Upload 32 files

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/rugpt3medium_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3medium_based_on_gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3529
+- Accuracy: 0.5525
+
+## 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 4.28.0.dev0
+- Pytorch 1.13.0
+- Datasets 2.1.0
+- Tokenizers 0.13.2

essays/added_tokens.json

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

essays/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5524600847181492,
+    "eval_loss": 2.352853775024414,
+    "eval_runtime": 3.3047,
+    "eval_samples": 18,
+    "eval_samples_per_second": 5.447,
+    "eval_steps_per_second": 5.447,
+    "perplexity": 10.515535919777124,
+    "train_loss": 2.2163170891839106,
+    "train_runtime": 371.3638,
+    "train_samples": 185,
+    "train_samples_per_second": 1.494,
+    "train_steps_per_second": 1.494
+}

essays/checkpoint-500/added_tokens.json

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

essays/checkpoint-500/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3medium_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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "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": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

essays/checkpoint-500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.0.dev0"
+}

essays/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918d50b58ee0cb8747805cae2e4a787f7ef848eb21c7f4da4c799d0f5193e4a5
+size 2847153349

essays/checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccec3a81bf5d2599586dde1be12e73b88f61be7901a0caa4c880d1f11998d0b
+size 1524265245

essays/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7131747db73d14f50009ddafb9783592fd9286191b52c4e70fed693af48eaf53
+size 14575

essays/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b355d81bdb20ea2acf79e39128e85de5aa051c9f16ee4faade2b6f23dbeada4
+size 627

essays/checkpoint-500/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
+  }
+}

essays/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

essays/checkpoint-500/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7027027027027026,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 2.2712,
+      "step": 500
+    }
+  ],
+  "max_steps": 555,
+  "num_train_epochs": 3,
+  "total_flos": 928700694528000.0,
+  "trial_name": null,
+  "trial_params": null
+}

essays/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59932aaaf017b52565ed949386730e8ba6500baffdb5bf042664bd41503926f8
+size 3579

essays/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3medium_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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "n_special": 0,
+  "output_past": true,
+  "predict_special_tokens": true,
+  "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": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

essays/eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.5524600847181492,
+    "eval_loss": 2.352853775024414,
+    "eval_runtime": 3.3047,
+    "eval_samples": 18,
+    "eval_samples_per_second": 5.447,
+    "eval_steps_per_second": 5.447,
+    "perplexity": 10.515535919777124
+}

essays/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.0.dev0"
+}

essays/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1807f8948208c0df1351973a78e3f1418d3c5d24ebf6eab692ca5af121486c
+size 1524265245

essays/runs/Apr06_11-49-42_c4a44d0e4fd9/1680781807.6289053/events.out.tfevents.1680781807.c4a44d0e4fd9.196.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b3ea5b3426894cca6236e1626971dd9c5083cedd79ff294a08f0c0e5d1cd79
+size 5816

essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680781807.c4a44d0e4fd9.196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc71a0de09ebbba3b212337071cdf09d5b2f3304d95ca78d4e3695a7865daeed
+size 4722

essays/runs/Apr06_11-49-42_c4a44d0e4fd9/events.out.tfevents.1680782185.c4a44d0e4fd9.196.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691fb419bdfe55603829db2d6d215564e29ba254de4b6905f8a916602d7c834e
+size 363

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
+  }
+}

essays/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "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,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

essays/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.2163170891839106,
+    "train_runtime": 371.3638,
+    "train_samples": 185,
+    "train_samples_per_second": 1.494,
+    "train_steps_per_second": 1.494
+}

essays/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 555,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 2.2712,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 555,
+      "total_flos": 1030857770926080.0,
+      "train_loss": 2.2163170891839106,
+      "train_runtime": 371.3638,
+      "train_samples_per_second": 1.494,
+      "train_steps_per_second": 1.494
+    }
+  ],
+  "max_steps": 555,
+  "num_train_epochs": 3,
+  "total_flos": 1030857770926080.0,
+  "trial_name": null,
+  "trial_params": null
+}

essays/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59932aaaf017b52565ed949386730e8ba6500baffdb5bf042664bd41503926f8
+size 3579