Upload 7 files

README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+base_model: princeton-nlp/Sheared-LLaMA-1.3B
+tags:
+- generated_from_trainer
+model-index:
+- name: out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# out
+
+This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5764
+
+## 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: 2.5e-05
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 9
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0341        | 0.03  | 30   | 1.7322          |
+| 1.7952        | 0.05  | 60   | 1.7122          |
+| 1.8476        | 0.08  | 90   | 1.7011          |
+| 2.1762        | 0.1   | 120  | 1.6919          |
+| 2.0459        | 0.13  | 150  | 1.6838          |
+| 1.7417        | 0.16  | 180  | 1.6761          |
+| 1.7508        | 0.18  | 210  | 1.6685          |
+| 1.8539        | 0.21  | 240  | 1.6612          |
+| 1.7672        | 0.24  | 270  | 1.6559          |
+| 1.7327        | 0.26  | 300  | 1.6521          |
+| 1.9346        | 0.29  | 330  | 1.6458          |
+| 1.8972        | 0.31  | 360  | 1.6432          |
+| 1.545         | 0.34  | 390  | 1.6394          |
+| 1.6737        | 0.37  | 420  | 1.6351          |
+| 1.9233        | 0.39  | 450  | 1.6305          |
+| 1.6822        | 0.42  | 480  | 1.6274          |
+| 1.3781        | 0.44  | 510  | 1.6243          |
+| 1.8232        | 0.47  | 540  | 1.6209          |
+| 1.6995        | 0.5   | 570  | 1.6178          |
+| 1.9164        | 0.52  | 600  | 1.6145          |
+| 1.8104        | 0.55  | 630  | 1.6116          |
+| 1.9563        | 0.58  | 660  | 1.6098          |
+| 1.9536        | 0.6   | 690  | 1.6063          |
+| 1.9269        | 0.63  | 720  | 1.6043          |
+| 1.6234        | 0.65  | 750  | 1.6026          |
+| 1.7635        | 0.68  | 780  | 1.5994          |
+| 1.2534        | 0.71  | 810  | 1.5966          |
+| 1.8849        | 0.73  | 840  | 1.5951          |
+| 1.8618        | 0.76  | 870  | 1.5925          |
+| 1.8688        | 0.79  | 900  | 1.5896          |
+| 1.9419        | 0.81  | 930  | 1.5877          |
+| 1.637         | 0.84  | 960  | 1.5878          |
+| 1.4612        | 0.86  | 990  | 1.5848          |
+| 1.5509        | 0.89  | 1020 | 1.5832          |
+| 1.706         | 0.92  | 1050 | 1.5816          |
+| 1.8552        | 0.94  | 1080 | 1.5797          |
+| 1.7589        | 0.97  | 1110 | 1.5791          |
+| 1.4988        | 0.99  | 1140 | 1.5764          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eae6dc609e085b5f005091644a3edb30afbe41c2d85d5a031a9d9969829484b
+size 2690915481

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

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
+    }
+  },
+  "bos_token": "<s>",
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}