Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: gpt2
+library_name: transformers
+model_name: gpt2-cpt-dutch
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gpt2-cpt-dutch
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Alqayed2024/gpt2-cpt-dutch", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/ktrmzdcf)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.0
+- Transformers: 4.46.1
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2783887138750464.0,
+    "train_loss": 0.0,
+    "train_runtime": 2.3096,
+    "train_samples": 12593,
+    "train_samples_per_second": 4599.857,
+    "train_steps_per_second": 71.873
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e56ad414e88a43f621e6e58d714e9fa67975af8ef1c5bcfebe07217baca59f
+size 248894656

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2783887138750464.0,
+    "train_loss": 0.0,
+    "train_runtime": 2.3096,
+    "train_samples": 12593,
+    "train_samples_per_second": 4599.857,
+    "train_steps_per_second": 71.873
+}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012048192771084338,
+      "grad_norm": 5.144875488861497,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 5.2383,
+      "step": 1
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 4.400640807642775,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 5.1426,
+      "step": 5
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 2.8424185774279995,
+      "learning_rate": 0.00019990989662046818,
+      "loss": 4.9195,
+      "step": 10
+    },
+    {
+      "epoch": 0.18072289156626506,
+      "grad_norm": 2.1742733252180533,
+      "learning_rate": 0.0001967732946933499,
+      "loss": 4.5773,
+      "step": 15
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 2.0811257888315406,
+      "learning_rate": 0.00018929258581495685,
+      "loss": 4.3453,
+      "step": 20
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "grad_norm": 1.3196766642254727,
+      "learning_rate": 0.00017780357543184397,
+      "loss": 4.1766,
+      "step": 25
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 1.7074769394742433,
+      "learning_rate": 0.00016282199972956425,
+      "loss": 4.0355,
+      "step": 30
+    },
+    {
+      "epoch": 0.42168674698795183,
+      "grad_norm": 1.786794986516103,
+      "learning_rate": 0.00014502037448176734,
+      "loss": 3.9418,
+      "step": 35
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 1.712555578478064,
+      "learning_rate": 0.00012519780613851254,
+      "loss": 3.8637,
+      "step": 40
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 1.1317257705596584,
+      "learning_rate": 0.00010424412031961484,
+      "loss": 3.8164,
+      "step": 45
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 0.8808395413039651,
+      "learning_rate": 8.309991796781511e-05,
+      "loss": 3.7855,
+      "step": 50
+    },
+    {
+      "epoch": 0.6626506024096386,
+      "grad_norm": 0.9070705182297121,
+      "learning_rate": 6.271435222196916e-05,
+      "loss": 3.7594,
+      "step": 55
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.800430133148163,
+      "learning_rate": 4.4002521386240466e-05,
+      "loss": 3.723,
+      "step": 60
+    },
+    {
+      "epoch": 0.7831325301204819,
+      "grad_norm": 0.9084524552496485,
+      "learning_rate": 2.7804390604547557e-05,
+      "loss": 3.7258,
+      "step": 65
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 0.7470706061804011,
+      "learning_rate": 1.4847086226668872e-05,
+      "loss": 3.6902,
+      "step": 70
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 0.697773024233771,
+      "learning_rate": 5.71225545389158e-06,
+      "loss": 3.691,
+      "step": 75
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.70777044124217,
+      "learning_rate": 8.099564741123166e-07,
+      "loss": 3.6707,
+      "step": 80
+    },
+    {
+      "epoch": 0.5120481927710844,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 3.6468,
+      "step": 85
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 0.89453125,
+      "learning_rate": 8.23529411764706e-05,
+      "loss": 3.6491,
+      "step": 90
+    },
+    {
+      "epoch": 0.572289156626506,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 3.6893,
+      "step": 95
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0002,
+      "loss": 3.6404,
+      "step": 100
+    },
+    {
+      "epoch": 0.6325301204819277,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.00019944481853548335,
+      "loss": 3.6761,
+      "step": 105
+    },
+    {
+      "epoch": 0.6626506024096386,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.00019778543867110426,
+      "loss": 3.6328,
+      "step": 110
+    },
+    {
+      "epoch": 0.6927710843373494,
+      "grad_norm": 0.91796875,
+      "learning_rate": 0.00019504028554572864,
+      "loss": 3.6478,
+      "step": 115
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019123984032200586,
+      "loss": 3.6035,
+      "step": 120
+    },
+    {
+      "epoch": 0.7530120481927711,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.00018642630173483832,
+      "loss": 3.6189,
+      "step": 125
+    },
+    {
+      "epoch": 0.7831325301204819,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00018065311753227273,
+      "loss": 3.6364,
+      "step": 130
+    },
+    {
+      "epoch": 0.8132530120481928,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00017398439101151905,
+      "loss": 3.6213,
+      "step": 135
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.0001664941692397025,
+      "loss": 3.558,
+      "step": 140
+    },
+    {
+      "epoch": 0.8734939759036144,
+      "grad_norm": 0.91796875,
+      "learning_rate": 0.00015826562086267956,
+      "loss": 3.5992,
+      "step": 145
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.00014939011263122634,
+      "loss": 3.5675,
+      "step": 150
+    },
+    {
+      "epoch": 0.9337349397590361,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00013996619489850822,
+      "loss": 3.5625,
+      "step": 155
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.0001300985073534919,
+      "loss": 3.5525,
+      "step": 160
+    },
+    {
+      "epoch": 0.9939759036144579,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.00011989661714062999,
+      "loss": 3.5954,
+      "step": 165
+    },
+    {
+      "epoch": 1.0,
+      "step": 166,
+      "total_flos": 2783887138750464.0,
+      "train_loss": 0.0,
+      "train_runtime": 2.3096,
+      "train_samples_per_second": 4599.857,
+      "train_steps_per_second": 71.873
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 166,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2783887138750464.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254c3e3d20e04fa0c4beda434fb7b4b9427a6569237f0da874cfa5e1e5f6a50e
+size 5752