Training in progress, step 500

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: mit
+base_model: danghuy1999/gpt2-viwiki
+tags:
+- generated_from_trainer
+model-index:
+- name: vietnamese-poem-gpt2-sauchu
+  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. -->
+
+# vietnamese-poem-gpt2-sauchu
+
+This model is a fine-tuned version of [danghuy1999/gpt2-viwiki](https://huggingface.co/danghuy1999/gpt2-viwiki) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.9586
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use 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: 500
+- num_epochs: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 17   | 7.5820          |
+| No log        | 2.0   | 34   | 7.2608          |
+| No log        | 3.0   | 51   | 6.9590          |
+| No log        | 4.0   | 68   | 6.7325          |
+| No log        | 5.0   | 85   | 6.5588          |
+| No log        | 6.0   | 102  | 6.4239          |
+| No log        | 7.0   | 119  | 6.3150          |
+| No log        | 8.0   | 136  | 6.2274          |
+| No log        | 9.0   | 153  | 6.1426          |
+| No log        | 10.0  | 170  | 6.0750          |
+| No log        | 11.0  | 187  | 6.0142          |
+| No log        | 12.0  | 204  | 5.9586          |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "danghuy1999/gpt2-viwiki",
+  "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": 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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f08607ac414fa25e8139856bdbbc2168aceca2694a6df56dbed5afc70501c7
+size 497774208

runs/Dec30_10-26-32_b2ab2675858f/events.out.tfevents.1735554393.b2ab2675858f.362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a9e8d70438ef50c0b929decb2630199bc07e2eef1e7f6fc72a1ee17daacf84
+size 5673

runs/Dec30_10-37-41_b2ab2675858f/events.out.tfevents.1735555062.b2ab2675858f.3261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec034fed21bfabfc5154f6c6c839d0da1f6c5ac787cc0b62c93e29bafecb4f4
+size 5791

runs/Dec30_11-01-41_b2ab2675858f/events.out.tfevents.1735556504.b2ab2675858f.9977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22c70ae340070dd4951338bdae7c9fbc5a77d6105460eb55eaaa867e9cb15f4
+size 5791

runs/Dec30_11-36-11_b2ab2675858f/events.out.tfevents.1735558573.b2ab2675858f.11857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9fcff51d8e69c0de676148d6449cf2e127ea2db546fd9724a938afd5ad535f
+size 9017

runs/Dec30_12-27-43_b2ab2675858f/events.out.tfevents.1735561664.b2ab2675858f.31967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab3a6095e64afefdbd90ddf0907057eda4677e4942e2d8f64677d414481859d
+size 8899

runs/Dec30_12-44-42_b2ab2675858f/events.out.tfevents.1735562684.b2ab2675858f.36127.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06cc3d61cbe25de04e741d96f3405da66fa204d094c76760cdd9e89736380f5
+size 6470

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026df79ea96a07de596515546a8d94d151f4612a00707659bcb75920afaf3ed1
+size 5368