Upload 15 files

models/essays/README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: essays
+  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. -->
+
+# essays
+
+This model is a fine-tuned version of [sberbank-ai/rugpt3small_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3small_based_on_gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7676
+- Accuracy: 0.4758
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.29.0.dev0
+- Pytorch 1.9.1+cu111
+- Datasets 2.11.0
+- Tokenizers 0.13.3

models/essays/added_tokens.json

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

models/essays/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.4757639906638441,
+    "eval_loss": 2.767648458480835,
+    "eval_runtime": 1.0081,
+    "eval_samples": 9,
+    "eval_samples_per_second": 8.928,
+    "eval_steps_per_second": 8.928,
+    "perplexity": 15.921150708373386,
+    "train_loss": 2.7605772156646284,
+    "train_runtime": 87.21,
+    "train_samples": 92,
+    "train_samples_per_second": 3.165,
+    "train_steps_per_second": 3.165
+}

models/essays/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
+  "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,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

models/essays/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.4757639906638441,
+    "eval_loss": 2.767648458480835,
+    "eval_runtime": 1.0081,
+    "eval_samples": 9,
+    "eval_samples_per_second": 8.928,
+    "eval_steps_per_second": 8.928,
+    "perplexity": 15.921150708373386
+}

models/essays/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.29.0.dev0"
+}

models/essays/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f145dc6ca97655187b357bc9b9484ecde90f445362bae691bc45c2faf0d587
+size 551312489

models/essays/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/essays/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/essays/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.7605772156646284,
+    "train_runtime": 87.21,
+    "train_samples": 92,
+    "train_samples_per_second": 3.165,
+    "train_steps_per_second": 3.165
+}

models/essays/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 276,
+      "total_flos": 288466403328000.0,
+      "train_loss": 2.7605772156646284,
+      "train_runtime": 87.21,
+      "train_samples_per_second": 3.165,
+      "train_steps_per_second": 3.165
+    }
+  ],
+  "max_steps": 276,
+  "num_train_epochs": 3,
+  "total_flos": 288466403328000.0,
+  "trial_name": null,
+  "trial_params": null
+}

models/essays/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc90d13a3c1e167dedc3e673a03634beb1998f6a5a2653d6c61b9729498f4d7
+size 3567