Upload 14 files

README.md

@@ -1,3 +1,57 @@
 ---
 license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: artgpt
+  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. -->
+
+# artgpt
+
+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: 60.5072
+- Accuracy: 0.0
+
+## 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 4.37.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.0,
+    "eval_loss": 60.507171630859375,
+    "eval_runtime": 2.1604,
+    "eval_samples": 4,
+    "eval_samples_per_second": 1.851,
+    "eval_steps_per_second": 0.926,
+    "perplexity": 1.8964035291436836e+26,
+    "train_loss": 58.570675893930286,
+    "train_runtime": 5757.0891,
+    "train_samples": 78,
+    "train_samples_per_second": 0.542,
+    "train_steps_per_second": 0.271
+}

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": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.0,
+    "eval_loss": 60.507171630859375,
+    "eval_runtime": 2.1604,
+    "eval_samples": 4,
+    "eval_samples_per_second": 1.851,
+    "eval_steps_per_second": 0.926,
+    "perplexity": 1.8964035291436836e+26
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b3865084cdafe4342279733148472e00cd2bb362e20c47bbfbd2e76d2ace55
+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 +1,8 @@
+{
+    "epoch": 40.0,
+    "train_loss": 58.570675893930286,
+    "train_runtime": 5757.0891,
+    "train_samples": 78,
+    "train_samples_per_second": 0.542,
+    "train_steps_per_second": 0.271
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 1560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.82,
+      "learning_rate": 3.397435897435898e-05,
+      "loss": 57.3349,
+      "step": 500
+    },
+    {
+      "epoch": 25.64,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 60.598,
+      "step": 1000
+    },
+    {
+      "epoch": 38.46,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 57.9515,
+      "step": 1500
+    },
+    {
+      "epoch": 40.0,
+      "step": 1560,
+      "total_flos": 1630462279680000.0,
+      "train_loss": 58.570675893930286,
+      "train_runtime": 5757.0891,
+      "train_samples_per_second": 0.542,
+      "train_steps_per_second": 0.271
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 1630462279680000.0,
+  "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 sha256:1a070211ff7c023c343776f0db501684b80e80c3dc9f4807beac8922744e1a28
+size 4664