VTSNLP/base_LLM_CAC_200M_final

README.md

@@ -0,0 +1,52 @@
+---
+base_model: wanderer2k1/base_LLM_183MB_concat_and_chunk
+tags:
+- generated_from_trainer
+model-index:
+- name: base_LLM_CAC_200M_final
+  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. -->
+
+# base_LLM_CAC_200M_final
+
+This model is a fine-tuned version of [wanderer2k1/base_LLM_183MB_concat_and_chunk](https://huggingface.co/wanderer2k1/base_LLM_183MB_concat_and_chunk) on an unknown dataset.
+
+## 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: 3.6e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "wanderer2k1/base_LLM_183MB_concat_and_chunk",
+  "abili": false,
+  "architectures": [
+    "MptForCausalLM"
+  ],
+  "attn_config": {
+    "model_type": ""
+  },
+  "d_model": 768,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "init_device": "cpu",
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 8192,
+  "model_type": "mpt",
+  "n_heads": 12,
+  "n_layers": 12,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "pad_token_id": 128001,
+  "resid_pdrop": 0.0,
+  "rope": true,
+  "rope_theta": 100000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 128009,
+  "transformers_version": "4.40.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c603f5d0dc1fb1e4c8fbdab928589f2843f15fb7c77ce5e7d2b6d2ea6b8682
+size 733826032

runs/Oct21_03-06-18_kao-dgxa-e10-u17/events.out.tfevents.1729476401.kao-dgxa-e10-u17.1154007.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c45ba1ea41565032953f286357106931bd6e423cddebe3aaf895ddc74f4bb20
+size 63347

runs/Oct21_04-52-08_kao-dgxa-e10-u17/events.out.tfevents.1729482743.kao-dgxa-e10-u17.1702577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9743d756a25518a2429bd768c7ddedad485ec53788e15c2b4afcc55b326e7e89
+size 111867

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d80f14de7317e70641db54a6a3284168a487ad2ebb942ee34cedc1c12c42ca
+size 5112