Model save

README.md

@@ -0,0 +1,58 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: gpt2-cpt-dutch
+  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. -->
+
+# gpt2-cpt-dutch
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 684585123840000.0,
+    "train_loss": 4.120773559663354,
+    "train_runtime": 120.6544,
+    "train_samples": 32152,
+    "train_samples_per_second": 10.857,
+    "train_steps_per_second": 0.68
+}

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": "4.40.2",
+  "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": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d247bcd3ccd7f7ec05f948ad46f8c74999182be2346aeb1fb98f1b5f879f7e1
+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": true,
+  "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": 684585123840000.0,
+    "train_loss": 4.120773559663354,
+    "train_runtime": 120.6544,
+    "train_samples": 32152,
+    "train_samples_per_second": 10.857,
+    "train_steps_per_second": 0.68
+}

trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 82,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012195121951219513,
+      "grad_norm": 10.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 4.6342,
+      "step": 1
+    },
+    {
+      "epoch": 0.06097560975609756,
+      "grad_norm": 8.5,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 4.6731,
+      "step": 5
+    },
+    {
+      "epoch": 0.12195121951219512,
+      "grad_norm": 3.34375,
+      "learning_rate": 0.00019990741151022301,
+      "loss": 4.3963,
+      "step": 10
+    },
+    {
+      "epoch": 0.18292682926829268,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00019668478136052774,
+      "loss": 4.2375,
+      "step": 15
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00018900275764346768,
+      "loss": 4.1537,
+      "step": 20
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00017721565844991643,
+      "loss": 4.1163,
+      "step": 25
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00016186714032625035,
+      "loss": 4.0943,
+      "step": 30
+    },
+    {
+      "epoch": 0.4268292682926829,
+      "grad_norm": 1.9375,
+      "learning_rate": 0.0001436651231956064,
+      "loss": 4.0725,
+      "step": 35
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 1.8515625,
+      "learning_rate": 0.00012344913895704097,
+      "loss": 4.0395,
+      "step": 40
+    },
+    {
+      "epoch": 0.5487804878048781,
+      "grad_norm": 1.6328125,
+      "learning_rate": 0.00010215160974362223,
+      "loss": 4.0439,
+      "step": 45
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 1.625,
+      "learning_rate": 8.075484180291701e-05,
+      "loss": 4.0223,
+      "step": 50
+    },
+    {
+      "epoch": 0.6707317073170732,
+      "grad_norm": 1.7265625,
+      "learning_rate": 6.024571857174443e-05,
+      "loss": 4.0318,
+      "step": 55
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.1570182637163155e-05,
+      "loss": 4.0052,
+      "step": 60
+    },
+    {
+      "epoch": 0.7926829268292683,
+      "grad_norm": 1.7421875,
+      "learning_rate": 2.5589606012863963e-05,
+      "loss": 4.0278,
+      "step": 65
+    },
+    {
+      "epoch": 0.8536585365853658,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.30410610653389e-05,
+      "loss": 4.019,
+      "step": 70
+    },
+    {
+      "epoch": 0.9146341463414634,
+      "grad_norm": 1.609375,
+      "learning_rate": 4.503324514474483e-06,
+      "loss": 4.0281,
+      "step": 75
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.609375,
+      "learning_rate": 3.701825065392184e-07,
+      "loss": 4.0339,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "step": 82,
+      "total_flos": 684585123840000.0,
+      "train_loss": 4.120773559663354,
+      "train_runtime": 120.6544,
+      "train_samples_per_second": 10.857,
+      "train_steps_per_second": 0.68
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 82,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 684585123840000.0,
+  "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 sha256:14a58caf7cfe2d00aff9be0bbb296e554d9ad71d260085b3e7f500ade161affb
+size 5048