Upload 19 files

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: spell
+  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. -->
+
+# spell
+
+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: 2.4051
+- Accuracy: 0.6097
+
+## 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.7.1+cu110
+- Datasets 2.9.0
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|endoftext|>": 50257,
+  "==>": 50258
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.609682229056006,
+    "eval_loss": 2.405073642730713,
+    "eval_runtime": 0.9514,
+    "eval_samples": 42,
+    "eval_samples_per_second": 44.146,
+    "eval_steps_per_second": 44.146,
+    "perplexity": 11.079246158085713,
+    "train_loss": 2.4779672030492494,
+    "train_runtime": 4952.7178,
+    "train_samples": 20804,
+    "train_samples_per_second": 12.602,
+    "train_steps_per_second": 12.602
+}

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": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.609682229056006,
+    "eval_loss": 2.405073642730713,
+    "eval_runtime": 0.9514,
+    "eval_samples": 42,
+    "eval_samples_per_second": 44.146,
+    "eval_steps_per_second": 44.146,
+    "perplexity": 11.079246158085713
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4a21309fe0ee749687abf15f5700d13f1593f5d808c8e5f0a637556d114937
+size 551315232

runs/Feb04_10-45-09_anaslan/1675507566.4468966/events.out.tfevents.1675507566.anaslan.31123.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401f896bad692803325efd1da7fad841ad5a6bfc2bb7700a0a55633b67b69df6
+size 5707

runs/Feb04_10-45-09_anaslan/events.out.tfevents.1675507566.anaslan.31123.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d4f57f979549f330ba0f6689c6bc55af9be632da989d8faeb4e7d8950a92f2
+size 12638

runs/Feb04_10-47-45_anaslan/1675507678.0166109/events.out.tfevents.1675507678.anaslan.31153.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e815f837c4dca0f42422733aca60ca1441837afec89f48812937d67918e07c
+size 5707

runs/Feb04_10-47-45_anaslan/events.out.tfevents.1675507677.anaslan.31153.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dba686e1fff57906f672e7973e06f1e6b9fc8d31173c6be735e732ee1fc3dd8
+size 11383

runs/Feb04_10-48-56_anaslan/1675507748.4822354/events.out.tfevents.1675507748.anaslan.31175.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cb52ea6f15496e26e59e99f24320d88cff027a8611f0643de8683e080100d3
+size 5707

runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675507748.anaslan.31175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc53afde625d2e4280e25b5b83cc30e3869070d4b4baf83fd457d315df28fd03
+size 998011

runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675512703.anaslan.31175.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50192c45759dbe3c307ac12c6c59e2823c1a8318bb26325271c160d47d49b29e
+size 369

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "sep_token": "==>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
+  "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
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.4779672030492494,
+    "train_runtime": 4952.7178,
+    "train_samples": 20804,
+    "train_samples_per_second": 12.602,
+    "train_steps_per_second": 12.602
+}