Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: cyberagent/calm2-7b-chat
+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 [cyberagent/calm2-7b-chat](https://huggingface.co/cyberagent/calm2-7b-chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2941
+
+## 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: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 6
+- total_eval_batch_size: 3
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.5899        | 0.0   | 1    | 4.1781          |
+| 3.4689        | 0.05  | 352  | 3.5988          |
+| 3.519         | 0.1   | 704  | 3.6209          |
+| 3.4168        | 0.15  | 1056 | 3.6161          |
+| 3.4906        | 0.2   | 1408 | 3.6054          |
+| 3.4853        | 0.25  | 1760 | 3.5950          |
+| 3.475         | 0.3   | 2112 | 3.5806          |
+| 3.2476        | 0.35  | 2464 | 3.5675          |
+| 3.2339        | 0.4   | 2816 | 3.5398          |
+| 3.3711        | 0.45  | 3168 | 3.5233          |
+| 3.4195        | 0.5   | 3520 | 3.5006          |
+| 3.1105        | 0.55  | 3872 | 3.4804          |
+| 3.2477        | 0.6   | 4224 | 3.4546          |
+| 3.2753        | 0.65  | 4576 | 3.4311          |
+| 3.1867        | 0.7   | 4928 | 3.4054          |
+| 3.2009        | 0.75  | 5280 | 3.3783          |
+| 3.1037        | 0.8   | 5632 | 3.3509          |
+| 3.0394        | 0.85  | 5984 | 3.3314          |
+| 3.0759        | 0.9   | 6336 | 3.3095          |
+| 3.1989        | 0.95  | 6688 | 3.2941          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "cyberagent/calm2-7b-chat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86777aa7f151785d50e9b81bbbf8ad2484d6bee18618a77dc33d533354c0eac0
+size 14017936677

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "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 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<|endoftext|>",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86756e665c69be190c3de2e236f3cb1a2a4bdb410bba7277fd198efa1b9a6a27
+size 6011