first upload

README.md

@@ -1,3 +1,57 @@
----
-license: apache-2.0
----
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: toxic_generator_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. -->
+
+# toxic_generator_model
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3880
+- Accuracy: 0.4552
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 40.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.4551971326164875,
+    "eval_loss": 3.3879826068878174,
+    "eval_runtime": 0.6202,
+    "eval_samples": 9,
+    "eval_samples_per_second": 14.512,
+    "eval_steps_per_second": 8.062,
+    "perplexity": 29.606164710375456,
+    "total_flos": 2884664033280000.0,
+    "train_loss": 1.075979393115942,
+    "train_runtime": 1098.0309,
+    "train_samples": 138,
+    "train_samples_per_second": 5.027,
+    "train_steps_per_second": 2.514
+}

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": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.4551971326164875,
+    "eval_loss": 3.3879826068878174,
+    "eval_runtime": 0.6202,
+    "eval_samples": 9,
+    "eval_samples_per_second": 14.512,
+    "eval_steps_per_second": 8.062,
+    "perplexity": 29.606164710375456
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef7be064efc06c3b3424b89c5e82b54d86e22388f22020d88afe04c74e36b0f
+size 497774208

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 40.0,
+    "total_flos": 2884664033280000.0,
+    "train_loss": 1.075979393115942,
+    "train_runtime": 1098.0309,
+    "train_samples": 138,
+    "train_samples_per_second": 5.027,
+    "train_steps_per_second": 2.514
+}

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 2760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 4.833008289337158,
+      "learning_rate": 4.094202898550725e-05,
+      "loss": 1.952,
+      "step": 500
+    },
+    {
+      "epoch": 14.492753623188406,
+      "grad_norm": 4.0949931144714355,
+      "learning_rate": 3.188405797101449e-05,
+      "loss": 1.3781,
+      "step": 1000
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 2.9236912727355957,
+      "learning_rate": 2.282608695652174e-05,
+      "loss": 0.9801,
+      "step": 1500
+    },
+    {
+      "epoch": 28.985507246376812,
+      "grad_norm": 2.521008014678955,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.7325,
+      "step": 2000
+    },
+    {
+      "epoch": 36.231884057971016,
+      "grad_norm": 2.6362154483795166,
+      "learning_rate": 4.710144927536232e-06,
+      "loss": 0.6039,
+      "step": 2500
+    },
+    {
+      "epoch": 40.0,
+      "step": 2760,
+      "total_flos": 2884664033280000.0,
+      "train_loss": 1.075979393115942,
+      "train_runtime": 1098.0309,
+      "train_samples_per_second": 5.027,
+      "train_steps_per_second": 2.514
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 2884664033280000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae976c09c53bdb05e8ca014460f2f59fa1cf06f8dd5c69036eb041f8d59908dc
+size 4984