初始化项目，由ModelHub XC社区提供模型

Model: babylm-anon/rta
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: babylm-base5M-gpt2
+  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. -->
+
+# babylm-base5M-gpt2 (Fork with chck_100M Checkpoint)
+
+This repository is a fork of [alexandertam/babylm-base5m-gpt2](https://huggingface.co/alexandertam/babylm-base5m-gpt2), created for the [BabyLM Challenge 2025](https://babylm.github.io/) submission. 
+It extends the original model by including an additional checkpoint (`chck_100M`), adhering to the challenge's guidelines.
+
+## Model Description
+
+This model is a pre-trained version of the GPT-2 architecture.
+It achieves the following results on the evaluation set:
+- Loss: 3.0628
+- Accuracy: 0.4521
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 190
+- training_steps: 19000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| 5.579         | 0.1024 | 200   | 4.7677          | 0.3189   |
+| 4.7716        | 0.2048 | 400   | 4.3385          | 0.3544   |
+| 4.5162        | 0.3072 | 600   | 4.1772          | 0.3593   |
+| 4.4056        | 0.4096 | 800   | 4.0754          | 0.3693   |
+| 4.3138        | 0.5120 | 1000  | 4.0143          | 0.3626   |
+| 4.2148        | 0.6144 | 1200  | 3.9601          | 0.3554   |
+| 4.1925        | 0.7168 | 1400  | 3.9019          | 0.3723   |
+| 4.0293        | 0.8193 | 1600  | 3.8579          | 0.3749   |
+| 3.9407        | 0.9217 | 1800  | 3.8101          | 0.3782   |
+| 3.8371        | 1.0241 | 2000  | 3.7870          | 0.3721   |
+| 3.0659        | 2.0481 | 4000  | 3.4672          | 0.4085   |
+| 2.6866        | 3.0722 | 6000  | 3.2850          | 0.4316   |
+| 2.5063        | 4.0963 | 8000  | 3.1963          | 0.4372   |
+| 2.4139        | 5.1203 | 10000 | 3.1406          | 0.4442   |
+| 2.3246        | 6.1444 | 12000 | 3.1152          | 0.4484   |
+| 2.3111        | 7.1685 | 14000 | 3.0879          | 0.4489   |
+| 2.2761        | 8.1925 | 16000 | 3.0668          | 0.4542   |
+| 2.2231        | 9.2166 | 18000 | 3.0695          | 0.4517   |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.4

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.728622631848438,
+    "eval_accuracy": 0.45214562944577746,
+    "eval_loss": 3.0628035068511963,
+    "eval_runtime": 95.1631,
+    "eval_samples": 33544,
+    "eval_samples_per_second": 352.49,
+    "eval_steps_per_second": 22.036,
+    "perplexity": 21.38743300660324,
+    "total_flos": 7.9413964701696e+16,
+    "train_loss": 2.775124670731394,
+    "train_runtime": 3271.669,
+    "train_samples": 31240,
+    "train_samples_per_second": 92.919,
+    "train_steps_per_second": 5.807
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "use_cache": true,
+  "vocab_size": 16384
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 9.728622631848438,
+    "eval_accuracy": 0.45214562944577746,
+    "eval_loss": 3.0628035068511963,
+    "eval_runtime": 95.1631,
+    "eval_samples": 33544,
+    "eval_samples_per_second": 352.49,
+    "eval_steps_per_second": 22.036,
+    "perplexity": 21.38743300660324
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.50.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ef61138a105c85ceffe6b6f43295e1227d2edb594f4b906933ab8302486203
+size 393716352

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": null,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": null,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": null,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.728622631848438,
+    "total_flos": 7.9413964701696e+16,
+    "train_loss": 2.775124670731394,
+    "train_runtime": 3271.669,
+    "train_samples": 31240,
+    "train_samples_per_second": 92.919,
+    "train_steps_per_second": 5.807
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d250537b2585c6d06b8b0dcfae2c77def32b4b994aeb860086cca09095186307
+size 5841