adity12345/chakma-gpt2

README.md

@@ -0,0 +1,47 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: chakma_model
+  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. -->
+
+# chakma_model
+
+This model is a fine-tuned version of [](https://huggingface.co/) 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: 0.0005
+- train_batch_size: 16
+- eval_batch_size: 8
+- 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
+- num_epochs: 5
+
+### Framework versions
+
+- Transformers 4.55.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 256,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 512,
+  "pad_token_id": 3,
+  "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": "4.55.1",
+  "use_cache": true,
+  "vocab_size": 3286
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 3,
+  "transformers_version": "4.55.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30cf74947ca0f710fa62168bdcca47243c1a7443e42060522983bbf6ceb89765
+size 16532464

runs/Aug17_11-36-59_b9dde2d71266/events.out.tfevents.1755430619.b9dde2d71266.1253.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35fbb769eb6cbe6676a3183a6df409811f5b322fb14adf38f54160cc0caafcb
+size 5102

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ec9e72748b06feee903543b90878d255a5456a739a8c8ec8f63d07686db834
+size 5304