.2379          |
+| 2.26          | 2.74  | 48   | 2.2303          |
+| 2.2937        | 2.97  | 52   | 2.2237          |
+| 2.3681        | 3.2   | 56   | 2.2179          |
+| 2.095         | 3.43  | 60   | 2.2129          |
+| 2.1456        | 3.66  | 64   | 2.2087          |
+| 2.4307        | 3.89  | 68   | 2.2053          |
+| 2.2769        | 4.11  | 72   | 2.2025          |
+| 2.3649        | 4.34  | 76   | 2.2005          |
+| 2.3577        | 4.57  | 80   | 2.1992          |
+| 2.1575        | 4.8   | 84   | 2.1986          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trelis/Llama-2-7b-chat-hf-sharded-bf16",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd60a3d7392d23dd321852d451e4f83d01000f6df1f6fb40002ed5071608111
+size 159967880

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

runs/Feb08_03-00-07_7fcdef0775c2/events.out.tfevents.1707361209.7fcdef0775c2.412.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f3c8628765c3ebe4557a8990e9205527af1e8b84e973c21f88118729313c6d
+size 12058

runs/Feb08_03-16-29_7fcdef0775c2/events.out.tfevents.1707362191.7fcdef0775c2.5984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb54ec22f85caf0ab39857b77230bb0bd5da18fd7080cfde9cfacf0851f3064
+size 5060

runs/Feb08_03-20-05_7fcdef0775c2/events.out.tfevents.1707362407.7fcdef0775c2.6851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75427bdc34b9f43cdcbc52df436c476c946bf896c9e74471b5afa7a5241f62f0
+size 12058

runs/Feb08_05-13-45_7fcdef0775c2/events.out.tfevents.1707369227.7fcdef0775c2.33338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff327f6f57abcf0a52f504f68fc74abecebebbd793c7f52d3bd8f2569b9d2b8
+size 10659

runs/Feb08_05-29-54_7fcdef0775c2/events.out.tfevents.1707370195.7fcdef0775c2.40218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebec7ca3ec0e50ad2d7034f9d36c466663487742c19a824f20567fc51b48372
+size 23929

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a347c11818060515daa22efc2808605735815351a1166cecf871f4c53ff334
+size 4728