VTSNLP/base_LLM_RAW_200M

README.md

@@ -0,0 +1,51 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: base_LLM_RAW_200M
+  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_RAW_200M
+
+This model was trained from scratch 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": "base_LLM_200M/checkpoint-755000",
+  "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 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.40.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a96ca2c63db07fabb703beced8b0571f223d070f4d81b0641bf72b1da637ae
+size 733826032

runs/Sep30_02-51-31_kao-dgxa-e10-u17/events.out.tfevents.1727661183.kao-dgxa-e10-u17.3914059.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526c0baa0309a7a6f39a7e165a281f8c5690b669dd22ebb3b72260ff1776afcc
+size 9544

runs/Sep30_03-02-52_kao-dgxa-e10-u17/events.out.tfevents.1727661782.kao-dgxa-e10-u17.3914059.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45ab86c303c8bbd2f926b7c65328c57e0c3e6e2b4371140033e4a8ec9db0bfe
+size 13153

runs/Sep30_03-15-41_kao-dgxa-e10-u17/events.out.tfevents.1727662566.kao-dgxa-e10-u17.3914059.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d877d34c46aabd5c7471c80661ac13c478bbc5ca51799fe398f5f705230e729
+size 7159

runs/Sep30_03-17-23_kao-dgxa-e10-u17/events.out.tfevents.1727662660.kao-dgxa-e10-u17.3914059.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68ea7dc08aa90416a3f3d255fbf5a13704e1215fe895c813a6d91e68a64c26c
+size 111831

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56b3d70273091e79d19bbd3a7ed681052462b54a632f73912584616de7f7415
+size 5112