add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: distilgpt2-finetuned-tamil-gpt
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- 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. -->
+
+# distilgpt2-finetuned-tamil-gpt
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.4097
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 228  | 4.4097          |
+| No log        | 2.0   | 456  | 4.4097          |
+| 4.3169        | 3.0   | 684  | 4.4097          |
+| 4.3169        | 4.0   | 912  | 4.4097          |
+| 4.3116        | 5.0   | 1140 | 4.4097          |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fe69f1ac4164e7171fa0ea0a687ec9258dda97a23d95552cd033db2679277e
+size 333972957

runs/Aug16_14-21-07_02119d6be1fb/1629123711.8741536/events.out.tfevents.1629123711.02119d6be1fb.63.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bcbe796bdb5cc0d15c278f80d51b395d2ef89776def7af667b3fa03039a6c74
+size 4191

runs/Aug16_14-21-07_02119d6be1fb/1629123815.9251168/events.out.tfevents.1629123815.02119d6be1fb.63.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07cf189cde5aff58d2c9b00da01be1b0007a52d8d83a467a5616e70d6148ff2
+size 4191

runs/Aug16_14-21-07_02119d6be1fb/events.out.tfevents.1629123711.02119d6be1fb.63.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38562fd45529460743fa9bf978aae8c24c2c64e9351cb35c784e7f320ff0f81
+size 5273

runs/Aug16_14-21-07_02119d6be1fb/events.out.tfevents.1629123815.02119d6be1fb.63.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b335a0f46d8e55bf505c8a94884f83b9e069149d22c843038c55f913df5eb09
+size 5301

runs/Aug16_14-21-07_02119d6be1fb/events.out.tfevents.1629123937.02119d6be1fb.63.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a41a3fcbb75ef962ccdf5eafc8a5629e016eac3c400c375d497bfede5faca6
+size 311

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63241265f296613152b584418824506201a474ec6fbfcd9cb0f35b9b96c020b3
+size 2671