Upload 7 files

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T
+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 [TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9391
+
+## 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: 6
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 36
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.388         | 0.03  | 30   | 2.3495          |
+| 2.3877        | 0.05  | 60   | 2.2353          |
+| 2.1812        | 0.08  | 90   | 2.1786          |
+| 2.1711        | 0.1   | 120  | 2.1453          |
+| 2.098         | 0.13  | 150  | 2.1210          |
+| 2.0884        | 0.15  | 180  | 2.1037          |
+| 2.0129        | 0.18  | 210  | 2.0894          |
+| 2.0921        | 0.2   | 240  | 2.0765          |
+| 2.001         | 0.23  | 270  | 2.0648          |
+| 2.0986        | 0.25  | 300  | 2.0550          |
+| 2.0128        | 0.28  | 330  | 2.0458          |
+| 2.1144        | 0.3   | 360  | 2.0385          |
+| 2.0711        | 0.33  | 390  | 2.0308          |
+| 1.9607        | 0.36  | 420  | 2.0239          |
+| 1.9092        | 0.38  | 450  | 2.0179          |
+| 2.1955        | 0.41  | 480  | 2.0121          |
+| 2.0293        | 0.43  | 510  | 2.0063          |
+| 2.0482        | 0.46  | 540  | 2.0017          |
+| 2.0518        | 0.48  | 570  | 2.0036          |
+| 1.9647        | 0.51  | 600  | 1.9984          |
+| 2.0573        | 0.53  | 630  | 1.9938          |
+| 1.9912        | 0.56  | 660  | 1.9879          |
+| 1.9836        | 0.58  | 690  | 1.9866          |
+| 1.9514        | 0.61  | 720  | 1.9834          |
+| 1.9413        | 0.63  | 750  | 1.9792          |
+| 1.9775        | 0.66  | 780  | 1.9726          |
+| 1.9499        | 0.69  | 810  | 1.9690          |
+| 2.0497        | 0.71  | 840  | 1.9663          |
+| 2.0045        | 0.74  | 870  | 1.9636          |
+| 2.0324        | 0.76  | 900  | 1.9605          |
+| 1.9913        | 0.79  | 930  | 1.9574          |
+| 1.9861        | 0.81  | 960  | 1.9553          |
+| 1.8449        | 0.84  | 990  | 1.9527          |
+| 1.9932        | 0.86  | 1020 | 1.9502          |
+| 1.9845        | 0.89  | 1050 | 1.9485          |
+| 2.0407        | 0.91  | 1080 | 1.9494          |
+| 1.9496        | 0.94  | 1110 | 1.9448          |
+| 1.9851        | 0.97  | 1140 | 1.9406          |
+| 1.9856        | 0.99  | 1170 | 1.9391          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T",
+  "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": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "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 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "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:ba0b44e6028f697a6c4c5c016228e2bb745c6c169c75b806e45fcb643049ac9a
+size 2200159833

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 +1,44 @@
+{
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "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
+}