haha upload

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T
+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 [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2355
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.4654        | 0.0   | 1     | 3.5326          |
+| 1.2162        | 0.05  | 1503  | 1.9335          |
+| 1.1918        | 0.1   | 3006  | 1.7391          |
+| 1.4188        | 0.15  | 4509  | 1.7574          |
+| 1.8281        | 0.2   | 6012  | 1.6704          |
+| 0.8639        | 0.25  | 7515  | 1.7459          |
+| 1.3764        | 0.3   | 9018  | 1.6832          |
+| 2.1172        | 0.35  | 10521 | 1.6398          |
+| 1.1855        | 0.4   | 12024 | 1.6007          |
+| 1.5604        | 0.45  | 13527 | 1.5256          |
+| 1.0224        | 0.5   | 15030 | 1.4891          |
+| 1.5582        | 0.55  | 16533 | 1.4903          |
+| 0.9489        | 0.6   | 18036 | 1.4179          |
+| 1.67          | 0.65  | 19539 | 1.4585          |
+| 0.8542        | 0.7   | 21042 | 1.3810          |
+| 1.5301        | 0.75  | 22545 | 1.3645          |
+| 0.951         | 0.8   | 24048 | 1.3087          |
+| 1.1791        | 0.85  | 25551 | 1.3018          |
+| 1.3342        | 0.9   | 27054 | 1.2595          |
+| 1.1221        | 0.95  | 28557 | 1.2355          |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.6
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T",
+  "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": 4096,
+  "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": "float16",
+  "transformers_version": "4.34.0",
+  "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": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb450416fca5bb813d12ad24917c24838f6e1068946dbed33d1bb338e752641c
+size 2200123773

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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>",
+  "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",
+  "tokenizer_file": "/root/.cache/huggingface/hub/models--PY007--TinyLlama-1.1B-intermediate-step-715k-1.5T/snapshots/314e0f65d90384e224ac8d7c0b228a661a06673f/tokenizer.json",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}