Jais_AOU

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: inceptionai/jais-family-590m-chat
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Jais-AOU
+  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. -->
+
+# Jais-AOU
+
+This model is a fine-tuned version of [inceptionai/jais-family-590m-chat](https://huggingface.co/inceptionai/jais-family-590m-chat) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7540
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 1.1215        | 1.7699  | 50   | 1.1407          |
+| 0.5782        | 3.5398  | 100  | 0.8883          |
+| 0.3542        | 5.3097  | 150  | 0.7643          |
+| 0.2372        | 7.0796  | 200  | 0.7418          |
+| 0.203         | 8.8496  | 250  | 0.7372          |
+| 0.1891        | 10.6195 | 300  | 0.7540          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "inceptionai/jais-family-590m-chat",
+  "activation_function": "swiglu",
+  "alibi_scaling": null,
+  "architectures": [
+    "JAISLMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "inceptionai/jais-family-590m-chat--configuration_jais.JAISConfig",
+    "AutoModel": "inceptionai/jais-family-590m-chat--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "inceptionai/jais-family-590m-chat--modeling_jais.JAISLMHeadModel",
+    "AutoModelForQuestionAnswering": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForQuestionAnswering",
+    "AutoModelForSequenceClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForSequenceClassification",
+    "AutoModelForTokenClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForTokenClassification"
+  },
+  "bos_token_id": 84992,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 84993,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "mup_embeddings_scale": 9.1705785388303,
+  "mup_output_alpha": 1.09518349815769,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.16666666666666666,
+  "n_embd": 1536,
+  "n_head": 12,
+  "n_inner": 4096,
+  "n_layer": 18,
+  "n_positions": 2048,
+  "pad_token_id": 84993,
+  "position_embedding_type": "alibi",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "rotary_dim": null,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 84994
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 84992,
+  "eos_token_id": 84993,
+  "pad_token_id": 84993,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5e9e7edbe1f6ff7a92b445b992f766c1dd5d7efc4f87f72a2d80a5aec58e61
+size 3084462464

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84992": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84993": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa1c08a635b18c4ce16c2c0e96caa7ff062a7e1a374a4774f55f2e09adf53c4
+size 5432